.env.example

@@ -10,8 +10,3 @@ OPENAI_API_KEY=''
 # DO NOT TRACK
 SCARF_NO_ANALYTICS=true
 DO_NOT_TRACK=true
-ANONYMIZED_TELEMETRY=false
-
-# Use locally bundled version of the LiteLLM cost map json
-# to avoid repetitive startup connections
-LITELLM_LOCAL_MODEL_COST_MAP="True"

.eslintrc.cjs

@@ -4,7 +4,6 @@ module.exports = {
 		'eslint:recommended',
 		'plugin:@typescript-eslint/recommended',
 		'plugin:svelte/recommended',
-		'plugin:cypress/recommended',
 		'prettier'
 	],
 	parser: '@typescript-eslint/parser',

.github/ISSUE_TEMPLATE/bug_report.md

@@ -24,9 +24,6 @@ assignees: ''
 
 ## Environment
 
-- **Open WebUI Version:** [e.g., 0.1.120]
-- **Ollama (if applicable):** [e.g., 0.1.30, 0.1.32-rc1]
-
 - **Operating System:** [e.g., Windows 10, macOS Big Sur, Ubuntu 20.04]
 - **Browser (if applicable):** [e.g., Chrome 100.0, Firefox 98.0]
 

.github/dependabot.yml

@@ -1,11 +0,0 @@
-version: 2
-updates:
-- package-ecosystem: pip
-  directory: "/backend"
-  schedule:
-    interval: daily
-    time: "13:00"
-  groups:
-    python-packages:
-      patterns:
-        - "*"

.github/pull_request_template.md

@@ -2,16 +2,14 @@
 
 - [ ] **Description:** Briefly describe the changes in this pull request.
 - [ ] **Changelog:** Ensure a changelog entry following the format of [Keep a Changelog](https://keepachangelog.com/) is added at the bottom of the PR description.
-- [ ] **Documentation:** Have you updated relevant documentation [Open WebUI Docs](https://github.com/open-webui/docs), or other documentation sources?
+- [ ] **Documentation:** Have you updated relevant documentation?
 - [ ] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation?
-- [ ] **Testing:** Have you written and run sufficient tests for the changes?
-- [ ] **Code Review:** Have you self-reviewed your code and addressed any coding standard issues?
 
 ---
 
 ## Description
 
-[Insert a brief description of the changes made in this pull request, including any relevant motivation and impact.]
+[Insert a brief description of the changes made in this pull request]
 
 ---
 
@@ -19,32 +17,16 @@
 
 ### Added
 
-- [List any new features, functionalities, or additions]
+- [List any new features or additions]
 
 ### Fixed
 
-- [List any fixes, corrections, or bug fixes]
+- [List any fixes or corrections]
 
 ### Changed
 
-- [List any changes, updates, refactorings, or optimizations]
+- [List any changes or updates]
 
 ### Removed
 
-- [List any removed features, files, or deprecated functionalities]
+- [List any removed features or files]
-
-### Security
-
-- [List any new or updated security-related changes, including vulnerability fixes]
-
-### Breaking Changes
-
-- [List any breaking changes affecting compatibility or functionality]
-
----
-
-### Additional Information
-
-- [Insert any additional context, notes, or explanations for the changes]
-
-- [Reference any related issues, commits, or other relevant information]

.github/workflows/build-release.yml

@@ -57,14 +57,3 @@ jobs:
         path: .
       env:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-    - name: Trigger Docker build workflow
-      uses: actions/github-script@v7
-      with:
-        script: |
-          github.rest.actions.createWorkflowDispatch({
-            owner: context.repo.owner,
-            repo: context.repo.repo,
-            workflow_id: 'docker-build.yaml',
-            ref: 'v${{ steps.get_version.outputs.version }}',
-          })

.github/workflows/docker-build.yaml

@@ -1,7 +1,8 @@
-name: Create and publish Docker images with specific build args
+#
+name: Create and publish a Docker image
 
+# Configures this workflow to run every time a change is pushed to the branch called `release`.
 on:
-  workflow_dispatch:
   push:
     branches:
       - main
@@ -9,55 +10,43 @@ on:
     tags:
       - v*
 
+# Defines two custom environment variables for the workflow. These are used for the Container registry domain, and a name for the Docker image that this workflow builds.
 env:
-  REGISTRY: git.depeuter.dev
+  REGISTRY: ghcr.io
   IMAGE_NAME: ${{ github.repository }}
-  RUNNER_TOOL_CACHE: /toolcache
-  FULL_IMAGE_NAME: ${{ env.REGISTRY }}/${{ github.repository }}
 
+# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
 jobs:
-  build-main-image:
+  build-and-push-image:
     runs-on: ubuntu-latest
-    container:
-      image: catthehacker/ubuntu:act-latest
     # Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
     permissions:
       contents: read
       packages: write
-    strategy:
+      #
-      fail-fast: false
-      matrix:
-        platform:
-          - linux/amd64
-          - linux/arm64
-
     steps:
-      - name: Prepare
-        run: |
-          platform=${{ matrix.platform }}
-          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
-
       - name: Checkout repository
         uses: actions/checkout@v4
-
+      # Required for multi architecture build
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v3
-
+      # Required for multi architecture build
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
-
+      # Uses the `docker/login-action` action to log in to the Container registry registry using the account and password that will publish the packages. Once published, the packages are scoped to the account defined here.
       - name: Log in to the Container registry
         uses: docker/login-action@v3
         with:
           registry: ${{ env.REGISTRY }}
           username: ${{ github.actor }}
-          password: ${{ secrets.CI_TOKEN }}
+          password: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Extract metadata for Docker images (default latest tag)
+      - name: Extract metadata for Docker images
         id: meta
         uses: docker/metadata-action@v5
         with:
-          images: ${{ env.FULL_IMAGE_NAME }}
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          # This configuration dynamically generates tags based on the branch, tag, commit, and custom suffix for lite version.
           tags: |
             type=ref,event=branch
             type=ref,event=tag
@@ -67,322 +56,11 @@ jobs:
           flavor: |
             latest=${{ github.ref == 'refs/heads/main' }}
 
-      - name: Build Docker image (latest)
+      - name: Build and push Docker image
         uses: docker/build-push-action@v5
-        id: build
         with:
           context: .
           push: true
-          platforms: ${{ matrix.platform }}
+          platforms: linux/amd64,linux/arm64
+          tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
-          outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-
-      - name: Export digest
-        run: |
-          mkdir -p /tmp/digests
-          digest="${{ steps.build.outputs.digest }}"
-          touch "/tmp/digests/${digest#sha256:}"
-
-      - name: Upload digest
-        uses: actions/upload-artifact@v4
-        with:
-          name: digests-main-${{ env.PLATFORM_PAIR }}
-          path: /tmp/digests/*
-          if-no-files-found: error
-          retention-days: 1
-
-  build-cuda-image:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    strategy:
-      fail-fast: false
-      matrix:
-        platform:
-          - linux/amd64
-          - linux/arm64
-
-    steps:
-      - name: Prepare
-        run: |
-          platform=${{ matrix.platform }}
-          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
-
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@v3
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.CI_TOKEN }}
-
-      - name: Extract metadata for Docker images (default latest tag)
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ env.FULL_IMAGE_NAME }}
-          tags: |
-            type=ref,event=branch
-            type=ref,event=tag
-            type=sha,prefix=git-
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-            type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=cuda
-          flavor: |
-            latest=${{ github.ref == 'refs/heads/main' }}
-            suffix=-cuda,onlatest=true
-
-      - name: Build Docker image (cuda)
-        uses: docker/build-push-action@v5
-        id: build
-        with:
-          context: .
-          push: true
-          platforms: ${{ matrix.platform }}
-          labels: ${{ steps.meta.outputs.labels }}
-          outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-          build-args: USE_CUDA=true
-
-      - name: Export digest
-        run: |
-          mkdir -p /tmp/digests
-          digest="${{ steps.build.outputs.digest }}"
-          touch "/tmp/digests/${digest#sha256:}"
-
-      - name: Upload digest
-        uses: actions/upload-artifact@v4
-        with:
-          name: digests-cuda-${{ env.PLATFORM_PAIR }}
-          path: /tmp/digests/*
-          if-no-files-found: error
-          retention-days: 1
-
-  build-ollama-image:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    strategy:
-      fail-fast: false
-      matrix:
-        platform:
-          - linux/amd64
-          - linux/arm64
-
-    steps:
-      - name: Prepare
-        run: |
-          platform=${{ matrix.platform }}
-          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
-
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@v3
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.CI_TOKEN }}
-
-      - name: Extract metadata for Docker images (ollama tag)
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ env.FULL_IMAGE_NAME }}
-          tags: |
-            type=ref,event=branch
-            type=ref,event=tag
-            type=sha,prefix=git-
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-            type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=ollama
-          flavor: |
-            latest=${{ github.ref == 'refs/heads/main' }}
-            suffix=-ollama,onlatest=true
-
-      - name: Build Docker image (ollama)
-        uses: docker/build-push-action@v5
-        id: build
-        with:
-          context: .
-          push: true
-          platforms: ${{ matrix.platform }}
-          labels: ${{ steps.meta.outputs.labels }}
-          outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-          build-args: USE_OLLAMA=true
-
-      - name: Export digest
-        run: |
-          mkdir -p /tmp/digests
-          digest="${{ steps.build.outputs.digest }}"
-          touch "/tmp/digests/${digest#sha256:}"
-
-      - name: Upload digest
-        uses: actions/upload-artifact@v4
-        with:
-          name: digests-ollama-${{ env.PLATFORM_PAIR }}
-          path: /tmp/digests/*
-          if-no-files-found: error
-          retention-days: 1
-
-  merge-main-images:
-    runs-on: ubuntu-latest
-    needs: [ build-main-image ]
-    steps:
-      - name: Download digests
-        uses: actions/download-artifact@v4
-        with:
-          pattern: digests-main-*
-          path: /tmp/digests
-          merge-multiple: true
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@v3
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.CI_TOKEN }}
-
-      - name: Extract metadata for Docker images (default latest tag)
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ env.FULL_IMAGE_NAME }}
-          tags: |
-            type=ref,event=branch
-            type=ref,event=tag
-            type=sha,prefix=git-
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-          flavor: |
-            latest=${{ github.ref == 'refs/heads/main' }}
-
-      - name: Create manifest list and push
-        working-directory: /tmp/digests
-        run: |
-          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
-            $(printf '${{ env.FULL_IMAGE_NAME }}@sha256:%s ' *)
-
-      - name: Inspect image
-        run: |
-          docker buildx imagetools inspect ${{ env.FULL_IMAGE_NAME }}:${{ steps.meta.outputs.version }}
-
-
-  merge-cuda-images:
-    runs-on: ubuntu-latest
-    needs: [ build-cuda-image ]
-    steps:
-      - name: Download digests
-        uses: actions/download-artifact@v4
-        with:
-          pattern: digests-cuda-*
-          path: /tmp/digests
-          merge-multiple: true
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@v3
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.CI_TOKEN }}
-
-      - name: Extract metadata for Docker images (default latest tag)
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ env.FULL_IMAGE_NAME }}
-          tags: |
-            type=ref,event=branch
-            type=ref,event=tag
-            type=sha,prefix=git-
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-            type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=cuda
-          flavor: |
-            latest=${{ github.ref == 'refs/heads/main' }}
-            suffix=-cuda,onlatest=true
-
-      - name: Create manifest list and push
-        working-directory: /tmp/digests
-        run: |
-          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
-            $(printf '${{ env.FULL_IMAGE_NAME }}@sha256:%s ' *)
-
-      - name: Inspect image
-        run: |
-          docker buildx imagetools inspect ${{ env.FULL_IMAGE_NAME }}:${{ steps.meta.outputs.version }}
-
-  merge-ollama-images:
-    runs-on: ubuntu-latest
-    needs: [ build-ollama-image ]
-    steps:
-      - name: Download digests
-        uses: actions/download-artifact@v4
-        with:
-          pattern: digests-ollama-*
-          path: /tmp/digests
-          merge-multiple: true
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@v3
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.CI_TOKEN }}
-
-      - name: Extract metadata for Docker images (default ollama tag)
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ env.FULL_IMAGE_NAME }}
-          tags: |
-            type=ref,event=branch
-            type=ref,event=tag
-            type=sha,prefix=git-
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-            type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=ollama
-          flavor: |
-            latest=${{ github.ref == 'refs/heads/main' }}
-            suffix=-ollama,onlatest=true
-
-      - name: Create manifest list and push
-        working-directory: /tmp/digests
-        run: |
-          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
-            $(printf '${{ env.FULL_IMAGE_NAME }}@sha256:%s ' *)
-
-      - name: Inspect image
-        run: |
-          docker buildx imagetools inspect ${{ env.FULL_IMAGE_NAME }}:${{ steps.meta.outputs.version }}

.github/workflows/format-backend.yaml

@@ -1,39 +1,27 @@
 name: Python CI
-
 on:
   push:
-    branches:
+    branches: ['main']
-      - main
-      - dev
   pull_request:
-    branches:
-      - main
-      - dev
-
 jobs:
   build:
     name: 'Format Backend'
+    env:
+      PUBLIC_API_BASE_URL: ''
     runs-on: ubuntu-latest
-
     strategy:
       matrix:
-        python-version: [3.11]
+        node-version:
-
+          - latest
     steps:
       - uses: actions/checkout@v4
-
+      - name: Use Python
-      - name: Set up Python
+        uses: actions/setup-python@v4
-        uses: actions/setup-python@v2
+      - name: Use Bun
-        with:
+        uses: oven-sh/setup-bun@v1
-          python-version: ${{ matrix.python-version }}
-
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install black
+          pip install yapf
-
       - name: Format backend
-        run: npm run format:backend
+        run: bun run format:backend
-
-      - name: Check for changes after format
-        run: git diff --exit-code

.github/workflows/format-build-frontend.yaml

@@ -1,39 +1,22 @@
-name: Frontend Build
+name: Bun CI
-
 on:
   push:
-    branches:
+    branches: ['main']
-      - main
-      - dev
   pull_request:
-    branches:
-      - main
-      - dev
-
 jobs:
   build:
     name: 'Format & Build Frontend'
+    env:
+      PUBLIC_API_BASE_URL: ''
     runs-on: ubuntu-latest
     steps:
-      - name: Checkout Repository
+      - uses: actions/checkout@v4
-        uses: actions/checkout@v4
+      - name: Use Bun
-
+        uses: oven-sh/setup-bun@v1
-      - name: Setup Node.js
+      - run: bun --version
-        uses: actions/setup-node@v3
+      - name: Install frontend dependencies
-        with:
+        run: bun install
-          node-version: '20' # Or specify any other version you want to use
+      - name: Format frontend
-
+        run: bun run format
-      - name: Install Dependencies
+      - name: Build frontend
-        run: npm install
+        run: bun run build
-
-      - name: Format Frontend
-        run: npm run format
-
-      - name: Run i18next
-        run: npm run i18n:parse
-
-      - name: Check for Changes After Format
-        run: git diff --exit-code
-
-      - name: Build Frontend
-        run: npm run build

.github/workflows/integration-test.yml

@@ -1,186 +0,0 @@
-name: Integration Test
-
-on:
-  push:
-    branches:
-      - main
-      - dev
-  pull_request:
-    branches:
-      - main
-      - dev
-
-jobs:
-  cypress-run:
-    name: Run Cypress Integration Tests
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout Repository
-        uses: actions/checkout@v4
-
-      - name: Build and run Compose Stack
-        run: |
-          docker compose up --detach --build
-
-      - name: Preload Ollama model
-        run: |
-          docker exec ollama ollama pull qwen:0.5b-chat-v1.5-q2_K
-
-      - name: Cypress run
-        uses: cypress-io/github-action@v6
-        with:
-          browser: chrome
-          wait-on: 'http://localhost:3000'
-          config: baseUrl=http://localhost:3000
-
-      - uses: actions/upload-artifact@v4
-        if: always()
-        name: Upload Cypress videos
-        with:
-          name: cypress-videos
-          path: cypress/videos
-          if-no-files-found: ignore
-
-      - name: Extract Compose logs
-        if: always()
-        run: |
-          docker compose logs > compose-logs.txt
-
-      - uses: actions/upload-artifact@v4
-        if: always()
-        name: Upload Compose logs
-        with:
-          name: compose-logs
-          path: compose-logs.txt
-          if-no-files-found: ignore
-
-  migration_test:
-    name: Run Migration Tests
-    runs-on: ubuntu-latest
-    services:
-      postgres:
-        image: postgres
-        env:
-          POSTGRES_PASSWORD: postgres
-        options: >-
-          --health-cmd pg_isready
-          --health-interval 10s
-          --health-timeout 5s
-          --health-retries 5
-        ports:
-          - 5432:5432
-#      mysql:
-#        image: mysql
-#        env:
-#          MYSQL_ROOT_PASSWORD: mysql
-#          MYSQL_DATABASE: mysql
-#        options: >-
-#          --health-cmd "mysqladmin ping -h localhost"
-#          --health-interval 10s
-#          --health-timeout 5s
-#          --health-retries 5
-#        ports:
-#          - 3306:3306
-    steps:
-      - name: Checkout Repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v2
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: Set up uv
-        uses: yezz123/setup-uv@v4
-        with:
-          uv-venv: venv
-
-      - name: Activate virtualenv
-        run: |
-          . venv/bin/activate
-          echo PATH=$PATH >> $GITHUB_ENV
-
-      - name: Install dependencies
-        run: |
-          uv pip install -r backend/requirements.txt
-
-      - name: Test backend with SQLite
-        id: sqlite
-        env:
-          WEBUI_SECRET_KEY: secret-key
-          GLOBAL_LOG_LEVEL: debug
-        run: |
-          cd backend
-          uvicorn main:app --port "8080" --forwarded-allow-ips '*' &
-          UVICORN_PID=$!
-          # Wait up to 20 seconds for the server to start
-          for i in {1..20}; do
-              curl -s http://localhost:8080/api/config > /dev/null && break
-              sleep 1
-              if [ $i -eq 20 ]; then
-                  echo "Server failed to start"
-                  kill -9 $UVICORN_PID
-                  exit 1
-              fi
-          done
-          # Check that the server is still running after 5 seconds
-          sleep 5
-          if ! kill -0 $UVICORN_PID; then
-              echo "Server has stopped"
-              exit 1
-          fi
-          
-
-      - name: Test backend with Postgres
-        if: success() || steps.sqlite.conclusion == 'failure'
-        env:
-          WEBUI_SECRET_KEY: secret-key
-          GLOBAL_LOG_LEVEL: debug
-          DATABASE_URL: postgresql://postgres:postgres@localhost:5432/postgres
-        run: |
-          cd backend
-          uvicorn main:app --port "8081" --forwarded-allow-ips '*' &
-          UVICORN_PID=$!
-          # Wait up to 20 seconds for the server to start
-          for i in {1..20}; do
-              curl -s http://localhost:8081/api/config > /dev/null && break
-              sleep 1
-              if [ $i -eq 20 ]; then
-                  echo "Server failed to start"
-                  kill -9 $UVICORN_PID
-                  exit 1
-              fi
-          done
-          # Check that the server is still running after 5 seconds
-          sleep 5
-          if ! kill -0 $UVICORN_PID; then
-              echo "Server has stopped"
-              exit 1
-          fi
-
-#      - name: Test backend with MySQL
-#        if: success() || steps.sqlite.conclusion == 'failure' || steps.postgres.conclusion == 'failure'
-#        env:
-#          WEBUI_SECRET_KEY: secret-key
-#          GLOBAL_LOG_LEVEL: debug
-#          DATABASE_URL: mysql://root:mysql@localhost:3306/mysql
-#        run: |
-#          cd backend
-#          uvicorn main:app --port "8083" --forwarded-allow-ips '*' &
-#          UVICORN_PID=$!
-#          # Wait up to 20 seconds for the server to start
-#          for i in {1..20}; do
-#              curl -s http://localhost:8083/api/config > /dev/null && break
-#              sleep 1
-#              if [ $i -eq 20 ]; then
-#                  echo "Server failed to start"
-#                  kill -9 $UVICORN_PID
-#                  exit 1
-#              fi
-#          done
-#          # Check that the server is still running after 5 seconds
-#          sleep 5
-#          if ! kill -0 $UVICORN_PID; then
-#              echo "Server has stopped"
-#              exit 1
-#          fi

.gitignore

@@ -166,7 +166,7 @@ cython_debug/
 #  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-.idea/
+#.idea/
 
 # Logs
 logs
@@ -298,7 +298,3 @@ dist
 .yarn/build-state.yml
 .yarn/install-state.gz
 .pnp.*
-
-# cypress artifacts
-cypress/videos
-cypress/screenshots

CHANGELOG.md

@@ -5,240 +5,6 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [0.1.123] - 2024-05-02
-
-### Added
-
-- **🎨 New Landing Page Design**: Refreshed design for a more modern look and optimized use of screen space.
-- **📹 Youtube RAG Pipeline**: Introduces dedicated RAG pipeline for Youtube videos, enabling interaction with video transcriptions directly.
-- **🔧 Enhanced Admin Panel**: Streamlined user management with options to add users directly or in bulk via CSV import.
-- **👥 '@' Model Integration**: Easily switch to specific models during conversations; old collaborative chat feature phased out.
-- **🌐 Language Enhancements**: Swedish translation added, plus improvements to German, Spanish, and the addition of Doge translation.
-
-### Fixed
-
-- **🗑️ Delete Chat Shortcut**: Addressed issue where shortcut wasn't functioning.
-- **🖼️ Modal Closing Bug**: Resolved unexpected closure of modal when dragging from within.
-- **✏️ Edit Button Styling**: Fixed styling inconsistency with edit buttons.
-- **🌐 Image Generation Compatibility Issue**: Rectified image generation compatibility issue with third-party APIs.
-- **📱 iOS PWA Icon Fix**: Corrected iOS PWA home screen icon shape.
-- **🔍 Scroll Gesture Bug**: Adjusted gesture sensitivity to prevent accidental activation when scrolling through code on mobile; now requires scrolling from the leftmost side to open the sidebar.
-
-### Changed
-
-- **🔄 Unlimited Context Length**: Advanced settings now allow unlimited max context length (previously limited to 16000).
-- **👑 Super Admin Assignment**: The first signup is automatically assigned a super admin role, unchangeable by other admins.
-- **🛡️ Admin User Restrictions**: User action buttons from the admin panel are now disabled for users with admin roles.
-- **🔝 Default Model Selector**: Set as default model option now exclusively available on the landing page.
-
-## [0.1.122] - 2024-04-27
-
-### Added
-
-- **🌟 Enhanced RAG Pipeline**: Now with hybrid searching via 'BM25', reranking powered by 'CrossEncoder', and configurable relevance score thresholds.
-- **🛢️ External Database Support**: Seamlessly connect to custom SQLite or Postgres databases using the 'DATABASE_URL' environment variable.
-- **🌐 Remote ChromaDB Support**: Introducing the capability to connect to remote ChromaDB servers.
-- **👨‍💼 Improved Admin Panel**: Admins can now conveniently check users' chat lists and last active status directly from the admin panel.
-- **🎨 Splash Screen**: Introducing a loading splash screen for a smoother user experience.
-- **🌍 Language Support Expansion**: Added support for Bangla (bn-BD), along with enhancements to Chinese, Spanish, and Ukrainian translations.
-- **💻 Improved LaTeX Rendering Performance**: Enjoy faster rendering times for LaTeX equations.
-- **🔧 More Environment Variables**: Explore additional environment variables in our documentation (https://docs.openwebui.com), including the 'ENABLE_LITELLM' option to manage memory usage.
-
-### Fixed
-
-- **🔧 Ollama Compatibility**: Resolved errors occurring when Ollama server version isn't an integer, such as SHA builds or RCs.
-- **🐛 Various OpenAI API Issues**: Addressed several issues related to the OpenAI API.
-- **🛑 Stop Sequence Issue**: Fixed the problem where the stop sequence with a backslash '\' was not functioning.
-- **🔤 Font Fallback**: Corrected font fallback issue.
-
-### Changed
-
-- **⌨️ Prompt Input Behavior on Mobile**: Enter key prompt submission disabled on mobile devices for improved user experience.
-
-## [0.1.121] - 2024-04-24
-
-### Fixed
-
-- **🔧 Translation Issues**: Addressed various translation discrepancies.
-- **🔒 LiteLLM Security Fix**: Updated LiteLLM version to resolve a security vulnerability.
-- **🖥️ HTML Tag Display**: Rectified the issue where the '< br >' tag wasn't displaying correctly.
-- **🔗 WebSocket Connection**: Resolved the failure of WebSocket connection under HTTPS security for ComfyUI server.
-- **📜 FileReader Optimization**: Implemented FileReader initialization per image in multi-file drag & drop to ensure reusability.
-- **🏷️ Tag Display**: Corrected tag display inconsistencies.
-- **📦 Archived Chat Styling**: Fixed styling issues in archived chat.
-- **🔖 Safari Copy Button Bug**: Addressed the bug where the copy button failed to copy links in Safari.
-
-## [0.1.120] - 2024-04-20
-
-### Added
-
-- **📦 Archive Chat Feature**: Easily archive chats with a new sidebar button, and access archived chats via the profile button > archived chats.
-- **🔊 Configurable Text-to-Speech Endpoint**: Customize your Text-to-Speech experience with configurable OpenAI endpoints.
-- **🛠️ Improved Error Handling**: Enhanced error message handling for connection failures.
-- **⌨️ Enhanced Shortcut**: When editing messages, use ctrl/cmd+enter to save and submit, and esc to close.
-- **🌐 Language Support**: Added support for Georgian and enhanced translations for Portuguese and Vietnamese.
-
-### Fixed
-
-- **🔧 Model Selector**: Resolved issue where default model selection was not saving.
-- **🔗 Share Link Copy Button**: Fixed bug where the copy button wasn't copying links in Safari.
-- **🎨 Light Theme Styling**: Addressed styling issue with the light theme.
-
-## [0.1.119] - 2024-04-16
-
-### Added
-
-- **🌟 Enhanced RAG Embedding Support**: Ollama, and OpenAI models can now be used for RAG embedding model.
-- **🔄 Seamless Integration**: Copy 'ollama run <model name>' directly from Ollama page to easily select and pull models.
-- **🏷️ Tagging Feature**: Add tags to chats directly via the sidebar chat menu.
-- **📱 Mobile Accessibility**: Swipe left and right on mobile to effortlessly open and close the sidebar.
-- **🔍 Improved Navigation**: Admin panel now supports pagination for user list.
-- **🌍 Additional Language Support**: Added Polish language support.
-
-### Fixed
-
-- **🌍 Language Enhancements**: Vietnamese and Spanish translations have been improved.
-- **🔧 Helm Fixes**: Resolved issues with Helm trailing slash and manifest.json.
-
-### Changed
-
-- **🐳 Docker Optimization**: Updated docker image build process to utilize 'uv' for significantly faster builds compared to 'pip3'.
-
-## [0.1.118] - 2024-04-10
-
-### Added
-
-- **🦙 Ollama and CUDA Images**: Added support for ':ollama' and ':cuda' tagged images.
-- **👍 Enhanced Response Rating**: Now you can annotate your ratings for better feedback.
-- **👤 User Initials Profile Photo**: User initials are now the default profile photo.
-- **🔍 Update RAG Embedding Model**: Customize RAG embedding model directly in document settings.
-- **🌍 Additional Language Support**: Added Turkish language support.
-
-### Fixed
-
-- **🔒 Share Chat Permission**: Resolved issue with chat sharing permissions.
-- **🛠 Modal Close**: Modals can now be closed using the Esc key.
-
-### Changed
-
-- **🎨 Admin Panel Styling**: Refreshed styling for the admin panel.
-- **🐳 Docker Image Build**: Updated docker image build process for improved efficiency.
-
-## [0.1.117] - 2024-04-03
-
-### Added
-
-- 🗨️ **Local Chat Sharing**: Share chat links seamlessly between users.
-- 🔑 **API Key Generation Support**: Generate secret keys to leverage Open WebUI with OpenAI libraries.
-- 📄 **Chat Download as PDF**: Easily download chats in PDF format.
-- 📝 **Improved Logging**: Enhancements to logging functionality.
-- 📧 **Trusted Email Authentication**: Authenticate using a trusted email header.
-
-### Fixed
-
-- 🌷 **Enhanced Dutch Translation**: Improved translation for Dutch users.
-- ⚪ **White Theme Styling**: Resolved styling issue with the white theme.
-- 📜 **LaTeX Chat Screen Overflow**: Fixed screen overflow issue with LaTeX rendering.
-- 🔒 **Security Patches**: Applied necessary security patches.
-
-## [0.1.116] - 2024-03-31
-
-### Added
-
-- **🔄 Enhanced UI**: Model selector now conveniently located in the navbar, enabling seamless switching between multiple models during conversations.
-- **🔍 Improved Model Selector**: Directly pull a model from the selector/Models now display detailed information for better understanding.
-- **💬 Webhook Support**: Now compatible with Google Chat and Microsoft Teams.
-- **🌐 Localization**: Korean translation (I18n) now available.
-- **🌑 Dark Theme**: OLED dark theme introduced for reduced strain during prolonged usage.
-- **🏷️ Tag Autocomplete**: Dropdown feature added for effortless chat tagging.
-
-### Fixed
-
-- **🔽 Auto-Scrolling**: Addressed OpenAI auto-scrolling issue.
-- **🏷️ Tag Validation**: Implemented tag validation to prevent empty string tags.
-- **🚫 Model Whitelisting**: Resolved LiteLLM model whitelisting issue.
-- **✅ Spelling**: Corrected various spelling issues for improved readability.
-
-## [0.1.115] - 2024-03-24
-
-### Added
-
-- **🔍 Custom Model Selector**: Easily find and select custom models with the new search filter feature.
-- **🛑 Cancel Model Download**: Added the ability to cancel model downloads.
-- **🎨 Image Generation ComfyUI**: Image generation now supports ComfyUI.
-- **🌟 Updated Light Theme**: Updated the light theme for a fresh look.
-- **🌍 Additional Language Support**: Now supporting Bulgarian, Italian, Portuguese, Japanese, and Dutch.
-
-### Fixed
-
-- **🔧 Fixed Broken Experimental GGUF Upload**: Resolved issues with experimental GGUF upload functionality.
-
-### Changed
-
-- **🔄 Vector Storage Reset Button**: Moved the reset vector storage button to document settings.
-
-## [0.1.114] - 2024-03-20
-
-### Added
-
-- **🔗 Webhook Integration**: Now you can subscribe to new user sign-up events via webhook. Simply navigate to the admin panel > admin settings > webhook URL.
-- **🛡️ Enhanced Model Filtering**: Alongside Ollama, OpenAI proxy model whitelisting, we've added model filtering functionality for LiteLLM proxy.
-- **🌍 Expanded Language Support**: Spanish, Catalan, and Vietnamese languages are now available, with improvements made to others.
-
-### Fixed
-
-- **🔧 Input Field Spelling**: Resolved issue with spelling mistakes in input fields.
-- **🖊️ Light Mode Styling**: Fixed styling issue with light mode in document adding.
-
-### Changed
-
-- **🔄 Language Sorting**: Languages are now sorted alphabetically by their code for improved organization.
-
-## [0.1.113] - 2024-03-18
-
-### Added
-
-- 🌍 **Localization**: You can now change the UI language in Settings > General. We support Ukrainian, German, Farsi (Persian), Traditional and Simplified Chinese and French translations. You can help us to translate the UI into your language! More info in our [CONTRIBUTION.md](https://github.com/open-webui/open-webui/blob/main/docs/CONTRIBUTING.md#-translations-and-internationalization).
-- 🎨 **System-wide Theme**: Introducing a new system-wide theme for enhanced visual experience.
-
-### Fixed
-
-- 🌑 **Dark Background on Select Fields**: Improved readability by adding a dark background to select fields, addressing issues on certain browsers/devices.
-- **Multiple OPENAI_API_BASE_URLS Issue**: Resolved issue where multiple base URLs caused conflicts when one wasn't functioning.
-- **RAG Encoding Issue**: Fixed encoding problem in RAG.
-- **npm Audit Fix**: Addressed npm audit findings.
-- **Reduced Scroll Threshold**: Improved auto-scroll experience by reducing the scroll threshold from 50px to 5px.
-
-### Changed
-
-- 🔄 **Sidebar UI Update**: Updated sidebar UI to feature a chat menu dropdown, replacing two icons for improved navigation.
-
-## [0.1.112] - 2024-03-15
-
-### Fixed
-
-- 🗨️ Resolved chat malfunction after image generation.
-- 🎨 Fixed various RAG issues.
-- 🧪 Rectified experimental broken GGUF upload logic.
-
-## [0.1.111] - 2024-03-10
-
-### Added
-
-- 🛡️ **Model Whitelisting**: Admins now have the ability to whitelist models for users with the 'user' role.
-- 🔄 **Update All Models**: Added a convenient button to update all models at once.
-- 📄 **Toggle PDF OCR**: Users can now toggle PDF OCR option for improved parsing performance.
-- 🎨 **DALL-E Integration**: Introduced DALL-E integration for image generation alongside automatic1111.
-- 🛠️ **RAG API Refactoring**: Refactored RAG logic and exposed its API, with additional documentation to follow.
-
-### Fixed
-
-- 🔒 **Max Token Settings**: Added max token settings for anthropic/claude-3-sonnet-20240229 (Issue #1094).
-- 🔧 **Misalignment Issue**: Corrected misalignment of Edit and Delete Icons when Chat Title is Empty (Issue #1104).
-- 🔄 **Context Loss Fix**: Resolved RAG losing context on model response regeneration with Groq models via API key (Issue #1105).
-- 📁 **File Handling Bug**: Addressed File Not Found Notification when Dropping a Conversation Element (Issue #1098).
-- 🖱️ **Dragged File Styling**: Fixed dragged file layover styling issue.
-
 ## [0.1.110] - 2024-03-06
 
 ### Added

Dockerfile

@@ -1,128 +1,77 @@
 # syntax=docker/dockerfile:1
-# Initialize device type args
-# use build args in the docker build commmand with --build-arg="BUILDARG=true"
-ARG USE_CUDA=false
-ARG USE_OLLAMA=false
-# Tested with cu117 for CUDA 11 and cu121 for CUDA 12 (default)
-ARG USE_CUDA_VER=cu121
-# any sentence transformer model; models to use can be found at https://huggingface.co/models?library=sentence-transformers
-# Leaderboard: https://huggingface.co/spaces/mteb/leaderboard 
-# for better performance and multilangauge support use "intfloat/multilingual-e5-large" (~2.5GB) or "intfloat/multilingual-e5-base" (~1.5GB)
-# IMPORTANT: If you change the embedding model (sentence-transformers/all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
-ARG USE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
-ARG USE_RERANKING_MODEL=""
 
-######## WebUI frontend ########
+FROM node:alpine as build
-FROM --platform=$BUILDPLATFORM node:21-alpine3.19 as build
 
 WORKDIR /app
 
+# wget embedding model weight from alpine (does not exist from slim-buster)
+RUN wget "https://chroma-onnx-models.s3.amazonaws.com/all-MiniLM-L6-v2/onnx.tar.gz" -O - | \
+    tar -xzf - -C /app
+
 COPY package.json package-lock.json ./
 RUN npm ci
 
 COPY . .
 RUN npm run build
 
-######## WebUI backend ########
+
 FROM python:3.11-slim-bookworm as base
 
-# Use args
+ENV ENV=prod
-ARG USE_CUDA
+ENV PORT ""
-ARG USE_OLLAMA
-ARG USE_CUDA_VER
-ARG USE_EMBEDDING_MODEL
-ARG USE_RERANKING_MODEL
 
-## Basis ##
+ENV OLLAMA_BASE_URL "/ollama"
-ENV ENV=prod \
-    PORT=8080 \
-    # pass build args to the build
-    USE_OLLAMA_DOCKER=${USE_OLLAMA} \
-    USE_CUDA_DOCKER=${USE_CUDA} \
-    USE_CUDA_DOCKER_VER=${USE_CUDA_VER} \
-    USE_EMBEDDING_MODEL_DOCKER=${USE_EMBEDDING_MODEL} \
-    USE_RERANKING_MODEL_DOCKER=${USE_RERANKING_MODEL}
 
-## Basis URL Config ##
+ENV OPENAI_API_BASE_URL ""
-ENV OLLAMA_BASE_URL="/ollama" \
+ENV OPENAI_API_KEY ""
-    OPENAI_API_BASE_URL=""
 
-## API Key and Security Config ##
+ENV WEBUI_SECRET_KEY ""
-ENV OPENAI_API_KEY="" \
-    WEBUI_SECRET_KEY="" \
-    SCARF_NO_ANALYTICS=true \
-    DO_NOT_TRACK=true \
-    ANONYMIZED_TELEMETRY=false
 
-# Use locally bundled version of the LiteLLM cost map json
+ENV SCARF_NO_ANALYTICS true
-# to avoid repetitive startup connections
+ENV DO_NOT_TRACK true
-ENV LITELLM_LOCAL_MODEL_COST_MAP="True"
 
+######## Preloaded models ########
+# whisper TTS Settings
+ENV WHISPER_MODEL="base"
+ENV WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models"
 
-#### Other models #########################################################
+# RAG Embedding Model Settings
-## whisper TTS model settings ##
+# any sentence transformer model; models to use can be found at https://huggingface.co/models?library=sentence-transformers
-ENV WHISPER_MODEL="base" \
+# Leaderboard: https://huggingface.co/spaces/mteb/leaderboard 
-    WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models"
+# for better persormance and multilangauge support use "intfloat/multilingual-e5-large" (~2.5GB) or "intfloat/multilingual-e5-base" (~1.5GB)
+# IMPORTANT: If you change the default model (all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
+ENV RAG_EMBEDDING_MODEL="all-MiniLM-L6-v2"
+# device type for whisper tts and embbeding models - "cpu" (default), "cuda" (nvidia gpu and CUDA required) or "mps" (apple silicon) - choosing this right can lead to better performance
+ENV RAG_EMBEDDING_MODEL_DEVICE_TYPE="cpu"
+ENV RAG_EMBEDDING_MODEL_DIR="/app/backend/data/cache/embedding/models"
+ENV SENTENCE_TRANSFORMERS_HOME $RAG_EMBEDDING_MODEL_DIR
 
-## RAG Embedding model settings ##
+######## Preloaded models ########
-ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
-    RAG_RERANKING_MODEL="$USE_RERANKING_MODEL_DOCKER" \
-    SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
-
-## Hugging Face download cache ##
-ENV HF_HOME="/app/backend/data/cache/embedding/models"
-#### Other models ##########################################################
 
 WORKDIR /app/backend
 
-ENV HOME /root
-RUN mkdir -p $HOME/.cache/chroma
-RUN echo -n 00000000-0000-0000-0000-000000000000 > $HOME/.cache/chroma/telemetry_user_id
-
-RUN if [ "$USE_OLLAMA" = "true" ]; then \
-        apt-get update && \
-        # Install pandoc and netcat
-        apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
-        # for RAG OCR
-        apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
-        # install helper tools
-        apt-get install -y --no-install-recommends curl && \
-        # install ollama
-        curl -fsSL https://ollama.com/install.sh | sh && \
-        # cleanup
-        rm -rf /var/lib/apt/lists/*; \
-    else \
-        apt-get update && \
-        # Install pandoc and netcat
-        apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
-        # for RAG OCR
-        apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
-        # cleanup
-        rm -rf /var/lib/apt/lists/*; \
-    fi
-
 # install python dependencies
 COPY ./backend/requirements.txt ./requirements.txt
 
-RUN pip3 install uv && \
+RUN apt-get update && apt-get install ffmpeg libsm6 libxext6  -y
-    if [ "$USE_CUDA" = "true" ]; then \
-        # If you use CUDA the whisper and embedding model will be downloaded on first use
-        pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir && \
-        uv pip install --system -r requirements.txt --no-cache-dir && \
-        python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
-        python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
-    else \
-        pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
-        uv pip install --system -r requirements.txt --no-cache-dir && \
-        python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
-        python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
-    fi
 
+RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir
+RUN pip3 install -r requirements.txt --no-cache-dir
 
+# Install pandoc and netcat
+# RUN python -c "import pypandoc; pypandoc.download_pandoc()"
+RUN apt-get update \
+    && apt-get install -y pandoc netcat-openbsd \
+    && rm -rf /var/lib/apt/lists/*
+
+# preload embedding model
+RUN python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device=os.environ['RAG_EMBEDDING_MODEL_DEVICE_TYPE'])"
+# preload tts model
+RUN python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='auto', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"
 
 # copy embedding weight from build
-# RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
+RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
-# COPY --from=build /app/onnx /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx
+COPY --from=build /app/onnx /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx
 
 # copy built frontend files
 COPY --from=build /app/build /app/build
@@ -132,6 +81,4 @@ COPY --from=build /app/package.json /app/package.json
 # copy backend files
 COPY ./backend .
 
-EXPOSE 8080
-
 CMD [ "bash", "start.sh"]

Makefile

@@ -1,33 +1,25 @@
-
-ifneq ($(shell which docker-compose 2>/dev/null),)
-    DOCKER_COMPOSE := docker-compose
-else
-    DOCKER_COMPOSE := docker compose
-endif
-
 install:
-	$(DOCKER_COMPOSE) up -d
+	@docker-compose up -d
 
 remove:
 	@chmod +x confirm_remove.sh
 	@./confirm_remove.sh
 
+
 start:
-	$(DOCKER_COMPOSE) start
+	@docker-compose start
-startAndBuild: 
-	$(DOCKER_COMPOSE) up -d --build
 
 stop:
-	$(DOCKER_COMPOSE) stop
+	@docker-compose stop
 
 update:
 	# Calls the LLM update script
 	chmod +x update_ollama_models.sh
 	@./update_ollama_models.sh
 	@git pull
-	$(DOCKER_COMPOSE) down
+	@docker-compose down
 	# Make sure the ollama-webui container is stopped before rebuilding
 	@docker stop open-webui || true
-	$(DOCKER_COMPOSE) up --build -d
+	@docker-compose up --build -d
-	$(DOCKER_COMPOSE) start
+	@docker-compose start
 

README.md

@@ -11,7 +11,7 @@
 [![Discord](https://img.shields.io/badge/Discord-Open_WebUI-blue?logo=discord&logoColor=white)](https://discord.gg/5rJgQTnV4s)
 [![](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=%23fe8e86)](https://github.com/sponsors/tjbck)
 
-Open WebUI is an extensible, feature-rich, and user-friendly self-hosted WebUI designed to operate entirely offline. It supports various LLM runners, including Ollama and OpenAI-compatible APIs. For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
+User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs. For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
 
 ![Open WebUI Demo](./demo.gif)
 
@@ -25,28 +25,22 @@ Open WebUI is an extensible, feature-rich, and user-friendly self-hosted WebUI d
 
 - 🚀 **Effortless Setup**: Install seamlessly using Docker or Kubernetes (kubectl, kustomize or helm) for a hassle-free experience.
 
-- 🌈 **Theme Customization**: Choose from a variety of themes to personalize your Open WebUI experience.
-
 - 💻 **Code Syntax Highlighting**: Enjoy enhanced code readability with our syntax highlighting feature.
 
 - ✒️🔢 **Full Markdown and LaTeX Support**: Elevate your LLM experience with comprehensive Markdown and LaTeX capabilities for enriched interaction.
 
 - 📚 **Local RAG Integration**: Dive into the future of chat interactions with the groundbreaking Retrieval Augmented Generation (RAG) support. This feature seamlessly integrates document interactions into your chat experience. You can load documents directly into the chat or add files to your document library, effortlessly accessing them using `#` command in the prompt. In its alpha phase, occasional issues may arise as we actively refine and enhance this feature to ensure optimal performance and reliability.
 
-- 🔍 **RAG Embedding Support**: Change the RAG embedding model directly in document settings, enhancing document processing. This feature supports Ollama and OpenAI models.
-
 - 🌐 **Web Browsing Capability**: Seamlessly integrate websites into your chat experience using the `#` command followed by the URL. This feature allows you to incorporate web content directly into your conversations, enhancing the richness and depth of your interactions.
 
 - 📜 **Prompt Preset Support**: Instantly access preset prompts using the `/` command in the chat input. Load predefined conversation starters effortlessly and expedite your interactions. Effortlessly import prompts through [Open WebUI Community](https://openwebui.com/) integration.
 
-- 👍👎 **RLHF Annotation**: Empower your messages by rating them with thumbs up and thumbs down, followed by the option to provide textual feedback, facilitating the creation of datasets for Reinforcement Learning from Human Feedback (RLHF). Utilize your messages to train or fine-tune models, all while ensuring the confidentiality of locally saved data.
+- 👍👎 **RLHF Annotation**: Empower your messages by rating them with thumbs up and thumbs down, facilitating the creation of datasets for Reinforcement Learning from Human Feedback (RLHF). Utilize your messages to train or fine-tune models, all while ensuring the confidentiality of locally saved data.
 
 - 🏷️ **Conversation Tagging**: Effortlessly categorize and locate specific chats for quick reference and streamlined data collection.
 
 - 📥🗑️ **Download/Delete Models**: Easily download or remove models directly from the web UI.
 
-- 🔄 **Update All Ollama Models**: Easily update locally installed models all at once with a convenient button, streamlining model management.
-
 - ⬆️ **GGUF File Model Creation**: Effortlessly create Ollama models by uploading GGUF files directly from the web UI. Streamlined process with options to upload from your machine or download GGUF files from Hugging Face.
 
 - 🤖 **Multiple Model Support**: Seamlessly switch between different chat models for diverse interactions.
@@ -59,48 +53,32 @@ Open WebUI is an extensible, feature-rich, and user-friendly self-hosted WebUI d
 
 - 💬 **Collaborative Chat**: Harness the collective intelligence of multiple models by seamlessly orchestrating group conversations. Use the `@` command to specify the model, enabling dynamic and diverse dialogues within your chat interface. Immerse yourself in the collective intelligence woven into your chat environment.
 
-- 🗨️ **Local Chat Sharing**: Generate and share chat links seamlessly between users, enhancing collaboration and communication.
-
 - 🔄 **Regeneration History Access**: Easily revisit and explore your entire regeneration history.
 
 - 📜 **Chat History**: Effortlessly access and manage your conversation history.
 
-- 📬 **Archive Chats**: Effortlessly store away completed conversations with LLMs for future reference, maintaining a tidy and clutter-free chat interface while allowing for easy retrieval and reference.
-
 - 📤📥 **Import/Export Chat History**: Seamlessly move your chat data in and out of the platform.
 
 - 🗣️ **Voice Input Support**: Engage with your model through voice interactions; enjoy the convenience of talking to your model directly. Additionally, explore the option for sending voice input automatically after 3 seconds of silence for a streamlined experience.
 
-- 🔊 **Configurable Text-to-Speech Endpoint**: Customize your Text-to-Speech experience with configurable OpenAI endpoints.
-
 - ⚙️ **Fine-Tuned Control with Advanced Parameters**: Gain a deeper level of control by adjusting parameters such as temperature and defining your system prompts to tailor the conversation to your specific preferences and needs.
 
-- 🎨🤖 **Image Generation Integration**: Seamlessly incorporate image generation capabilities using options such as AUTOMATIC1111 API (local), ComfyUI (local), and DALL-E, enriching your chat experience with dynamic visual content.
+- 🎨🤖 **Image Generation Integration**: Seamlessly incorporate image generation capabilities using AUTOMATIC1111 API (local) and DALL-E, enriching your chat experience with dynamic visual content.
 
 - 🤝 **OpenAI API Integration**: Effortlessly integrate OpenAI-compatible API for versatile conversations alongside Ollama models. Customize the API Base URL to link with **LMStudio, Mistral, OpenRouter, and more**.
 
 - ✨ **Multiple OpenAI-Compatible API Support**: Seamlessly integrate and customize various OpenAI-compatible APIs, enhancing the versatility of your chat interactions.
 
-- 🔑 **API Key Generation Support**: Generate secret keys to leverage Open WebUI with OpenAI libraries, simplifying integration and development.
-
 - 🔗 **External Ollama Server Connection**: Seamlessly link to an external Ollama server hosted on a different address by configuring the environment variable.
 
 - 🔀 **Multiple Ollama Instance Load Balancing**: Effortlessly distribute chat requests across multiple Ollama instances for enhanced performance and reliability.
 
 - 👥 **Multi-User Management**: Easily oversee and administer users via our intuitive admin panel, streamlining user management processes.
 
-- 🔗 **Webhook Integration**: Subscribe to new user sign-up events via webhook (compatible with Google Chat and Microsoft Teams), providing real-time notifications and automation capabilities.
-
-- 🛡️ **Model Whitelisting**: Admins can whitelist models for users with the 'user' role, enhancing security and access control.
-
-- 📧 **Trusted Email Authentication**: Authenticate using a trusted email header, adding an additional layer of security and authentication.
-
 - 🔐 **Role-Based Access Control (RBAC)**: Ensure secure access with restricted permissions; only authorized individuals can access your Ollama, and exclusive model creation/pulling rights are reserved for administrators.
 
 - 🔒 **Backend Reverse Proxy Support**: Bolster security through direct communication between Open WebUI backend and Ollama. This key feature eliminates the need to expose Ollama over LAN. Requests made to the '/ollama/api' route from the web UI are seamlessly redirected to Ollama from the backend, enhancing overall system security.
 
-- 🌐🌍 **Multilingual Support**: Experience Open WebUI in your preferred language with our internationalization (i18n) support. Join us in expanding our supported languages! We're actively seeking contributors!
-
 - 🌟 **Continuous Updates**: We are committed to improving Open WebUI with regular updates and new features.
 
 ## 🔗 Also Check Out Open WebUI Community!
@@ -114,27 +92,24 @@ Don't forget to explore our sibling project, [Open WebUI Community](https://open
 
 ### Quick Start with Docker 🐳
 
-> [!WARNING]
+> [!IMPORTANT]
 > When using Docker to install Open WebUI, make sure to include the `-v open-webui:/app/backend/data` in your Docker command. This step is crucial as it ensures your database is properly mounted and prevents any loss of data.
 
-> [!TIP]  
+- **If Ollama is on your computer**, use this command:
-> If you wish to utilize Open WebUI with Ollama included or CUDA acceleration, we recommend utilizing our official images tagged with either `:cuda` or `:ollama`. To enable CUDA, you must install the [Nvidia CUDA container toolkit](https://docs.nvidia.com/dgx/nvidia-container-runtime-upgrade/) on your Linux/WSL system.
 
-**If Ollama is on your computer**, use this command:
+  ```bash
+  docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
+  ```
 
-```bash
+- **If Ollama is on a Different Server**, use this command:
-docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
-```
 
-**If Ollama is on a Different Server**, use this command:
+- To connect to Ollama on another server, change the `OLLAMA_BASE_URL` to the server's URL:
 
-To connect to Ollama on another server, change the `OLLAMA_BASE_URL` to the server's URL:
+  ```bash
+  docker run -d -p 3000:8080 -e OLLAMA_BASE_URL=https://example.com -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
+  ```
 
-```bash
+- After installation, you can access Open WebUI at [http://localhost:3000](http://localhost:3000). Enjoy! 😄
-docker run -d -p 3000:8080 -e OLLAMA_BASE_URL=https://example.com -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
-```
-
-After installation, you can access Open WebUI at [http://localhost:3000](http://localhost:3000). Enjoy! 😄
 
 #### Open WebUI: Server Connection Error
 
@@ -205,4 +180,4 @@ If you have any questions, suggestions, or need assistance, please open an issue
 
 ---
 
-Created by [Timothy J. Baek](https://github.com/tjbck) - Let's make Open WebUI even more amazing together! 💪
+Created by [Timothy J. Baek](https://github.com/tjbck) - Let's make Open Web UI even more amazing together! 💪

backend/apps/audio/main.py

@@ -1,5 +1,4 @@
 import os
-import logging
 from fastapi import (
     FastAPI,
     Request,
@@ -10,19 +9,8 @@ from fastapi import (
     File,
     Form,
 )
-
-from fastapi.responses import StreamingResponse, JSONResponse, FileResponse
-
 from fastapi.middleware.cors import CORSMiddleware
 from faster_whisper import WhisperModel
-from pydantic import BaseModel
-
-
-import requests
-import hashlib
-from pathlib import Path
-import json
-
 
 from constants import ERROR_MESSAGES
 from utils.utils import (
@@ -33,20 +21,7 @@ from utils.utils import (
 )
 from utils.misc import calculate_sha256
 
-from config import (
+from config import CACHE_DIR, UPLOAD_DIR, WHISPER_MODEL, WHISPER_MODEL_DIR
-    SRC_LOG_LEVELS,
-    CACHE_DIR,
-    UPLOAD_DIR,
-    WHISPER_MODEL,
-    WHISPER_MODEL_DIR,
-    WHISPER_MODEL_AUTO_UPDATE,
-    DEVICE_TYPE,
-    AUDIO_OPENAI_API_BASE_URL,
-    AUDIO_OPENAI_API_KEY,
-)
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["AUDIO"])
 
 app = FastAPI()
 app.add_middleware(
@@ -58,108 +33,12 @@ app.add_middleware(
 )
 
 
-app.state.OPENAI_API_BASE_URL = AUDIO_OPENAI_API_BASE_URL
+@app.post("/transcribe")
-app.state.OPENAI_API_KEY = AUDIO_OPENAI_API_KEY
-
-# setting device type for whisper model
-whisper_device_type = DEVICE_TYPE if DEVICE_TYPE and DEVICE_TYPE == "cuda" else "cpu"
-log.info(f"whisper_device_type: {whisper_device_type}")
-
-SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
-SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
-
-
-class OpenAIConfigUpdateForm(BaseModel):
-    url: str
-    key: str
-
-
-@app.get("/config")
-async def get_openai_config(user=Depends(get_admin_user)):
-    return {
-        "OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL,
-        "OPENAI_API_KEY": app.state.OPENAI_API_KEY,
-    }
-
-
-@app.post("/config/update")
-async def update_openai_config(
-    form_data: OpenAIConfigUpdateForm, user=Depends(get_admin_user)
-):
-    if form_data.key == "":
-        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
-
-    app.state.OPENAI_API_BASE_URL = form_data.url
-    app.state.OPENAI_API_KEY = form_data.key
-
-    return {
-        "status": True,
-        "OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL,
-        "OPENAI_API_KEY": app.state.OPENAI_API_KEY,
-    }
-
-
-@app.post("/speech")
-async def speech(request: Request, user=Depends(get_verified_user)):
-    body = await request.body()
-    name = hashlib.sha256(body).hexdigest()
-
-    file_path = SPEECH_CACHE_DIR.joinpath(f"{name}.mp3")
-    file_body_path = SPEECH_CACHE_DIR.joinpath(f"{name}.json")
-
-    # Check if the file already exists in the cache
-    if file_path.is_file():
-        return FileResponse(file_path)
-
-    headers = {}
-    headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEY}"
-    headers["Content-Type"] = "application/json"
-
-    r = None
-    try:
-        r = requests.post(
-            url=f"{app.state.OPENAI_API_BASE_URL}/audio/speech",
-            data=body,
-            headers=headers,
-            stream=True,
-        )
-
-        r.raise_for_status()
-
-        # Save the streaming content to a file
-        with open(file_path, "wb") as f:
-            for chunk in r.iter_content(chunk_size=8192):
-                f.write(chunk)
-
-        with open(file_body_path, "w") as f:
-            json.dump(json.loads(body.decode("utf-8")), f)
-
-        # Return the saved file
-        return FileResponse(file_path)
-
-    except Exception as e:
-        log.exception(e)
-        error_detail = "Open WebUI: Server Connection Error"
-        if r is not None:
-            try:
-                res = r.json()
-                if "error" in res:
-                    error_detail = f"External: {res['error']['message']}"
-            except:
-                error_detail = f"External: {e}"
-
-        raise HTTPException(
-            status_code=r.status_code if r != None else 500,
-            detail=error_detail,
-        )
-
-
-@app.post("/transcriptions")
 def transcribe(
     file: UploadFile = File(...),
     user=Depends(get_current_user),
 ):
-    log.info(f"file.content_type: {file.content_type}")
+    print(file.content_type)
 
     if file.content_type not in ["audio/mpeg", "audio/wav"]:
         raise HTTPException(
@@ -175,27 +54,15 @@ def transcribe(
             f.write(contents)
             f.close()
 
-        whisper_kwargs = {
+        model = WhisperModel(
-            "model_size_or_path": WHISPER_MODEL,
+            WHISPER_MODEL,
-            "device": whisper_device_type,
+            device="auto",
-            "compute_type": "int8",
+            compute_type="int8",
-            "download_root": WHISPER_MODEL_DIR,
+            download_root=WHISPER_MODEL_DIR,
-            "local_files_only": not WHISPER_MODEL_AUTO_UPDATE,
+        )
-        }
-
-        log.debug(f"whisper_kwargs: {whisper_kwargs}")
-
-        try:
-            model = WhisperModel(**whisper_kwargs)
-        except:
-            log.warning(
-                "WhisperModel initialization failed, attempting download with local_files_only=False"
-            )
-            whisper_kwargs["local_files_only"] = False
-            model = WhisperModel(**whisper_kwargs)
 
         segments, info = model.transcribe(file_path, beam_size=5)
-        log.info(
+        print(
             "Detected language '%s' with probability %f"
             % (info.language, info.language_probability)
         )
@@ -205,7 +72,7 @@ def transcribe(
         return {"text": transcript.strip()}
 
     except Exception as e:
-        log.exception(e)
+        print(e)
 
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,

backend/apps/images/main.py

@@ -18,36 +18,17 @@ from utils.utils import (
     get_current_user,
     get_admin_user,
 )
-
-from apps.images.utils.comfyui import ImageGenerationPayload, comfyui_generate_image
 from utils.misc import calculate_sha256
 from typing import Optional
 from pydantic import BaseModel
 from pathlib import Path
-import mimetypes
 import uuid
 import base64
 import json
-import logging
 
-from config import (
+from config import CACHE_DIR, AUTOMATIC1111_BASE_URL
-    SRC_LOG_LEVELS,
-    CACHE_DIR,
-    IMAGE_GENERATION_ENGINE,
-    ENABLE_IMAGE_GENERATION,
-    AUTOMATIC1111_BASE_URL,
-    COMFYUI_BASE_URL,
-    IMAGES_OPENAI_API_BASE_URL,
-    IMAGES_OPENAI_API_KEY,
-    IMAGE_GENERATION_MODEL,
-    IMAGE_SIZE,
-    IMAGE_STEPS,
-)
 
 
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["IMAGES"])
-
 IMAGE_CACHE_DIR = Path(CACHE_DIR).joinpath("./image/generations/")
 IMAGE_CACHE_DIR.mkdir(parents=True, exist_ok=True)
 
@@ -60,21 +41,17 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-app.state.ENGINE = IMAGE_GENERATION_ENGINE
+app.state.ENGINE = ""
-app.state.ENABLED = ENABLE_IMAGE_GENERATION
+app.state.ENABLED = False
 
-app.state.OPENAI_API_BASE_URL = IMAGES_OPENAI_API_BASE_URL
+app.state.OPENAI_API_KEY = ""
-app.state.OPENAI_API_KEY = IMAGES_OPENAI_API_KEY
+app.state.MODEL = ""
-
-app.state.MODEL = IMAGE_GENERATION_MODEL
 
 
 app.state.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL
-app.state.COMFYUI_BASE_URL = COMFYUI_BASE_URL
 
-
+app.state.IMAGE_SIZE = "512x512"
-app.state.IMAGE_SIZE = IMAGE_SIZE
+app.state.IMAGE_STEPS = 50
-app.state.IMAGE_STEPS = IMAGE_STEPS
 
 
 @app.get("/config")
@@ -94,79 +71,57 @@ async def update_config(form_data: ConfigUpdateForm, user=Depends(get_admin_user
     return {"engine": app.state.ENGINE, "enabled": app.state.ENABLED}
 
 
-class EngineUrlUpdateForm(BaseModel):
+class UrlUpdateForm(BaseModel):
-    AUTOMATIC1111_BASE_URL: Optional[str] = None
+    url: str
-    COMFYUI_BASE_URL: Optional[str] = None
 
 
 @app.get("/url")
-async def get_engine_url(user=Depends(get_admin_user)):
+async def get_automatic1111_url(user=Depends(get_admin_user)):
-    return {
+    return {"AUTOMATIC1111_BASE_URL": app.state.AUTOMATIC1111_BASE_URL}
-        "AUTOMATIC1111_BASE_URL": app.state.AUTOMATIC1111_BASE_URL,
-        "COMFYUI_BASE_URL": app.state.COMFYUI_BASE_URL,
-    }
 
 
 @app.post("/url/update")
-async def update_engine_url(
+async def update_automatic1111_url(
-    form_data: EngineUrlUpdateForm, user=Depends(get_admin_user)
+    form_data: UrlUpdateForm, user=Depends(get_admin_user)
 ):
 
-    if form_data.AUTOMATIC1111_BASE_URL == None:
+    if form_data.url == "":
         app.state.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL
     else:
-        url = form_data.AUTOMATIC1111_BASE_URL.strip("/")
+        url = form_data.url.strip("/")
         try:
             r = requests.head(url)
             app.state.AUTOMATIC1111_BASE_URL = url
         except Exception as e:
             raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
 
-    if form_data.COMFYUI_BASE_URL == None:
-        app.state.COMFYUI_BASE_URL = COMFYUI_BASE_URL
-    else:
-        url = form_data.COMFYUI_BASE_URL.strip("/")
-
-        try:
-            r = requests.head(url)
-            app.state.COMFYUI_BASE_URL = url
-        except Exception as e:
-            raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
-
     return {
         "AUTOMATIC1111_BASE_URL": app.state.AUTOMATIC1111_BASE_URL,
-        "COMFYUI_BASE_URL": app.state.COMFYUI_BASE_URL,
         "status": True,
     }
 
 
-class OpenAIConfigUpdateForm(BaseModel):
+class OpenAIKeyUpdateForm(BaseModel):
-    url: str
     key: str
 
 
-@app.get("/openai/config")
+@app.get("/key")
-async def get_openai_config(user=Depends(get_admin_user)):
+async def get_openai_key(user=Depends(get_admin_user)):
-    return {
+    return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY}
-        "OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL,
-        "OPENAI_API_KEY": app.state.OPENAI_API_KEY,
-    }
 
 
-@app.post("/openai/config/update")
+@app.post("/key/update")
-async def update_openai_config(
+async def update_openai_key(
-    form_data: OpenAIConfigUpdateForm, user=Depends(get_admin_user)
+    form_data: OpenAIKeyUpdateForm, user=Depends(get_admin_user)
 ):
+
     if form_data.key == "":
         raise HTTPException(status_code=400, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
 
-    app.state.OPENAI_API_BASE_URL = form_data.url
     app.state.OPENAI_API_KEY = form_data.key
-
     return {
-        "status": True,
-        "OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL,
         "OPENAI_API_KEY": app.state.OPENAI_API_KEY,
+        "status": True,
     }
 
 
@@ -231,18 +186,6 @@ def get_models(user=Depends(get_current_user)):
                 {"id": "dall-e-2", "name": "DALL·E 2"},
                 {"id": "dall-e-3", "name": "DALL·E 3"},
             ]
-        elif app.state.ENGINE == "comfyui":
-
-            r = requests.get(url=f"{app.state.COMFYUI_BASE_URL}/object_info")
-            info = r.json()
-
-            return list(
-                map(
-                    lambda model: {"id": model, "name": model},
-                    info["CheckpointLoaderSimple"]["input"]["required"]["ckpt_name"][0],
-                )
-            )
-
         else:
             r = requests.get(
                 url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/sd-models"
@@ -264,8 +207,6 @@ async def get_default_model(user=Depends(get_admin_user)):
     try:
         if app.state.ENGINE == "openai":
             return {"model": app.state.MODEL if app.state.MODEL else "dall-e-2"}
-        elif app.state.ENGINE == "comfyui":
-            return {"model": app.state.MODEL if app.state.MODEL else ""}
         else:
             r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options")
             options = r.json()
@@ -280,12 +221,10 @@ class UpdateModelForm(BaseModel):
 
 
 def set_model_handler(model: str):
+
     if app.state.ENGINE == "openai":
         app.state.MODEL = model
         return app.state.MODEL
-    if app.state.ENGINE == "comfyui":
-        app.state.MODEL = model
-        return app.state.MODEL
     else:
         r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options")
         options = r.json()
@@ -316,63 +255,20 @@ class GenerateImageForm(BaseModel):
 
 
 def save_b64_image(b64_str):
-    try:
-        image_id = str(uuid.uuid4())
-
-        if "," in b64_str:
-            header, encoded = b64_str.split(",", 1)
-            mime_type = header.split(";")[0]
-
-            img_data = base64.b64decode(encoded)
-            image_format = mimetypes.guess_extension(mime_type)
-
-            image_filename = f"{image_id}{image_format}"
-            file_path = IMAGE_CACHE_DIR / f"{image_filename}"
-            with open(file_path, "wb") as f:
-                f.write(img_data)
-            return image_filename
-        else:
-            image_filename = f"{image_id}.png"
-            file_path = IMAGE_CACHE_DIR.joinpath(image_filename)
-
-            img_data = base64.b64decode(b64_str)
-
-            # Write the image data to a file
-            with open(file_path, "wb") as f:
-                f.write(img_data)
-            return image_filename
-
-    except Exception as e:
-        log.exception(f"Error saving image: {e}")
-        return None
-
-
-def save_url_image(url):
     image_id = str(uuid.uuid4())
+    file_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.png")
+
     try:
-        r = requests.get(url)
+        # Split the base64 string to get the actual image data
-        r.raise_for_status()
+        img_data = base64.b64decode(b64_str)
-        if r.headers["content-type"].split("/")[0] == "image":
 
-            mime_type = r.headers["content-type"]
+        # Write the image data to a file
-            image_format = mimetypes.guess_extension(mime_type)
+        with open(file_path, "wb") as f:
-
+            f.write(img_data)
-            if not image_format:
-                raise ValueError("Could not determine image type from MIME type")
-
-            image_filename = f"{image_id}{image_format}"
-
-            file_path = IMAGE_CACHE_DIR.joinpath(f"{image_filename}")
-            with open(file_path, "wb") as image_file:
-                for chunk in r.iter_content(chunk_size=8192):
-                    image_file.write(chunk)
-            return image_filename
-        else:
-            log.error(f"Url does not point to an image.")
-            return None
 
+        return image_id
     except Exception as e:
-        log.exception(f"Error saving image: {e}")
+        print(f"Error saving image: {e}")
         return None
 
 
@@ -382,8 +278,6 @@ def generate_image(
     user=Depends(get_current_user),
 ):
 
-    width, height = tuple(map(int, app.state.IMAGE_SIZE.split("x")))
-
     r = None
     try:
         if app.state.ENGINE == "openai":
@@ -399,69 +293,34 @@ def generate_image(
                 "size": form_data.size if form_data.size else app.state.IMAGE_SIZE,
                 "response_format": "b64_json",
             }
-
             r = requests.post(
-                url=f"{app.state.OPENAI_API_BASE_URL}/images/generations",
+                url=f"https://api.openai.com/v1/images/generations",
                 json=data,
                 headers=headers,
             )
 
             r.raise_for_status()
+
             res = r.json()
 
             images = []
 
             for image in res["data"]:
-                image_filename = save_b64_image(image["b64_json"])
+                image_id = save_b64_image(image["b64_json"])
-                images.append({"url": f"/cache/image/generations/{image_filename}"})
+                images.append({"url": f"/cache/image/generations/{image_id}.png"})
-                file_body_path = IMAGE_CACHE_DIR.joinpath(f"{image_filename}.json")
+                file_body_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.json")
 
                 with open(file_body_path, "w") as f:
                     json.dump(data, f)
 
             return images
 
-        elif app.state.ENGINE == "comfyui":
-
-            data = {
-                "prompt": form_data.prompt,
-                "width": width,
-                "height": height,
-                "n": form_data.n,
-            }
-
-            if app.state.IMAGE_STEPS != None:
-                data["steps"] = app.state.IMAGE_STEPS
-
-            if form_data.negative_prompt != None:
-                data["negative_prompt"] = form_data.negative_prompt
-
-            data = ImageGenerationPayload(**data)
-
-            res = comfyui_generate_image(
-                app.state.MODEL,
-                data,
-                user.id,
-                app.state.COMFYUI_BASE_URL,
-            )
-            log.debug(f"res: {res}")
-
-            images = []
-
-            for image in res["data"]:
-                image_filename = save_url_image(image["url"])
-                images.append({"url": f"/cache/image/generations/{image_filename}"})
-                file_body_path = IMAGE_CACHE_DIR.joinpath(f"{image_filename}.json")
-
-                with open(file_body_path, "w") as f:
-                    json.dump(data.model_dump(exclude_none=True), f)
-
-            log.debug(f"images: {images}")
-            return images
         else:
             if form_data.model:
                 set_model_handler(form_data.model)
 
+            width, height = tuple(map(int, app.state.IMAGE_SIZE.split("x")))
+
             data = {
                 "prompt": form_data.prompt,
                 "batch_size": form_data.n,
@@ -482,14 +341,14 @@ def generate_image(
 
             res = r.json()
 
-            log.debug(f"res: {res}")
+            print(res)
 
             images = []
 
             for image in res["images"]:
-                image_filename = save_b64_image(image)
+                image_id = save_b64_image(image)
-                images.append({"url": f"/cache/image/generations/{image_filename}"})
+                images.append({"url": f"/cache/image/generations/{image_id}.png"})
-                file_body_path = IMAGE_CACHE_DIR.joinpath(f"{image_filename}.json")
+                file_body_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.json")
 
                 with open(file_body_path, "w") as f:
                     json.dump({**data, "info": res["info"]}, f)
@@ -497,10 +356,7 @@ def generate_image(
             return images
 
     except Exception as e:
-        error = e
+        print(e)
-
+        if r:
-        if r != None:
+            print(r.json())
-            data = r.json()
+        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
-            if "error" in data:
-                error = data["error"]["message"]
-        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(error))

backend/apps/images/utils/comfyui.py

@@ -1,234 +0,0 @@
-import websocket  # NOTE: websocket-client (https://github.com/websocket-client/websocket-client)
-import uuid
-import json
-import urllib.request
-import urllib.parse
-import random
-import logging
-
-from config import SRC_LOG_LEVELS
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["COMFYUI"])
-
-from pydantic import BaseModel
-
-from typing import Optional
-
-COMFYUI_DEFAULT_PROMPT = """
-{
-  "3": {
-    "inputs": {
-      "seed": 0,
-      "steps": 20,
-      "cfg": 8,
-      "sampler_name": "euler",
-      "scheduler": "normal",
-      "denoise": 1,
-      "model": [
-        "4",
-        0
-      ],
-      "positive": [
-        "6",
-        0
-      ],
-      "negative": [
-        "7",
-        0
-      ],
-      "latent_image": [
-        "5",
-        0
-      ]
-    },
-    "class_type": "KSampler",
-    "_meta": {
-      "title": "KSampler"
-    }
-  },
-  "4": {
-    "inputs": {
-      "ckpt_name": "model.safetensors"
-    },
-    "class_type": "CheckpointLoaderSimple",
-    "_meta": {
-      "title": "Load Checkpoint"
-    }
-  },
-  "5": {
-    "inputs": {
-      "width": 512,
-      "height": 512,
-      "batch_size": 1
-    },
-    "class_type": "EmptyLatentImage",
-    "_meta": {
-      "title": "Empty Latent Image"
-    }
-  },
-  "6": {
-    "inputs": {
-      "text": "Prompt",
-      "clip": [
-        "4",
-        1
-      ]
-    },
-    "class_type": "CLIPTextEncode",
-    "_meta": {
-      "title": "CLIP Text Encode (Prompt)"
-    }
-  },
-  "7": {
-    "inputs": {
-      "text": "Negative Prompt",
-      "clip": [
-        "4",
-        1
-      ]
-    },
-    "class_type": "CLIPTextEncode",
-    "_meta": {
-      "title": "CLIP Text Encode (Prompt)"
-    }
-  },
-  "8": {
-    "inputs": {
-      "samples": [
-        "3",
-        0
-      ],
-      "vae": [
-        "4",
-        2
-      ]
-    },
-    "class_type": "VAEDecode",
-    "_meta": {
-      "title": "VAE Decode"
-    }
-  },
-  "9": {
-    "inputs": {
-      "filename_prefix": "ComfyUI",
-      "images": [
-        "8",
-        0
-      ]
-    },
-    "class_type": "SaveImage",
-    "_meta": {
-      "title": "Save Image"
-    }
-  }
-}
-"""
-
-
-def queue_prompt(prompt, client_id, base_url):
-    log.info("queue_prompt")
-    p = {"prompt": prompt, "client_id": client_id}
-    data = json.dumps(p).encode("utf-8")
-    req = urllib.request.Request(f"{base_url}/prompt", data=data)
-    return json.loads(urllib.request.urlopen(req).read())
-
-
-def get_image(filename, subfolder, folder_type, base_url):
-    log.info("get_image")
-    data = {"filename": filename, "subfolder": subfolder, "type": folder_type}
-    url_values = urllib.parse.urlencode(data)
-    with urllib.request.urlopen(f"{base_url}/view?{url_values}") as response:
-        return response.read()
-
-
-def get_image_url(filename, subfolder, folder_type, base_url):
-    log.info("get_image")
-    data = {"filename": filename, "subfolder": subfolder, "type": folder_type}
-    url_values = urllib.parse.urlencode(data)
-    return f"{base_url}/view?{url_values}"
-
-
-def get_history(prompt_id, base_url):
-    log.info("get_history")
-    with urllib.request.urlopen(f"{base_url}/history/{prompt_id}") as response:
-        return json.loads(response.read())
-
-
-def get_images(ws, prompt, client_id, base_url):
-    prompt_id = queue_prompt(prompt, client_id, base_url)["prompt_id"]
-    output_images = []
-    while True:
-        out = ws.recv()
-        if isinstance(out, str):
-            message = json.loads(out)
-            if message["type"] == "executing":
-                data = message["data"]
-                if data["node"] is None and data["prompt_id"] == prompt_id:
-                    break  # Execution is done
-        else:
-            continue  # previews are binary data
-
-    history = get_history(prompt_id, base_url)[prompt_id]
-    for o in history["outputs"]:
-        for node_id in history["outputs"]:
-            node_output = history["outputs"][node_id]
-            if "images" in node_output:
-                for image in node_output["images"]:
-                    url = get_image_url(
-                        image["filename"], image["subfolder"], image["type"], base_url
-                    )
-                    output_images.append({"url": url})
-    return {"data": output_images}
-
-
-class ImageGenerationPayload(BaseModel):
-    prompt: str
-    negative_prompt: Optional[str] = ""
-    steps: Optional[int] = None
-    seed: Optional[int] = None
-    width: int
-    height: int
-    n: int = 1
-
-
-def comfyui_generate_image(
-    model: str, payload: ImageGenerationPayload, client_id, base_url
-):
-    ws_url = base_url.replace("http://", "ws://").replace("https://", "wss://")
-
-    comfyui_prompt = json.loads(COMFYUI_DEFAULT_PROMPT)
-
-    comfyui_prompt["4"]["inputs"]["ckpt_name"] = model
-    comfyui_prompt["5"]["inputs"]["batch_size"] = payload.n
-    comfyui_prompt["5"]["inputs"]["width"] = payload.width
-    comfyui_prompt["5"]["inputs"]["height"] = payload.height
-
-    # set the text prompt for our positive CLIPTextEncode
-    comfyui_prompt["6"]["inputs"]["text"] = payload.prompt
-    comfyui_prompt["7"]["inputs"]["text"] = payload.negative_prompt
-
-    if payload.steps:
-        comfyui_prompt["3"]["inputs"]["steps"] = payload.steps
-
-    comfyui_prompt["3"]["inputs"]["seed"] = (
-        payload.seed if payload.seed else random.randint(0, 18446744073709551614)
-    )
-
-    try:
-        ws = websocket.WebSocket()
-        ws.connect(f"{ws_url}/ws?clientId={client_id}")
-        log.info("WebSocket connection established.")
-    except Exception as e:
-        log.exception(f"Failed to connect to WebSocket server: {e}")
-        return None
-
-    try:
-        images = get_images(ws, comfyui_prompt, client_id, base_url)
-    except Exception as e:
-        log.exception(f"Error while receiving images: {e}")
-        images = None
-
-    ws.close()
-
-    return images

backend/apps/litellm/main.py

@@ -1,372 +1,41 @@
-import sys
+from litellm.proxy.proxy_server import ProxyConfig, initialize
+from litellm.proxy.proxy_server import app
 
-from fastapi import FastAPI, Depends, HTTPException
+from fastapi import FastAPI, Request, Depends, status
-from fastapi.routing import APIRoute
-from fastapi.middleware.cors import CORSMiddleware
-
-import logging
-from fastapi import FastAPI, Request, Depends, status, Response
 from fastapi.responses import JSONResponse
+from utils.utils import get_http_authorization_cred, get_current_user
+from config import ENV
 
-from starlette.middleware.base import BaseHTTPMiddleware, RequestResponseEndpoint
+proxy_config = ProxyConfig()
-from starlette.responses import StreamingResponse
-import json
-import time
-import requests
-
-from pydantic import BaseModel, ConfigDict
-from typing import Optional, List
-
-from utils.utils import get_verified_user, get_current_user, get_admin_user
-from config import SRC_LOG_LEVELS, ENV
-from constants import MESSAGES
-
-import os
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["LITELLM"])
 
 
-from config import (
+async def config():
-    ENABLE_LITELLM,
+    router, model_list, general_settings = await proxy_config.load_config(
-    ENABLE_MODEL_FILTER,
+        router=None, config_file_path="./data/litellm/config.yaml"
-    MODEL_FILTER_LIST,
+    )
-    DATA_DIR,
-    LITELLM_PROXY_PORT,
-    LITELLM_PROXY_HOST,
-)
 
-from litellm.utils import get_llm_provider
+    await initialize(config="./data/litellm/config.yaml", telemetry=False)
-
-import asyncio
-import subprocess
-import yaml
-
-app = FastAPI()
-
-origins = ["*"]
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=origins,
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
 
 
-LITELLM_CONFIG_DIR = f"{DATA_DIR}/litellm/config.yaml"
+async def startup():
-
+    await config()
-with open(LITELLM_CONFIG_DIR, "r") as file:
-    litellm_config = yaml.safe_load(file)
-
-
-app.state.ENABLE = ENABLE_LITELLM
-app.state.CONFIG = litellm_config
-
-# Global variable to store the subprocess reference
-background_process = None
-
-CONFLICT_ENV_VARS = [
-    # Uvicorn uses PORT, so LiteLLM might use it as well
-    "PORT",
-    # LiteLLM uses DATABASE_URL for Prisma connections
-    "DATABASE_URL",
-]
-
-
-async def run_background_process(command):
-    global background_process
-    log.info("run_background_process")
-
-    try:
-        # Log the command to be executed
-        log.info(f"Executing command: {command}")
-        # Filter environment variables known to conflict with litellm
-        env = {k: v for k, v in os.environ.items() if k not in CONFLICT_ENV_VARS}
-        # Execute the command and create a subprocess
-        process = await asyncio.create_subprocess_exec(
-            *command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, env=env
-        )
-        background_process = process
-        log.info("Subprocess started successfully.")
-
-        # Capture STDERR for debugging purposes
-        stderr_output = await process.stderr.read()
-        stderr_text = stderr_output.decode().strip()
-        if stderr_text:
-            log.info(f"Subprocess STDERR: {stderr_text}")
-
-        # log.info output line by line
-        async for line in process.stdout:
-            log.info(line.decode().strip())
-
-        # Wait for the process to finish
-        returncode = await process.wait()
-        log.info(f"Subprocess exited with return code {returncode}")
-    except Exception as e:
-        log.error(f"Failed to start subprocess: {e}")
-        raise  # Optionally re-raise the exception if you want it to propagate
-
-
-async def start_litellm_background():
-    log.info("start_litellm_background")
-    # Command to run in the background
-    command = [
-        "litellm",
-        "--port",
-        str(LITELLM_PROXY_PORT),
-        "--host",
-        LITELLM_PROXY_HOST,
-        "--telemetry",
-        "False",
-        "--config",
-        LITELLM_CONFIG_DIR,
-    ]
-
-    await run_background_process(command)
-
-
-async def shutdown_litellm_background():
-    log.info("shutdown_litellm_background")
-    global background_process
-    if background_process:
-        background_process.terminate()
-        await background_process.wait()  # Ensure the process has terminated
-        log.info("Subprocess terminated")
-        background_process = None
 
 
 @app.on_event("startup")
-async def startup_event():
+async def on_startup():
-    log.info("startup_event")
+    await startup()
-    # TODO: Check config.yaml file and create one
-    asyncio.create_task(start_litellm_background())
 
 
-app.state.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
+@app.middleware("http")
-app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
+async def auth_middleware(request: Request, call_next):
+    auth_header = request.headers.get("Authorization", "")
 
-
+    if ENV != "dev":
-@app.get("/")
-async def get_status():
-    return {"status": True}
-
-
-async def restart_litellm():
-    """
-    Endpoint to restart the litellm background service.
-    """
-    log.info("Requested restart of litellm service.")
-    try:
-        # Shut down the existing process if it is running
-        await shutdown_litellm_background()
-        log.info("litellm service shutdown complete.")
-
-        # Restart the background service
-
-        asyncio.create_task(start_litellm_background())
-        log.info("litellm service restart complete.")
-
-        return {
-            "status": "success",
-            "message": "litellm service restarted successfully.",
-        }
-    except Exception as e:
-        log.info(f"Error restarting litellm service: {e}")
-        raise HTTPException(
-            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=str(e)
-        )
-
-
-@app.get("/restart")
-async def restart_litellm_handler(user=Depends(get_admin_user)):
-    return await restart_litellm()
-
-
-@app.get("/config")
-async def get_config(user=Depends(get_admin_user)):
-    return app.state.CONFIG
-
-
-class LiteLLMConfigForm(BaseModel):
-    general_settings: Optional[dict] = None
-    litellm_settings: Optional[dict] = None
-    model_list: Optional[List[dict]] = None
-    router_settings: Optional[dict] = None
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-@app.post("/config/update")
-async def update_config(form_data: LiteLLMConfigForm, user=Depends(get_admin_user)):
-    app.state.CONFIG = form_data.model_dump(exclude_none=True)
-
-    with open(LITELLM_CONFIG_DIR, "w") as file:
-        yaml.dump(app.state.CONFIG, file)
-
-    await restart_litellm()
-    return app.state.CONFIG
-
-
-@app.get("/models")
-@app.get("/v1/models")
-async def get_models(user=Depends(get_current_user)):
-
-    if app.state.ENABLE:
-        while not background_process:
-            await asyncio.sleep(0.1)
-
-        url = f"http://localhost:{LITELLM_PROXY_PORT}/v1"
-        r = None
         try:
-            r = requests.request(method="GET", url=f"{url}/models")
+            user = get_current_user(get_http_authorization_cred(auth_header))
-            r.raise_for_status()
+            print(user)
-
-            data = r.json()
-
-            if app.state.ENABLE_MODEL_FILTER:
-                if user and user.role == "user":
-                    data["data"] = list(
-                        filter(
-                            lambda model: model["id"] in app.state.MODEL_FILTER_LIST,
-                            data["data"],
-                        )
-                    )
-
-            return data
         except Exception as e:
+            return JSONResponse(status_code=400, content={"detail": str(e)})
 
-            log.exception(e)
+    response = await call_next(request)
-            error_detail = "Open WebUI: Server Connection Error"
+    return response
-            if r is not None:
-                try:
-                    res = r.json()
-                    if "error" in res:
-                        error_detail = f"External: {res['error']}"
-                except:
-                    error_detail = f"External: {e}"
-
-            return {
-                "data": [
-                    {
-                        "id": model["model_name"],
-                        "object": "model",
-                        "created": int(time.time()),
-                        "owned_by": "openai",
-                    }
-                    for model in app.state.CONFIG["model_list"]
-                ],
-                "object": "list",
-            }
-    else:
-        return {
-            "data": [],
-            "object": "list",
-        }
-
-
-@app.get("/model/info")
-async def get_model_list(user=Depends(get_admin_user)):
-    return {"data": app.state.CONFIG["model_list"]}
-
-
-class AddLiteLLMModelForm(BaseModel):
-    model_name: str
-    litellm_params: dict
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-@app.post("/model/new")
-async def add_model_to_config(
-    form_data: AddLiteLLMModelForm, user=Depends(get_admin_user)
-):
-    try:
-        get_llm_provider(model=form_data.model_name)
-        app.state.CONFIG["model_list"].append(form_data.model_dump())
-
-        with open(LITELLM_CONFIG_DIR, "w") as file:
-            yaml.dump(app.state.CONFIG, file)
-
-        await restart_litellm()
-
-        return {"message": MESSAGES.MODEL_ADDED(form_data.model_name)}
-    except Exception as e:
-        print(e)
-        raise HTTPException(
-            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=str(e)
-        )
-
-
-class DeleteLiteLLMModelForm(BaseModel):
-    id: str
-
-
-@app.post("/model/delete")
-async def delete_model_from_config(
-    form_data: DeleteLiteLLMModelForm, user=Depends(get_admin_user)
-):
-    app.state.CONFIG["model_list"] = [
-        model
-        for model in app.state.CONFIG["model_list"]
-        if model["model_name"] != form_data.id
-    ]
-
-    with open(LITELLM_CONFIG_DIR, "w") as file:
-        yaml.dump(app.state.CONFIG, file)
-
-    await restart_litellm()
-
-    return {"message": MESSAGES.MODEL_DELETED(form_data.id)}
-
-
-@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
-async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
-    body = await request.body()
-
-    url = f"http://localhost:{LITELLM_PROXY_PORT}"
-
-    target_url = f"{url}/{path}"
-
-    headers = {}
-    # headers["Authorization"] = f"Bearer {key}"
-    headers["Content-Type"] = "application/json"
-
-    r = None
-
-    try:
-        r = requests.request(
-            method=request.method,
-            url=target_url,
-            data=body,
-            headers=headers,
-            stream=True,
-        )
-
-        r.raise_for_status()
-
-        # Check if response is SSE
-        if "text/event-stream" in r.headers.get("Content-Type", ""):
-            return StreamingResponse(
-                r.iter_content(chunk_size=8192),
-                status_code=r.status_code,
-                headers=dict(r.headers),
-            )
-        else:
-            response_data = r.json()
-            return response_data
-    except Exception as e:
-        log.exception(e)
-        error_detail = "Open WebUI: Server Connection Error"
-        if r is not None:
-            try:
-                res = r.json()
-                if "error" in res:
-                    error_detail = f"External: {res['error']['message'] if 'message' in res['error'] else res['error']}"
-            except:
-                error_detail = f"External: {e}"
-
-        raise HTTPException(
-            status_code=r.status_code if r else 500, detail=error_detail
-        )

backend/apps/ollama/main.py

@@ -1,50 +1,24 @@
-from fastapi import (
+from fastapi import FastAPI, Request, Response, HTTPException, Depends, status
-    FastAPI,
-    Request,
-    Response,
-    HTTPException,
-    Depends,
-    status,
-    UploadFile,
-    File,
-    BackgroundTasks,
-)
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import StreamingResponse
 from fastapi.concurrency import run_in_threadpool
 
 from pydantic import BaseModel, ConfigDict
 
-import os
-import re
-import copy
 import random
 import requests
 import json
 import uuid
 import aiohttp
 import asyncio
-import logging
-from urllib.parse import urlparse
-from typing import Optional, List, Union
-
 
 from apps.web.models.users import Users
 from constants import ERROR_MESSAGES
 from utils.utils import decode_token, get_current_user, get_admin_user
+from config import OLLAMA_BASE_URLS
 
+from typing import Optional, List, Union
 
-from config import (
-    SRC_LOG_LEVELS,
-    OLLAMA_BASE_URLS,
-    ENABLE_MODEL_FILTER,
-    MODEL_FILTER_LIST,
-    UPLOAD_DIR,
-)
-from utils.misc import calculate_sha256
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["OLLAMA"])
 
 app = FastAPI()
 app.add_middleware(
@@ -56,8 +30,8 @@ app.add_middleware(
 )
 
 
-app.state.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
+app.state.MODEL_FILTER_ENABLED = False
-app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
+app.state.MODEL_LIST = []
 
 app.state.OLLAMA_BASE_URLS = OLLAMA_BASE_URLS
 app.state.MODELS = {}
@@ -82,12 +56,6 @@ async def check_url(request: Request, call_next):
     return response
 
 
-@app.head("/")
-@app.get("/")
-async def get_status():
-    return {"status": True}
-
-
 @app.get("/urls")
 async def get_ollama_api_urls(user=Depends(get_admin_user)):
     return {"OLLAMA_BASE_URLS": app.state.OLLAMA_BASE_URLS}
@@ -101,7 +69,7 @@ class UrlUpdateForm(BaseModel):
 async def update_ollama_api_url(form_data: UrlUpdateForm, user=Depends(get_admin_user)):
     app.state.OLLAMA_BASE_URLS = form_data.urls
 
-    log.info(f"app.state.OLLAMA_BASE_URLS: {app.state.OLLAMA_BASE_URLS}")
+    print(app.state.OLLAMA_BASE_URLS)
     return {"OLLAMA_BASE_URLS": app.state.OLLAMA_BASE_URLS}
 
 
@@ -122,7 +90,7 @@ async def fetch_url(url):
                 return await response.json()
     except Exception as e:
         # Handle connection error here
-        log.error(f"Connection error: {e}")
+        print(f"Connection error: {e}")
         return None
 
 
@@ -130,14 +98,13 @@ def merge_models_lists(model_lists):
     merged_models = {}
 
     for idx, model_list in enumerate(model_lists):
-        if model_list is not None:
+        for model in model_list:
-            for model in model_list:
+            digest = model["digest"]
-                digest = model["digest"]
+            if digest not in merged_models:
-                if digest not in merged_models:
+                model["urls"] = [idx]
-                    model["urls"] = [idx]
+                merged_models[digest] = model
-                    merged_models[digest] = model
+            else:
-                else:
+                merged_models[digest]["urls"].append(idx)
-                    merged_models[digest]["urls"].append(idx)
 
     return list(merged_models.values())
 
@@ -146,16 +113,16 @@ def merge_models_lists(model_lists):
 
 
 async def get_all_models():
-    log.info("get_all_models()")
+    print("get_all_models")
     tasks = [fetch_url(f"{url}/api/tags") for url in app.state.OLLAMA_BASE_URLS]
     responses = await asyncio.gather(*tasks)
+    responses = list(filter(lambda x: x is not None, responses))
 
     models = {
         "models": merge_models_lists(
-            map(lambda response: response["models"] if response else None, responses)
+            map(lambda response: response["models"], responses)
         )
     }
-
     app.state.MODELS = {model["model"]: model for model in models["models"]}
 
     return models
@@ -169,11 +136,11 @@ async def get_ollama_tags(
     if url_idx == None:
         models = await get_all_models()
 
-        if app.state.ENABLE_MODEL_FILTER:
+        if app.state.MODEL_FILTER_ENABLED:
             if user.role == "user":
                 models["models"] = list(
                     filter(
-                        lambda model: model["name"] in app.state.MODEL_FILTER_LIST,
+                        lambda model: model["name"] in app.state.MODEL_LIST,
                         models["models"],
                     )
                 )
@@ -187,7 +154,7 @@ async def get_ollama_tags(
 
             return r.json()
         except Exception as e:
-            log.exception(e)
+            print(e)
             error_detail = "Open WebUI: Server Connection Error"
             if r is not None:
                 try:
@@ -214,20 +181,11 @@ async def get_ollama_versions(url_idx: Optional[int] = None):
         responses = await asyncio.gather(*tasks)
         responses = list(filter(lambda x: x is not None, responses))
 
-        if len(responses) > 0:
+        lowest_version = min(
-            lowest_version = min(
+            responses, key=lambda x: tuple(map(int, x["version"].split(".")))
-                responses,
+        )
-                key=lambda x: tuple(
-                    map(int, re.sub(r"^v|-.*", "", x["version"]).split("."))
-                ),
-            )
 
-            return {"version": lowest_version["version"]}
+        return {"version": lowest_version["version"]}
-        else:
-            raise HTTPException(
-                status_code=500,
-                detail=ERROR_MESSAGES.OLLAMA_NOT_FOUND,
-            )
     else:
         url = app.state.OLLAMA_BASE_URLS[url_idx]
         try:
@@ -236,7 +194,7 @@ async def get_ollama_versions(url_idx: Optional[int] = None):
 
             return r.json()
         except Exception as e:
-            log.exception(e)
+            print(e)
             error_detail = "Open WebUI: Server Connection Error"
             if r is not None:
                 try:
@@ -262,33 +220,18 @@ async def pull_model(
     form_data: ModelNameForm, url_idx: int = 0, user=Depends(get_admin_user)
 ):
     url = app.state.OLLAMA_BASE_URLS[url_idx]
-    log.info(f"url: {url}")
+    print(url)
 
     r = None
 
     def get_request():
         nonlocal url
         nonlocal r
-
-        request_id = str(uuid.uuid4())
         try:
-            REQUEST_POOL.append(request_id)
 
             def stream_content():
-                try:
+                for chunk in r.iter_content(chunk_size=8192):
-                    yield json.dumps({"id": request_id, "done": False}) + "\n"
+                    yield chunk
-
-                    for chunk in r.iter_content(chunk_size=8192):
-                        if request_id in REQUEST_POOL:
-                            yield chunk
-                        else:
-                            log.warning("User: canceled request")
-                            break
-                finally:
-                    if hasattr(r, "close"):
-                        r.close()
-                        if request_id in REQUEST_POOL:
-                            REQUEST_POOL.remove(request_id)
 
             r = requests.request(
                 method="POST",
@@ -309,9 +252,8 @@ async def pull_model(
 
     try:
         return await run_in_threadpool(get_request)
-
     except Exception as e:
-        log.exception(e)
+        print(e)
         error_detail = "Open WebUI: Server Connection Error"
         if r is not None:
             try:
@@ -350,7 +292,7 @@ async def push_model(
             )
 
     url = app.state.OLLAMA_BASE_URLS[url_idx]
-    log.debug(f"url: {url}")
+    print(url)
 
     r = None
 
@@ -382,7 +324,7 @@ async def push_model(
     try:
         return await run_in_threadpool(get_request)
     except Exception as e:
-        log.exception(e)
+        print(e)
         error_detail = "Open WebUI: Server Connection Error"
         if r is not None:
             try:
@@ -410,9 +352,9 @@ class CreateModelForm(BaseModel):
 async def create_model(
     form_data: CreateModelForm, url_idx: int = 0, user=Depends(get_admin_user)
 ):
-    log.debug(f"form_data: {form_data}")
+    print(form_data)
     url = app.state.OLLAMA_BASE_URLS[url_idx]
-    log.info(f"url: {url}")
+    print(url)
 
     r = None
 
@@ -434,7 +376,7 @@ async def create_model(
 
             r.raise_for_status()
 
-            log.debug(f"r: {r}")
+            print(r)
 
             return StreamingResponse(
                 stream_content(),
@@ -447,7 +389,7 @@ async def create_model(
     try:
         return await run_in_threadpool(get_request)
     except Exception as e:
-        log.exception(e)
+        print(e)
         error_detail = "Open WebUI: Server Connection Error"
         if r is not None:
             try:
@@ -485,7 +427,7 @@ async def copy_model(
             )
 
     url = app.state.OLLAMA_BASE_URLS[url_idx]
-    log.info(f"url: {url}")
+    print(url)
 
     try:
         r = requests.request(
@@ -495,11 +437,11 @@ async def copy_model(
         )
         r.raise_for_status()
 
-        log.debug(f"r.text: {r.text}")
+        print(r.text)
 
         return True
     except Exception as e:
-        log.exception(e)
+        print(e)
         error_detail = "Open WebUI: Server Connection Error"
         if r is not None:
             try:
@@ -532,7 +474,7 @@ async def delete_model(
             )
 
     url = app.state.OLLAMA_BASE_URLS[url_idx]
-    log.info(f"url: {url}")
+    print(url)
 
     try:
         r = requests.request(
@@ -542,11 +484,11 @@ async def delete_model(
         )
         r.raise_for_status()
 
-        log.debug(f"r.text: {r.text}")
+        print(r.text)
 
         return True
     except Exception as e:
-        log.exception(e)
+        print(e)
         error_detail = "Open WebUI: Server Connection Error"
         if r is not None:
             try:
@@ -572,7 +514,7 @@ async def show_model_info(form_data: ModelNameForm, user=Depends(get_current_use
 
     url_idx = random.choice(app.state.MODELS[form_data.name]["urls"])
     url = app.state.OLLAMA_BASE_URLS[url_idx]
-    log.info(f"url: {url}")
+    print(url)
 
     try:
         r = requests.request(
@@ -584,7 +526,7 @@ async def show_model_info(form_data: ModelNameForm, user=Depends(get_current_use
 
         return r.json()
     except Exception as e:
-        log.exception(e)
+        print(e)
         error_detail = "Open WebUI: Server Connection Error"
         if r is not None:
             try:
@@ -615,13 +557,8 @@ async def generate_embeddings(
     user=Depends(get_current_user),
 ):
     if url_idx == None:
-        model = form_data.model
+        if form_data.model in app.state.MODELS:
-
+            url_idx = random.choice(app.state.MODELS[form_data.model]["urls"])
-        if ":" not in model:
-            model = f"{model}:latest"
-
-        if model in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[model]["urls"])
         else:
             raise HTTPException(
                 status_code=400,
@@ -629,7 +566,7 @@ async def generate_embeddings(
             )
 
     url = app.state.OLLAMA_BASE_URLS[url_idx]
-    log.info(f"url: {url}")
+    print(url)
 
     try:
         r = requests.request(
@@ -641,7 +578,7 @@ async def generate_embeddings(
 
         return r.json()
     except Exception as e:
-        log.exception(e)
+        print(e)
         error_detail = "Open WebUI: Server Connection Error"
         if r is not None:
             try:
@@ -657,60 +594,6 @@ async def generate_embeddings(
         )
 
 
-def generate_ollama_embeddings(
-    form_data: GenerateEmbeddingsForm,
-    url_idx: Optional[int] = None,
-):
-
-    log.info(f"generate_ollama_embeddings {form_data}")
-
-    if url_idx == None:
-        model = form_data.model
-
-        if ":" not in model:
-            model = f"{model}:latest"
-
-        if model in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[model]["urls"])
-        else:
-            raise HTTPException(
-                status_code=400,
-                detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model),
-            )
-
-    url = app.state.OLLAMA_BASE_URLS[url_idx]
-    log.info(f"url: {url}")
-
-    try:
-        r = requests.request(
-            method="POST",
-            url=f"{url}/api/embeddings",
-            data=form_data.model_dump_json(exclude_none=True).encode(),
-        )
-        r.raise_for_status()
-
-        data = r.json()
-
-        log.info(f"generate_ollama_embeddings {data}")
-
-        if "embedding" in data:
-            return data["embedding"]
-        else:
-            raise "Something went wrong :/"
-    except Exception as e:
-        log.exception(e)
-        error_detail = "Open WebUI: Server Connection Error"
-        if r is not None:
-            try:
-                res = r.json()
-                if "error" in res:
-                    error_detail = f"Ollama: {res['error']}"
-            except:
-                error_detail = f"Ollama: {e}"
-
-        raise error_detail
-
-
 class GenerateCompletionForm(BaseModel):
     model: str
     prompt: str
@@ -734,21 +617,16 @@ async def generate_completion(
 ):
 
     if url_idx == None:
-        model = form_data.model
+        if form_data.model in app.state.MODELS:
-
+            url_idx = random.choice(app.state.MODELS[form_data.model]["urls"])
-        if ":" not in model:
-            model = f"{model}:latest"
-
-        if model in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[model]["urls"])
         else:
             raise HTTPException(
                 status_code=400,
-                detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model),
+                detail="error_detail",
             )
 
     url = app.state.OLLAMA_BASE_URLS[url_idx]
-    log.info(f"url: {url}")
+    print(url)
 
     r = None
 
@@ -769,7 +647,7 @@ async def generate_completion(
                         if request_id in REQUEST_POOL:
                             yield chunk
                         else:
-                            log.warning("User: canceled request")
+                            print("User: canceled request")
                             break
                 finally:
                     if hasattr(r, "close"):
@@ -824,7 +702,7 @@ class GenerateChatCompletionForm(BaseModel):
     format: Optional[str] = None
     options: Optional[dict] = None
     template: Optional[str] = None
-    stream: Optional[bool] = None
+    stream: Optional[bool] = True
     keep_alive: Optional[Union[int, str]] = None
 
 
@@ -837,13 +715,8 @@ async def generate_chat_completion(
 ):
 
     if url_idx == None:
-        model = form_data.model
+        if form_data.model in app.state.MODELS:
-
+            url_idx = random.choice(app.state.MODELS[form_data.model]["urls"])
-        if ":" not in model:
-            model = f"{model}:latest"
-
-        if model in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[model]["urls"])
         else:
             raise HTTPException(
                 status_code=400,
@@ -851,15 +724,11 @@ async def generate_chat_completion(
             )
 
     url = app.state.OLLAMA_BASE_URLS[url_idx]
-    log.info(f"url: {url}")
+    print(url)
 
     r = None
 
-    log.debug(
+    print(form_data.model_dump_json(exclude_none=True).encode())
-        "form_data.model_dump_json(exclude_none=True).encode(): {0} ".format(
-            form_data.model_dump_json(exclude_none=True).encode()
-        )
-    )
 
     def get_request():
         nonlocal form_data
@@ -878,7 +747,7 @@ async def generate_chat_completion(
                         if request_id in REQUEST_POOL:
                             yield chunk
                         else:
-                            log.warning("User: canceled request")
+                            print("User: canceled request")
                             break
                 finally:
                     if hasattr(r, "close"):
@@ -901,7 +770,7 @@ async def generate_chat_completion(
                 headers=dict(r.headers),
             )
         except Exception as e:
-            log.exception(e)
+            print(e)
             raise e
 
     try:
@@ -946,13 +815,8 @@ async def generate_openai_chat_completion(
 ):
 
     if url_idx == None:
-        model = form_data.model
+        if form_data.model in app.state.MODELS:
-
+            url_idx = random.choice(app.state.MODELS[form_data.model]["urls"])
-        if ":" not in model:
-            model = f"{model}:latest"
-
-        if model in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[model]["urls"])
         else:
             raise HTTPException(
                 status_code=400,
@@ -960,7 +824,7 @@ async def generate_openai_chat_completion(
             )
 
     url = app.state.OLLAMA_BASE_URLS[url_idx]
-    log.info(f"url: {url}")
+    print(url)
 
     r = None
 
@@ -983,7 +847,7 @@ async def generate_openai_chat_completion(
                         if request_id in REQUEST_POOL:
                             yield chunk
                         else:
-                            log.warning("User: canceled request")
+                            print("User: canceled request")
                             break
                 finally:
                     if hasattr(r, "close"):
@@ -1026,220 +890,6 @@ async def generate_openai_chat_completion(
         )
 
 
-class UrlForm(BaseModel):
-    url: str
-
-
-class UploadBlobForm(BaseModel):
-    filename: str
-
-
-def parse_huggingface_url(hf_url):
-    try:
-        # Parse the URL
-        parsed_url = urlparse(hf_url)
-
-        # Get the path and split it into components
-        path_components = parsed_url.path.split("/")
-
-        # Extract the desired output
-        user_repo = "/".join(path_components[1:3])
-        model_file = path_components[-1]
-
-        return model_file
-    except ValueError:
-        return None
-
-
-async def download_file_stream(
-    ollama_url, file_url, file_path, file_name, chunk_size=1024 * 1024
-):
-    done = False
-
-    if os.path.exists(file_path):
-        current_size = os.path.getsize(file_path)
-    else:
-        current_size = 0
-
-    headers = {"Range": f"bytes={current_size}-"} if current_size > 0 else {}
-
-    timeout = aiohttp.ClientTimeout(total=600)  # Set the timeout
-
-    async with aiohttp.ClientSession(timeout=timeout) as session:
-        async with session.get(file_url, headers=headers) as response:
-            total_size = int(response.headers.get("content-length", 0)) + current_size
-
-            with open(file_path, "ab+") as file:
-                async for data in response.content.iter_chunked(chunk_size):
-                    current_size += len(data)
-                    file.write(data)
-
-                    done = current_size == total_size
-                    progress = round((current_size / total_size) * 100, 2)
-
-                    yield f'data: {{"progress": {progress}, "completed": {current_size}, "total": {total_size}}}\n\n'
-
-                if done:
-                    file.seek(0)
-                    hashed = calculate_sha256(file)
-                    file.seek(0)
-
-                    url = f"{ollama_url}/api/blobs/sha256:{hashed}"
-                    response = requests.post(url, data=file)
-
-                    if response.ok:
-                        res = {
-                            "done": done,
-                            "blob": f"sha256:{hashed}",
-                            "name": file_name,
-                        }
-                        os.remove(file_path)
-
-                        yield f"data: {json.dumps(res)}\n\n"
-                    else:
-                        raise "Ollama: Could not create blob, Please try again."
-
-
-# def number_generator():
-#     for i in range(1, 101):
-#         yield f"data: {i}\n"
-
-
-# url = "https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF/resolve/main/stablelm-zephyr-3b.Q2_K.gguf"
-@app.post("/models/download")
-@app.post("/models/download/{url_idx}")
-async def download_model(
-    form_data: UrlForm,
-    url_idx: Optional[int] = None,
-):
-
-    allowed_hosts = ["https://huggingface.co/", "https://github.com/"]
-
-    if not any(form_data.url.startswith(host) for host in allowed_hosts):
-        raise HTTPException(
-            status_code=400,
-            detail="Invalid file_url. Only URLs from allowed hosts are permitted.",
-        )
-
-    if url_idx == None:
-        url_idx = 0
-    url = app.state.OLLAMA_BASE_URLS[url_idx]
-
-    file_name = parse_huggingface_url(form_data.url)
-
-    if file_name:
-        file_path = f"{UPLOAD_DIR}/{file_name}"
-
-        return StreamingResponse(
-            download_file_stream(url, form_data.url, file_path, file_name),
-        )
-    else:
-        return None
-
-
-@app.post("/models/upload")
-@app.post("/models/upload/{url_idx}")
-def upload_model(file: UploadFile = File(...), url_idx: Optional[int] = None):
-    if url_idx == None:
-        url_idx = 0
-    ollama_url = app.state.OLLAMA_BASE_URLS[url_idx]
-
-    file_path = f"{UPLOAD_DIR}/{file.filename}"
-
-    # Save file in chunks
-    with open(file_path, "wb+") as f:
-        for chunk in file.file:
-            f.write(chunk)
-
-    def file_process_stream():
-        nonlocal ollama_url
-        total_size = os.path.getsize(file_path)
-        chunk_size = 1024 * 1024
-        try:
-            with open(file_path, "rb") as f:
-                total = 0
-                done = False
-
-                while not done:
-                    chunk = f.read(chunk_size)
-                    if not chunk:
-                        done = True
-                        continue
-
-                    total += len(chunk)
-                    progress = round((total / total_size) * 100, 2)
-
-                    res = {
-                        "progress": progress,
-                        "total": total_size,
-                        "completed": total,
-                    }
-                    yield f"data: {json.dumps(res)}\n\n"
-
-                if done:
-                    f.seek(0)
-                    hashed = calculate_sha256(f)
-                    f.seek(0)
-
-                    url = f"{ollama_url}/api/blobs/sha256:{hashed}"
-                    response = requests.post(url, data=f)
-
-                    if response.ok:
-                        res = {
-                            "done": done,
-                            "blob": f"sha256:{hashed}",
-                            "name": file.filename,
-                        }
-                        os.remove(file_path)
-                        yield f"data: {json.dumps(res)}\n\n"
-                    else:
-                        raise Exception(
-                            "Ollama: Could not create blob, Please try again."
-                        )
-
-        except Exception as e:
-            res = {"error": str(e)}
-            yield f"data: {json.dumps(res)}\n\n"
-
-    return StreamingResponse(file_process_stream(), media_type="text/event-stream")
-
-
-# async def upload_model(file: UploadFile = File(), url_idx: Optional[int] = None):
-#     if url_idx == None:
-#         url_idx = 0
-#     url = app.state.OLLAMA_BASE_URLS[url_idx]
-
-#     file_location = os.path.join(UPLOAD_DIR, file.filename)
-#     total_size = file.size
-
-#     async def file_upload_generator(file):
-#         print(file)
-#         try:
-#             async with aiofiles.open(file_location, "wb") as f:
-#                 completed_size = 0
-#                 while True:
-#                     chunk = await file.read(1024*1024)
-#                     if not chunk:
-#                         break
-#                     await f.write(chunk)
-#                     completed_size += len(chunk)
-#                     progress = (completed_size / total_size) * 100
-
-#                     print(progress)
-#                     yield f'data: {json.dumps({"status": "uploading", "percentage": progress, "total": total_size, "completed": completed_size, "done": False})}\n'
-#         except Exception as e:
-#             print(e)
-#             yield f"data: {json.dumps({'status': 'error', 'message': str(e)})}\n"
-#         finally:
-#             await file.close()
-#             print("done")
-#             yield f'data: {json.dumps({"status": "completed", "percentage": 100, "total": total_size, "completed": completed_size, "done": True})}\n'
-
-#     return StreamingResponse(
-#         file_upload_generator(copy.deepcopy(file)), media_type="text/event-stream"
-#     )
-
-
 @app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
 async def deprecated_proxy(path: str, request: Request, user=Depends(get_current_user)):
     url = app.state.OLLAMA_BASE_URLS[0]
@@ -1290,7 +940,7 @@ async def deprecated_proxy(path: str, request: Request, user=Depends(get_current
                         if request_id in REQUEST_POOL:
                             yield chunk
                         else:
-                            log.warning("User: canceled request")
+                            print("User: canceled request")
                             break
                 finally:
                     if hasattr(r, "close"):

backend/apps/openai/main.py

@@ -6,7 +6,6 @@ import requests
 import aiohttp
 import asyncio
 import json
-import logging
 
 from pydantic import BaseModel
 
@@ -19,23 +18,13 @@ from utils.utils import (
     get_verified_user,
     get_admin_user,
 )
-from config import (
+from config import OPENAI_API_BASE_URLS, OPENAI_API_KEYS, CACHE_DIR
-    SRC_LOG_LEVELS,
-    OPENAI_API_BASE_URLS,
-    OPENAI_API_KEYS,
-    CACHE_DIR,
-    ENABLE_MODEL_FILTER,
-    MODEL_FILTER_LIST,
-)
 from typing import List, Optional
 
 
 import hashlib
 from pathlib import Path
 
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["OPENAI"])
-
 app = FastAPI()
 app.add_middleware(
     CORSMiddleware,
@@ -45,8 +34,8 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-app.state.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
+app.state.MODEL_FILTER_ENABLED = False
-app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
+app.state.MODEL_LIST = []
 
 app.state.OPENAI_API_BASE_URLS = OPENAI_API_BASE_URLS
 app.state.OPENAI_API_KEYS = OPENAI_API_KEYS
@@ -80,7 +69,6 @@ async def get_openai_urls(user=Depends(get_admin_user)):
 
 @app.post("/urls/update")
 async def update_openai_urls(form_data: UrlsUpdateForm, user=Depends(get_admin_user)):
-    await get_all_models()
     app.state.OPENAI_API_BASE_URLS = form_data.urls
     return {"OPENAI_API_BASE_URLS": app.state.OPENAI_API_BASE_URLS}
 
@@ -117,7 +105,6 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEYS[idx]}"
         headers["Content-Type"] = "application/json"
 
-        r = None
         try:
             r = requests.post(
                 url=f"{app.state.OPENAI_API_BASE_URLS[idx]}/audio/speech",
@@ -140,7 +127,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
             return FileResponse(file_path)
 
         except Exception as e:
-            log.exception(e)
+            print(e)
             error_detail = "Open WebUI: Server Connection Error"
             if r is not None:
                 try:
@@ -150,9 +137,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
                 except:
                     error_detail = f"External: {e}"
 
-            raise HTTPException(
+            raise HTTPException(status_code=r.status_code, detail=error_detail)
-                status_code=r.status_code if r else 500, detail=error_detail
-            )
 
     except ValueError:
         raise HTTPException(status_code=401, detail=ERROR_MESSAGES.OPENAI_NOT_FOUND)
@@ -166,61 +151,42 @@ async def fetch_url(url, key):
                 return await response.json()
     except Exception as e:
         # Handle connection error here
-        log.error(f"Connection error: {e}")
+        print(f"Connection error: {e}")
         return None
 
 
 def merge_models_lists(model_lists):
-    log.info(f"merge_models_lists {model_lists}")
     merged_list = []
 
     for idx, models in enumerate(model_lists):
-        if models is not None and "error" not in models:
+        merged_list.extend(
-            merged_list.extend(
+            [
-                [
+                {**model, "urlIdx": idx}
-                    {**model, "urlIdx": idx}
+                for model in models
-                    for model in models
+                if "api.openai.com" not in app.state.OPENAI_API_BASE_URLS[idx]
-                    if "api.openai.com" not in app.state.OPENAI_API_BASE_URLS[idx]
+                or "gpt" in model["id"]
-                    or "gpt" in model["id"]
+            ]
-                ]
+        )
-            )
 
     return merged_list
 
 
 async def get_all_models():
-    log.info("get_all_models()")
+    print("get_all_models")
+    tasks = [
+        fetch_url(f"{url}/models", app.state.OPENAI_API_KEYS[idx])
+        for idx, url in enumerate(app.state.OPENAI_API_BASE_URLS)
+    ]
+    responses = await asyncio.gather(*tasks)
+    responses = list(filter(lambda x: x is not None and "error" not in x, responses))
+    models = {
+        "data": merge_models_lists(
+            list(map(lambda response: response["data"], responses))
+        )
+    }
+    app.state.MODELS = {model["id"]: model for model in models["data"]}
 
-    if len(app.state.OPENAI_API_KEYS) == 1 and app.state.OPENAI_API_KEYS[0] == "":
+    return models
-        models = {"data": []}
-    else:
-        tasks = [
-            fetch_url(f"{url}/models", app.state.OPENAI_API_KEYS[idx])
-            for idx, url in enumerate(app.state.OPENAI_API_BASE_URLS)
-        ]
-
-        responses = await asyncio.gather(*tasks)
-        log.info(f"get_all_models:responses() {responses}")
-
-        models = {
-            "data": merge_models_lists(
-                list(
-                    map(
-                        lambda response: (
-                            response["data"]
-                            if (response and "data" in response)
-                            else (response if isinstance(response, list) else None)
-                        ),
-                        responses,
-                    )
-                )
-            )
-        }
-
-        log.info(f"models: {models}")
-        app.state.MODELS = {model["id"]: model for model in models["data"]}
-
-        return models
 
 
 @app.get("/models")
@@ -228,11 +194,11 @@ async def get_all_models():
 async def get_models(url_idx: Optional[int] = None, user=Depends(get_current_user)):
     if url_idx == None:
         models = await get_all_models()
-        if app.state.ENABLE_MODEL_FILTER:
+        if app.state.MODEL_FILTER_ENABLED:
             if user.role == "user":
                 models["data"] = list(
                     filter(
-                        lambda model: model["id"] in app.state.MODEL_FILTER_LIST,
+                        lambda model: model["id"] in app.state.MODEL_LIST,
                         models["data"],
                     )
                 )
@@ -240,9 +206,6 @@ async def get_models(url_idx: Optional[int] = None, user=Depends(get_current_use
         return models
     else:
         url = app.state.OPENAI_API_BASE_URLS[url_idx]
-
-        r = None
-
         try:
             r = requests.request(method="GET", url=f"{url}/models")
             r.raise_for_status()
@@ -255,7 +218,7 @@ async def get_models(url_idx: Optional[int] = None, user=Depends(get_current_use
 
             return response_data
         except Exception as e:
-            log.exception(e)
+            print(e)
             error_detail = "Open WebUI: Server Connection Error"
             if r is not None:
                 try:
@@ -289,7 +252,7 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
         if body.get("model") == "gpt-4-vision-preview":
             if "max_tokens" not in body:
                 body["max_tokens"] = 4000
-            log.debug("Modified body_dict:", body)
+            print("Modified body_dict:", body)
 
         # Fix for ChatGPT calls failing because the num_ctx key is in body
         if "num_ctx" in body:
@@ -301,7 +264,7 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
         # Convert the modified body back to JSON
         body = json.dumps(body)
     except json.JSONDecodeError as e:
-        log.error("Error loading request body into a dictionary:", e)
+        print("Error loading request body into a dictionary:", e)
 
     url = app.state.OPENAI_API_BASE_URLS[idx]
     key = app.state.OPENAI_API_KEYS[idx]
@@ -315,8 +278,6 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
     headers["Authorization"] = f"Bearer {key}"
     headers["Content-Type"] = "application/json"
 
-    r = None
-
     try:
         r = requests.request(
             method=request.method,
@@ -339,16 +300,14 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
             response_data = r.json()
             return response_data
     except Exception as e:
-        log.exception(e)
+        print(e)
         error_detail = "Open WebUI: Server Connection Error"
         if r is not None:
             try:
                 res = r.json()
                 if "error" in res:
-                    error_detail = f"External: {res['error']['message'] if 'message' in res['error'] else res['error']}"
+                    error_detail = f"External: {res['error']}"
             except:
                 error_detail = f"External: {e}"
 
-        raise HTTPException(
+        raise HTTPException(status_code=r.status_code, detail=error_detail)
-            status_code=r.status_code if r else 500, detail=error_detail
-        )

backend/apps/rag/main.py

@@ -8,19 +8,19 @@ from fastapi import (
     Form,
 )
 from fastapi.middleware.cors import CORSMiddleware
-import os, shutil, logging, re
+import os, shutil
 
 from pathlib import Path
 from typing import List
 
-from chromadb.utils.batch_utils import create_batches
+from sentence_transformers import SentenceTransformer
+from chromadb.utils import embedding_functions
 
 from langchain_community.document_loaders import (
     WebBaseLoader,
     TextLoader,
     PyPDFLoader,
     CSVLoader,
-    BSHTMLLoader,
     Docx2txtLoader,
     UnstructuredEPubLoader,
     UnstructuredWordDocumentLoader,
@@ -28,22 +28,15 @@ from langchain_community.document_loaders import (
     UnstructuredXMLLoader,
     UnstructuredRSTLoader,
     UnstructuredExcelLoader,
-    YoutubeLoader,
 )
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 
-import validators
-import urllib.parse
-import socket
-
-
 from pydantic import BaseModel
 from typing import Optional
 import mimetypes
 import uuid
 import json
 
-import sentence_transformers
 
 from apps.web.models.documents import (
     Documents,
@@ -51,14 +44,7 @@ from apps.web.models.documents import (
     DocumentResponse,
 )
 
-from apps.rag.utils import (
+from apps.rag.utils import query_doc, query_collection
-    get_model_path,
-    get_embedding_function,
-    query_doc,
-    query_doc_with_hybrid_search,
-    query_collection,
-    query_collection_with_hybrid_search,
-)
 
 from utils.misc import (
     calculate_sha256,
@@ -67,108 +53,46 @@ from utils.misc import (
     extract_folders_after_data_docs,
 )
 from utils.utils import get_current_user, get_admin_user
-
 from config import (
-    SRC_LOG_LEVELS,
     UPLOAD_DIR,
     DOCS_DIR,
-    RAG_TOP_K,
-    RAG_RELEVANCE_THRESHOLD,
-    RAG_EMBEDDING_ENGINE,
     RAG_EMBEDDING_MODEL,
-    RAG_EMBEDDING_MODEL_AUTO_UPDATE,
+    RAG_EMBEDDING_MODEL_DEVICE_TYPE,
-    RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
-    ENABLE_RAG_HYBRID_SEARCH,
-    RAG_RERANKING_MODEL,
-    PDF_EXTRACT_IMAGES,
-    RAG_RERANKING_MODEL_AUTO_UPDATE,
-    RAG_RERANKING_MODEL_TRUST_REMOTE_CODE,
-    RAG_OPENAI_API_BASE_URL,
-    RAG_OPENAI_API_KEY,
-    DEVICE_TYPE,
     CHROMA_CLIENT,
     CHUNK_SIZE,
     CHUNK_OVERLAP,
     RAG_TEMPLATE,
-    ENABLE_LOCAL_WEB_FETCH,
 )
 
 from constants import ERROR_MESSAGES
 
-log = logging.getLogger(__name__)
+#
-log.setLevel(SRC_LOG_LEVELS["RAG"])
+# if RAG_EMBEDDING_MODEL:
+#    sentence_transformer_ef = SentenceTransformer(
+#        model_name_or_path=RAG_EMBEDDING_MODEL,
+#        cache_folder=RAG_EMBEDDING_MODEL_DIR,
+#        device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
+#    )
+
 
 app = FastAPI()
 
-app.state.TOP_K = RAG_TOP_K
-app.state.RELEVANCE_THRESHOLD = RAG_RELEVANCE_THRESHOLD
-
-app.state.ENABLE_RAG_HYBRID_SEARCH = ENABLE_RAG_HYBRID_SEARCH
-
 app.state.CHUNK_SIZE = CHUNK_SIZE
 app.state.CHUNK_OVERLAP = CHUNK_OVERLAP
-
-app.state.RAG_EMBEDDING_ENGINE = RAG_EMBEDDING_ENGINE
-app.state.RAG_EMBEDDING_MODEL = RAG_EMBEDDING_MODEL
-app.state.RAG_RERANKING_MODEL = RAG_RERANKING_MODEL
 app.state.RAG_TEMPLATE = RAG_TEMPLATE
+app.state.RAG_EMBEDDING_MODEL = RAG_EMBEDDING_MODEL
+app.state.TOP_K = 4
 
-app.state.OPENAI_API_BASE_URL = RAG_OPENAI_API_BASE_URL
+app.state.sentence_transformer_ef = (
-app.state.OPENAI_API_KEY = RAG_OPENAI_API_KEY
+    embedding_functions.SentenceTransformerEmbeddingFunction(
-
+        model_name=app.state.RAG_EMBEDDING_MODEL,
-app.state.PDF_EXTRACT_IMAGES = PDF_EXTRACT_IMAGES
+        device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
-
+    )
-
-def update_embedding_model(
-    embedding_model: str,
-    update_model: bool = False,
-):
-    if embedding_model and app.state.RAG_EMBEDDING_ENGINE == "":
-        app.state.sentence_transformer_ef = sentence_transformers.SentenceTransformer(
-            get_model_path(embedding_model, update_model),
-            device=DEVICE_TYPE,
-            trust_remote_code=RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
-        )
-    else:
-        app.state.sentence_transformer_ef = None
-
-
-def update_reranking_model(
-    reranking_model: str,
-    update_model: bool = False,
-):
-    if reranking_model:
-        app.state.sentence_transformer_rf = sentence_transformers.CrossEncoder(
-            get_model_path(reranking_model, update_model),
-            device=DEVICE_TYPE,
-            trust_remote_code=RAG_RERANKING_MODEL_TRUST_REMOTE_CODE,
-        )
-    else:
-        app.state.sentence_transformer_rf = None
-
-
-update_embedding_model(
-    app.state.RAG_EMBEDDING_MODEL,
-    RAG_EMBEDDING_MODEL_AUTO_UPDATE,
 )
 
-update_reranking_model(
-    app.state.RAG_RERANKING_MODEL,
-    RAG_RERANKING_MODEL_AUTO_UPDATE,
-)
-
-
-app.state.EMBEDDING_FUNCTION = get_embedding_function(
-    app.state.RAG_EMBEDDING_ENGINE,
-    app.state.RAG_EMBEDDING_MODEL,
-    app.state.sentence_transformer_ef,
-    app.state.OPENAI_API_KEY,
-    app.state.OPENAI_API_BASE_URL,
-)
 
 origins = ["*"]
 
-
 app.add_middleware(
     CORSMiddleware,
     allow_origins=origins,
@@ -182,10 +106,43 @@ class CollectionNameForm(BaseModel):
     collection_name: Optional[str] = "test"
 
 
-class UrlForm(CollectionNameForm):
+class StoreWebForm(CollectionNameForm):
     url: str
 
 
+def store_data_in_vector_db(data, collection_name, overwrite: bool = False) -> bool:
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=app.state.CHUNK_SIZE, chunk_overlap=app.state.CHUNK_OVERLAP
+    )
+    docs = text_splitter.split_documents(data)
+
+    texts = [doc.page_content for doc in docs]
+    metadatas = [doc.metadata for doc in docs]
+
+    try:
+        if overwrite:
+            for collection in CHROMA_CLIENT.list_collections():
+                if collection_name == collection.name:
+                    print(f"deleting existing collection {collection_name}")
+                    CHROMA_CLIENT.delete_collection(name=collection_name)
+
+        collection = CHROMA_CLIENT.create_collection(
+            name=collection_name,
+            embedding_function=app.state.sentence_transformer_ef,
+        )
+
+        collection.add(
+            documents=texts, metadatas=metadatas, ids=[str(uuid.uuid1()) for _ in texts]
+        )
+        return True
+    except Exception as e:
+        print(e)
+        if e.__class__.__name__ == "UniqueConstraintError":
+            return True
+
+        return False
+
+
 @app.get("/")
 async def get_status():
     return {
@@ -193,121 +150,46 @@ async def get_status():
         "chunk_size": app.state.CHUNK_SIZE,
         "chunk_overlap": app.state.CHUNK_OVERLAP,
         "template": app.state.RAG_TEMPLATE,
-        "embedding_engine": app.state.RAG_EMBEDDING_ENGINE,
         "embedding_model": app.state.RAG_EMBEDDING_MODEL,
-        "reranking_model": app.state.RAG_RERANKING_MODEL,
     }
 
 
-@app.get("/embedding")
+@app.get("/embedding/model")
-async def get_embedding_config(user=Depends(get_admin_user)):
+async def get_embedding_model(user=Depends(get_admin_user)):
     return {
         "status": True,
-        "embedding_engine": app.state.RAG_EMBEDDING_ENGINE,
         "embedding_model": app.state.RAG_EMBEDDING_MODEL,
-        "openai_config": {
-            "url": app.state.OPENAI_API_BASE_URL,
-            "key": app.state.OPENAI_API_KEY,
-        },
     }
 
 
-@app.get("/reranking")
-async def get_reraanking_config(user=Depends(get_admin_user)):
-    return {"status": True, "reranking_model": app.state.RAG_RERANKING_MODEL}
-
-
-class OpenAIConfigForm(BaseModel):
-    url: str
-    key: str
-
-
 class EmbeddingModelUpdateForm(BaseModel):
-    openai_config: Optional[OpenAIConfigForm] = None
-    embedding_engine: str
     embedding_model: str
 
 
-@app.post("/embedding/update")
+@app.post("/embedding/model/update")
-async def update_embedding_config(
+async def update_embedding_model(
     form_data: EmbeddingModelUpdateForm, user=Depends(get_admin_user)
 ):
-    log.info(
+    app.state.RAG_EMBEDDING_MODEL = form_data.embedding_model
-        f"Updating embedding model: {app.state.RAG_EMBEDDING_MODEL} to {form_data.embedding_model}"
+    app.state.sentence_transformer_ef = (
+        embedding_functions.SentenceTransformerEmbeddingFunction(
+            model_name=app.state.RAG_EMBEDDING_MODEL,
+            device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
+        )
     )
-    try:
-        app.state.RAG_EMBEDDING_ENGINE = form_data.embedding_engine
-        app.state.RAG_EMBEDDING_MODEL = form_data.embedding_model
 
-        if app.state.RAG_EMBEDDING_ENGINE in ["ollama", "openai"]:
-            if form_data.openai_config != None:
-                app.state.OPENAI_API_BASE_URL = form_data.openai_config.url
-                app.state.OPENAI_API_KEY = form_data.openai_config.key
-
-        update_embedding_model(app.state.RAG_EMBEDDING_MODEL, True)
-
-        app.state.EMBEDDING_FUNCTION = get_embedding_function(
-            app.state.RAG_EMBEDDING_ENGINE,
-            app.state.RAG_EMBEDDING_MODEL,
-            app.state.sentence_transformer_ef,
-            app.state.OPENAI_API_KEY,
-            app.state.OPENAI_API_BASE_URL,
-        )
-
-        return {
-            "status": True,
-            "embedding_engine": app.state.RAG_EMBEDDING_ENGINE,
-            "embedding_model": app.state.RAG_EMBEDDING_MODEL,
-            "openai_config": {
-                "url": app.state.OPENAI_API_BASE_URL,
-                "key": app.state.OPENAI_API_KEY,
-            },
-        }
-    except Exception as e:
-        log.exception(f"Problem updating embedding model: {e}")
-        raise HTTPException(
-            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=ERROR_MESSAGES.DEFAULT(e),
-        )
-
-
-class RerankingModelUpdateForm(BaseModel):
-    reranking_model: str
-
-
-@app.post("/reranking/update")
-async def update_reranking_config(
-    form_data: RerankingModelUpdateForm, user=Depends(get_admin_user)
-):
-    log.info(
-        f"Updating reranking model: {app.state.RAG_RERANKING_MODEL} to {form_data.reranking_model}"
-    )
-    try:
-        app.state.RAG_RERANKING_MODEL = form_data.reranking_model
-
-        update_reranking_model(app.state.RAG_RERANKING_MODEL, True)
-
-        return {
-            "status": True,
-            "reranking_model": app.state.RAG_RERANKING_MODEL,
-        }
-    except Exception as e:
-        log.exception(f"Problem updating reranking model: {e}")
-        raise HTTPException(
-            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=ERROR_MESSAGES.DEFAULT(e),
-        )
-
-
-@app.get("/config")
-async def get_rag_config(user=Depends(get_admin_user)):
     return {
         "status": True,
-        "pdf_extract_images": app.state.PDF_EXTRACT_IMAGES,
+        "embedding_model": app.state.RAG_EMBEDDING_MODEL,
-        "chunk": {
+    }
-            "chunk_size": app.state.CHUNK_SIZE,
+
-            "chunk_overlap": app.state.CHUNK_OVERLAP,
+
-        },
+@app.get("/chunk")
+async def get_chunk_params(user=Depends(get_admin_user)):
+    return {
+        "status": True,
+        "chunk_size": app.state.CHUNK_SIZE,
+        "chunk_overlap": app.state.CHUNK_OVERLAP,
     }
 
 
@@ -316,24 +198,17 @@ class ChunkParamUpdateForm(BaseModel):
     chunk_overlap: int
 
 
-class ConfigUpdateForm(BaseModel):
+@app.post("/chunk/update")
-    pdf_extract_images: bool
+async def update_chunk_params(
-    chunk: ChunkParamUpdateForm
+    form_data: ChunkParamUpdateForm, user=Depends(get_admin_user)
-
+):
-
+    app.state.CHUNK_SIZE = form_data.chunk_size
-@app.post("/config/update")
+    app.state.CHUNK_OVERLAP = form_data.chunk_overlap
-async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_user)):
-    app.state.PDF_EXTRACT_IMAGES = form_data.pdf_extract_images
-    app.state.CHUNK_SIZE = form_data.chunk.chunk_size
-    app.state.CHUNK_OVERLAP = form_data.chunk.chunk_overlap
 
     return {
         "status": True,
-        "pdf_extract_images": app.state.PDF_EXTRACT_IMAGES,
+        "chunk_size": app.state.CHUNK_SIZE,
-        "chunk": {
+        "chunk_overlap": app.state.CHUNK_OVERLAP,
-            "chunk_size": app.state.CHUNK_SIZE,
-            "chunk_overlap": app.state.CHUNK_OVERLAP,
-        },
     }
 
 
@@ -351,16 +226,12 @@ async def get_query_settings(user=Depends(get_admin_user)):
         "status": True,
         "template": app.state.RAG_TEMPLATE,
         "k": app.state.TOP_K,
-        "r": app.state.RELEVANCE_THRESHOLD,
-        "hybrid": app.state.ENABLE_RAG_HYBRID_SEARCH,
     }
 
 
 class QuerySettingsForm(BaseModel):
     k: Optional[int] = None
-    r: Optional[float] = None
     template: Optional[str] = None
-    hybrid: Optional[bool] = None
 
 
 @app.post("/query/settings/update")
@@ -369,23 +240,13 @@ async def update_query_settings(
 ):
     app.state.RAG_TEMPLATE = form_data.template if form_data.template else RAG_TEMPLATE
     app.state.TOP_K = form_data.k if form_data.k else 4
-    app.state.RELEVANCE_THRESHOLD = form_data.r if form_data.r else 0.0
+    return {"status": True, "template": app.state.RAG_TEMPLATE}
-    app.state.ENABLE_RAG_HYBRID_SEARCH = form_data.hybrid if form_data.hybrid else False
-    return {
-        "status": True,
-        "template": app.state.RAG_TEMPLATE,
-        "k": app.state.TOP_K,
-        "r": app.state.RELEVANCE_THRESHOLD,
-        "hybrid": app.state.ENABLE_RAG_HYBRID_SEARCH,
-    }
 
 
 class QueryDocForm(BaseModel):
     collection_name: str
     query: str
     k: Optional[int] = None
-    r: Optional[float] = None
-    hybrid: Optional[bool] = None
 
 
 @app.post("/query/doc")
@@ -393,25 +254,16 @@ def query_doc_handler(
     form_data: QueryDocForm,
     user=Depends(get_current_user),
 ):
+
     try:
-        if app.state.ENABLE_RAG_HYBRID_SEARCH:
+        return query_doc(
-            return query_doc_with_hybrid_search(
+            collection_name=form_data.collection_name,
-                collection_name=form_data.collection_name,
+            query=form_data.query,
-                query=form_data.query,
+            k=form_data.k if form_data.k else app.state.TOP_K,
-                embedding_function=app.state.EMBEDDING_FUNCTION,
+            embedding_function=app.state.sentence_transformer_ef,
-                k=form_data.k if form_data.k else app.state.TOP_K,
+        )
-                reranking_function=app.state.sentence_transformer_rf,
-                r=form_data.r if form_data.r else app.state.RELEVANCE_THRESHOLD,
-            )
-        else:
-            return query_doc(
-                collection_name=form_data.collection_name,
-                query=form_data.query,
-                embedding_function=app.state.EMBEDDING_FUNCTION,
-                k=form_data.k if form_data.k else app.state.TOP_K,
-            )
     except Exception as e:
-        log.exception(e)
+        print(e)
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.DEFAULT(e),
@@ -422,8 +274,6 @@ class QueryCollectionsForm(BaseModel):
     collection_names: List[str]
     query: str
     k: Optional[int] = None
-    r: Optional[float] = None
-    hybrid: Optional[bool] = None
 
 
 @app.post("/query/collection")
@@ -431,61 +281,19 @@ def query_collection_handler(
     form_data: QueryCollectionsForm,
     user=Depends(get_current_user),
 ):
-    try:
+    return query_collection(
-        if app.state.ENABLE_RAG_HYBRID_SEARCH:
+        collection_names=form_data.collection_names,
-            return query_collection_with_hybrid_search(
+        query=form_data.query,
-                collection_names=form_data.collection_names,
+        k=form_data.k if form_data.k else app.state.TOP_K,
-                query=form_data.query,
+        embedding_function=app.state.sentence_transformer_ef,
-                embedding_function=app.state.EMBEDDING_FUNCTION,
+    )
-                k=form_data.k if form_data.k else app.state.TOP_K,
-                reranking_function=app.state.sentence_transformer_rf,
-                r=form_data.r if form_data.r else app.state.RELEVANCE_THRESHOLD,
-            )
-        else:
-            return query_collection(
-                collection_names=form_data.collection_names,
-                query=form_data.query,
-                embedding_function=app.state.EMBEDDING_FUNCTION,
-                k=form_data.k if form_data.k else app.state.TOP_K,
-            )
-
-    except Exception as e:
-        log.exception(e)
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=ERROR_MESSAGES.DEFAULT(e),
-        )
-
-
-@app.post("/youtube")
-def store_youtube_video(form_data: UrlForm, user=Depends(get_current_user)):
-    try:
-        loader = YoutubeLoader.from_youtube_url(form_data.url, add_video_info=False)
-        data = loader.load()
-
-        collection_name = form_data.collection_name
-        if collection_name == "":
-            collection_name = calculate_sha256_string(form_data.url)[:63]
-
-        store_data_in_vector_db(data, collection_name, overwrite=True)
-        return {
-            "status": True,
-            "collection_name": collection_name,
-            "filename": form_data.url,
-        }
-    except Exception as e:
-        log.exception(e)
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=ERROR_MESSAGES.DEFAULT(e),
-        )
 
 
 @app.post("/web")
-def store_web(form_data: UrlForm, user=Depends(get_current_user)):
+def store_web(form_data: StoreWebForm, user=Depends(get_current_user)):
     # "https://www.gutenberg.org/files/1727/1727-h/1727-h.htm"
     try:
-        loader = get_web_loader(form_data.url)
+        loader = WebBaseLoader(form_data.url)
         data = loader.load()
 
         collection_name = form_data.collection_name
@@ -499,117 +307,13 @@ def store_web(form_data: UrlForm, user=Depends(get_current_user)):
             "filename": form_data.url,
         }
     except Exception as e:
-        log.exception(e)
+        print(e)
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.DEFAULT(e),
         )
 
 
-def get_web_loader(url: str):
-    # Check if the URL is valid
-    if isinstance(validators.url(url), validators.ValidationError):
-        raise ValueError(ERROR_MESSAGES.INVALID_URL)
-    if not ENABLE_LOCAL_WEB_FETCH:
-        # Local web fetch is disabled, filter out any URLs that resolve to private IP addresses
-        parsed_url = urllib.parse.urlparse(url)
-        # Get IPv4 and IPv6 addresses
-        ipv4_addresses, ipv6_addresses = resolve_hostname(parsed_url.hostname)
-        # Check if any of the resolved addresses are private
-        # This is technically still vulnerable to DNS rebinding attacks, as we don't control WebBaseLoader
-        for ip in ipv4_addresses:
-            if validators.ipv4(ip, private=True):
-                raise ValueError(ERROR_MESSAGES.INVALID_URL)
-        for ip in ipv6_addresses:
-            if validators.ipv6(ip, private=True):
-                raise ValueError(ERROR_MESSAGES.INVALID_URL)
-    return WebBaseLoader(url)
-
-
-def resolve_hostname(hostname):
-    # Get address information
-    addr_info = socket.getaddrinfo(hostname, None)
-
-    # Extract IP addresses from address information
-    ipv4_addresses = [info[4][0] for info in addr_info if info[0] == socket.AF_INET]
-    ipv6_addresses = [info[4][0] for info in addr_info if info[0] == socket.AF_INET6]
-
-    return ipv4_addresses, ipv6_addresses
-
-
-def store_data_in_vector_db(data, collection_name, overwrite: bool = False) -> bool:
-
-    text_splitter = RecursiveCharacterTextSplitter(
-        chunk_size=app.state.CHUNK_SIZE,
-        chunk_overlap=app.state.CHUNK_OVERLAP,
-        add_start_index=True,
-    )
-
-    docs = text_splitter.split_documents(data)
-
-    if len(docs) > 0:
-        log.info(f"store_data_in_vector_db {docs}")
-        return store_docs_in_vector_db(docs, collection_name, overwrite), None
-    else:
-        raise ValueError(ERROR_MESSAGES.EMPTY_CONTENT)
-
-
-def store_text_in_vector_db(
-    text, metadata, collection_name, overwrite: bool = False
-) -> bool:
-    text_splitter = RecursiveCharacterTextSplitter(
-        chunk_size=app.state.CHUNK_SIZE,
-        chunk_overlap=app.state.CHUNK_OVERLAP,
-        add_start_index=True,
-    )
-    docs = text_splitter.create_documents([text], metadatas=[metadata])
-    return store_docs_in_vector_db(docs, collection_name, overwrite)
-
-
-def store_docs_in_vector_db(docs, collection_name, overwrite: bool = False) -> bool:
-    log.info(f"store_docs_in_vector_db {docs} {collection_name}")
-
-    texts = [doc.page_content for doc in docs]
-    metadatas = [doc.metadata for doc in docs]
-
-    try:
-        if overwrite:
-            for collection in CHROMA_CLIENT.list_collections():
-                if collection_name == collection.name:
-                    log.info(f"deleting existing collection {collection_name}")
-                    CHROMA_CLIENT.delete_collection(name=collection_name)
-
-        collection = CHROMA_CLIENT.create_collection(name=collection_name)
-
-        embedding_func = get_embedding_function(
-            app.state.RAG_EMBEDDING_ENGINE,
-            app.state.RAG_EMBEDDING_MODEL,
-            app.state.sentence_transformer_ef,
-            app.state.OPENAI_API_KEY,
-            app.state.OPENAI_API_BASE_URL,
-        )
-
-        embedding_texts = list(map(lambda x: x.replace("\n", " "), texts))
-        embeddings = embedding_func(embedding_texts)
-
-        for batch in create_batches(
-            api=CHROMA_CLIENT,
-            ids=[str(uuid.uuid1()) for _ in texts],
-            metadatas=metadatas,
-            embeddings=embeddings,
-            documents=texts,
-        ):
-            collection.add(*batch)
-
-        return True
-    except Exception as e:
-        log.exception(e)
-        if e.__class__.__name__ == "UniqueConstraintError":
-            return True
-
-        return False
-
-
 def get_loader(filename: str, file_content_type: str, file_path: str):
     file_ext = filename.split(".")[-1].lower()
     known_type = True
@@ -660,15 +364,13 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
     ]
 
     if file_ext == "pdf":
-        loader = PyPDFLoader(file_path, extract_images=app.state.PDF_EXTRACT_IMAGES)
+        loader = PyPDFLoader(file_path, extract_images=True)
     elif file_ext == "csv":
         loader = CSVLoader(file_path)
     elif file_ext == "rst":
         loader = UnstructuredRSTLoader(file_path, mode="elements")
     elif file_ext == "xml":
         loader = UnstructuredXMLLoader(file_path)
-    elif file_ext in ["htm", "html"]:
-        loader = BSHTMLLoader(file_path, open_encoding="unicode_escape")
     elif file_ext == "md":
         loader = UnstructuredMarkdownLoader(file_path)
     elif file_content_type == "application/epub+zip":
@@ -687,9 +389,9 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
     elif file_ext in known_source_ext or (
         file_content_type and file_content_type.find("text/") >= 0
     ):
-        loader = TextLoader(file_path, autodetect_encoding=True)
+        loader = TextLoader(file_path)
     else:
-        loader = TextLoader(file_path, autodetect_encoding=True)
+        loader = TextLoader(file_path)
         known_type = False
 
     return loader, known_type
@@ -703,13 +405,10 @@ def store_doc(
 ):
     # "https://www.gutenberg.org/files/1727/1727-h/1727-h.htm"
 
-    log.info(f"file.content_type: {file.content_type}")
+    print(file.content_type)
     try:
-        unsanitized_filename = file.filename
+        filename = file.filename
-        filename = os.path.basename(unsanitized_filename)
-
         file_path = f"{UPLOAD_DIR}/{filename}"
-
         contents = file.file.read()
         with open(file_path, "wb") as f:
             f.write(contents)
@@ -720,26 +419,24 @@ def store_doc(
             collection_name = calculate_sha256(f)[:63]
         f.close()
 
-        loader, known_type = get_loader(filename, file.content_type, file_path)
+        loader, known_type = get_loader(file.filename, file.content_type, file_path)
         data = loader.load()
+        result = store_data_in_vector_db(data, collection_name)
 
-        try:
+        if result:
-            result = store_data_in_vector_db(data, collection_name)
+            return {
-
+                "status": True,
-            if result:
+                "collection_name": collection_name,
-                return {
+                "filename": filename,
-                    "status": True,
+                "known_type": known_type,
-                    "collection_name": collection_name,
+            }
-                    "filename": filename,
+        else:
-                    "known_type": known_type,
-                }
-        except Exception as e:
             raise HTTPException(
                 status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                detail=e,
+                detail=ERROR_MESSAGES.DEFAULT(),
             )
     except Exception as e:
-        log.exception(e)
+        print(e)
         if "No pandoc was found" in str(e):
             raise HTTPException(
                 status_code=status.HTTP_400_BAD_REQUEST,
@@ -752,37 +449,6 @@ def store_doc(
             )
 
 
-class TextRAGForm(BaseModel):
-    name: str
-    content: str
-    collection_name: Optional[str] = None
-
-
-@app.post("/text")
-def store_text(
-    form_data: TextRAGForm,
-    user=Depends(get_current_user),
-):
-
-    collection_name = form_data.collection_name
-    if collection_name == None:
-        collection_name = calculate_sha256_string(form_data.content)
-
-    result = store_text_in_vector_db(
-        form_data.content,
-        metadata={"name": form_data.name, "created_by": user.id},
-        collection_name=collection_name,
-    )
-
-    if result:
-        return {"status": True, "collection_name": collection_name}
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=ERROR_MESSAGES.DEFAULT(),
-        )
-
-
 @app.get("/scan")
 def scan_docs_dir(user=Depends(get_admin_user)):
     for path in Path(DOCS_DIR).rglob("./**/*"):
@@ -801,45 +467,41 @@ def scan_docs_dir(user=Depends(get_admin_user)):
                 )
                 data = loader.load()
 
-                try:
+                result = store_data_in_vector_db(data, collection_name)
-                    result = store_data_in_vector_db(data, collection_name)
 
-                    if result:
+                if result:
-                        sanitized_filename = sanitize_filename(filename)
+                    sanitized_filename = sanitize_filename(filename)
-                        doc = Documents.get_doc_by_name(sanitized_filename)
+                    doc = Documents.get_doc_by_name(sanitized_filename)
 
-                        if doc == None:
+                    if doc == None:
-                            doc = Documents.insert_new_doc(
+                        doc = Documents.insert_new_doc(
-                                user.id,
+                            user.id,
-                                DocumentForm(
+                            DocumentForm(
-                                    **{
+                                **{
-                                        "name": sanitized_filename,
+                                    "name": sanitized_filename,
-                                        "title": filename,
+                                    "title": filename,
-                                        "collection_name": collection_name,
+                                    "collection_name": collection_name,
-                                        "filename": filename,
+                                    "filename": filename,
-                                        "content": (
+                                    "content": (
-                                            json.dumps(
+                                        json.dumps(
-                                                {
+                                            {
-                                                    "tags": list(
+                                                "tags": list(
-                                                        map(
+                                                    map(
-                                                            lambda name: {"name": name},
+                                                        lambda name: {"name": name},
-                                                            tags,
+                                                        tags,
-                                                        )
                                                     )
-                                                }
+                                                )
-                                            )
+                                            }
-                                            if len(tags)
+                                        )
-                                            else "{}"
+                                        if len(tags)
-                                        ),
+                                        else "{}"
-                                    }
+                                    ),
-                                ),
+                                }
-                            )
+                            ),
-                except Exception as e:
+                        )
-                    log.exception(e)
-                    pass
 
         except Exception as e:
-            log.exception(e)
+            print(e)
 
     return True
 
@@ -860,11 +522,11 @@ def reset(user=Depends(get_admin_user)) -> bool:
             elif os.path.isdir(file_path):
                 shutil.rmtree(file_path)
         except Exception as e:
-            log.error("Failed to delete %s. Reason: %s" % (file_path, e))
+            print("Failed to delete %s. Reason: %s" % (file_path, e))
 
     try:
         CHROMA_CLIENT.reset()
     except Exception as e:
-        log.exception(e)
+        print(e)
 
     return True

backend/apps/rag/utils.py

@@ -1,517 +1,97 @@
-import os
+import re
-import logging
-import requests
-
 from typing import List
 
-from apps.ollama.main import (
+from config import CHROMA_CLIENT
-    generate_ollama_embeddings,
-    GenerateEmbeddingsForm,
-)
-
-from huggingface_hub import snapshot_download
-
-from langchain_core.documents import Document
-from langchain_community.retrievers import BM25Retriever
-from langchain.retrievers import (
-    ContextualCompressionRetriever,
-    EnsembleRetriever,
-)
-
-from typing import Optional
-from config import SRC_LOG_LEVELS, CHROMA_CLIENT
 
 
-log = logging.getLogger(__name__)
+def query_doc(collection_name: str, query: str, k: int, embedding_function):
-log.setLevel(SRC_LOG_LEVELS["RAG"])
-
-
-def query_doc(
-    collection_name: str,
-    query: str,
-    embedding_function,
-    k: int,
-):
     try:
-        collection = CHROMA_CLIENT.get_collection(name=collection_name)
+        # if you use docker use the model from the environment variable
-        query_embeddings = embedding_function(query)
+        collection = CHROMA_CLIENT.get_collection(
-
+            name=collection_name,
+            embedding_function=embedding_function,
+        )
         result = collection.query(
-            query_embeddings=[query_embeddings],
+            query_texts=[query],
             n_results=k,
         )
-
-        log.info(f"query_doc:result {result}")
         return result
     except Exception as e:
         raise e
 
 
-def query_doc_with_hybrid_search(
+def merge_and_sort_query_results(query_results, k):
-    collection_name: str,
-    query: str,
-    embedding_function,
-    k: int,
-    reranking_function,
-    r: float,
-):
-    try:
-        collection = CHROMA_CLIENT.get_collection(name=collection_name)
-        documents = collection.get()  # get all documents
-
-        bm25_retriever = BM25Retriever.from_texts(
-            texts=documents.get("documents"),
-            metadatas=documents.get("metadatas"),
-        )
-        bm25_retriever.k = k
-
-        chroma_retriever = ChromaRetriever(
-            collection=collection,
-            embedding_function=embedding_function,
-            top_n=k,
-        )
-
-        ensemble_retriever = EnsembleRetriever(
-            retrievers=[bm25_retriever, chroma_retriever], weights=[0.5, 0.5]
-        )
-
-        compressor = RerankCompressor(
-            embedding_function=embedding_function,
-            top_n=k,
-            reranking_function=reranking_function,
-            r_score=r,
-        )
-
-        compression_retriever = ContextualCompressionRetriever(
-            base_compressor=compressor, base_retriever=ensemble_retriever
-        )
-
-        result = compression_retriever.invoke(query)
-        result = {
-            "distances": [[d.metadata.get("score") for d in result]],
-            "documents": [[d.page_content for d in result]],
-            "metadatas": [[d.metadata for d in result]],
-        }
-
-        log.info(f"query_doc_with_hybrid_search:result {result}")
-        return result
-    except Exception as e:
-        raise e
-
-
-def merge_and_sort_query_results(query_results, k, reverse=False):
     # Initialize lists to store combined data
+    combined_ids = []
     combined_distances = []
-    combined_documents = []
     combined_metadatas = []
+    combined_documents = []
 
+    # Combine data from each dictionary
     for data in query_results:
+        combined_ids.extend(data["ids"][0])
         combined_distances.extend(data["distances"][0])
-        combined_documents.extend(data["documents"][0])
         combined_metadatas.extend(data["metadatas"][0])
+        combined_documents.extend(data["documents"][0])
 
-    # Create a list of tuples (distance, document, metadata)
+    # Create a list of tuples (distance, id, metadata, document)
-    combined = list(zip(combined_distances, combined_documents, combined_metadatas))
+    combined = list(
+        zip(combined_distances, combined_ids, combined_metadatas, combined_documents)
+    )
 
     # Sort the list based on distances
-    combined.sort(key=lambda x: x[0], reverse=reverse)
+    combined.sort(key=lambda x: x[0])
 
-    # We don't have anything :-(
+    # Unzip the sorted list
-    if not combined:
+    sorted_distances, sorted_ids, sorted_metadatas, sorted_documents = zip(*combined)
-        sorted_distances = []
-        sorted_documents = []
-        sorted_metadatas = []
-    else:
-        # Unzip the sorted list
-        sorted_distances, sorted_documents, sorted_metadatas = zip(*combined)
 
-        # Slicing the lists to include only k elements
+    # Slicing the lists to include only k elements
-        sorted_distances = list(sorted_distances)[:k]
+    sorted_distances = list(sorted_distances)[:k]
-        sorted_documents = list(sorted_documents)[:k]
+    sorted_ids = list(sorted_ids)[:k]
-        sorted_metadatas = list(sorted_metadatas)[:k]
+    sorted_metadatas = list(sorted_metadatas)[:k]
+    sorted_documents = list(sorted_documents)[:k]
 
     # Create the output dictionary
-    result = {
+    merged_query_results = {
+        "ids": [sorted_ids],
         "distances": [sorted_distances],
-        "documents": [sorted_documents],
         "metadatas": [sorted_metadatas],
+        "documents": [sorted_documents],
+        "embeddings": None,
+        "uris": None,
+        "data": None,
     }
 
-    return result
+    return merged_query_results
 
 
 def query_collection(
-    collection_names: List[str],
+    collection_names: List[str], query: str, k: int, embedding_function
-    query: str,
-    embedding_function,
-    k: int,
 ):
+
     results = []
+
     for collection_name in collection_names:
         try:
-            result = query_doc(
+            # if you use docker use the model from the environment variable
-                collection_name=collection_name,
+            collection = CHROMA_CLIENT.get_collection(
-                query=query,
+                name=collection_name,
-                k=k,
                 embedding_function=embedding_function,
             )
+
+            result = collection.query(
+                query_texts=[query],
+                n_results=k,
+            )
             results.append(result)
         except:
             pass
-    return merge_and_sort_query_results(results, k=k)
 
-
+    return merge_and_sort_query_results(results, k)
-def query_collection_with_hybrid_search(
-    collection_names: List[str],
-    query: str,
-    embedding_function,
-    k: int,
-    reranking_function,
-    r: float,
-):
-    results = []
-    for collection_name in collection_names:
-        try:
-            result = query_doc_with_hybrid_search(
-                collection_name=collection_name,
-                query=query,
-                embedding_function=embedding_function,
-                k=k,
-                reranking_function=reranking_function,
-                r=r,
-            )
-            results.append(result)
-        except:
-            pass
-    return merge_and_sort_query_results(results, k=k, reverse=True)
 
 
 def rag_template(template: str, context: str, query: str):
-    template = template.replace("[context]", context)
+    template = re.sub(r"\[context\]", context, template)
-    template = template.replace("[query]", query)
+    template = re.sub(r"\[query\]", query, template)
+
     return template
-
-
-def get_embedding_function(
-    embedding_engine,
-    embedding_model,
-    embedding_function,
-    openai_key,
-    openai_url,
-):
-    if embedding_engine == "":
-        return lambda query: embedding_function.encode(query).tolist()
-    elif embedding_engine in ["ollama", "openai"]:
-        if embedding_engine == "ollama":
-            func = lambda query: generate_ollama_embeddings(
-                GenerateEmbeddingsForm(
-                    **{
-                        "model": embedding_model,
-                        "prompt": query,
-                    }
-                )
-            )
-        elif embedding_engine == "openai":
-            func = lambda query: generate_openai_embeddings(
-                model=embedding_model,
-                text=query,
-                key=openai_key,
-                url=openai_url,
-            )
-
-        def generate_multiple(query, f):
-            if isinstance(query, list):
-                return [f(q) for q in query]
-            else:
-                return f(query)
-
-        return lambda query: generate_multiple(query, func)
-
-
-def rag_messages(
-    docs,
-    messages,
-    template,
-    embedding_function,
-    k,
-    reranking_function,
-    r,
-    hybrid_search,
-):
-    log.debug(f"docs: {docs} {messages} {embedding_function} {reranking_function}")
-
-    last_user_message_idx = None
-    for i in range(len(messages) - 1, -1, -1):
-        if messages[i]["role"] == "user":
-            last_user_message_idx = i
-            break
-
-    user_message = messages[last_user_message_idx]
-
-    if isinstance(user_message["content"], list):
-        # Handle list content input
-        content_type = "list"
-        query = ""
-        for content_item in user_message["content"]:
-            if content_item["type"] == "text":
-                query = content_item["text"]
-                break
-    elif isinstance(user_message["content"], str):
-        # Handle text content input
-        content_type = "text"
-        query = user_message["content"]
-    else:
-        # Fallback in case the input does not match expected types
-        content_type = None
-        query = ""
-
-    extracted_collections = []
-    relevant_contexts = []
-
-    for doc in docs:
-        context = None
-
-        collection = doc.get("collection_name")
-        if collection:
-            collection = [collection]
-        else:
-            collection = doc.get("collection_names", [])
-
-        collection = set(collection).difference(extracted_collections)
-        if not collection:
-            log.debug(f"skipping {doc} as it has already been extracted")
-            continue
-
-        try:
-            if doc["type"] == "text":
-                context = doc["content"]
-            else:
-                if hybrid_search:
-                    context = query_collection_with_hybrid_search(
-                        collection_names=(
-                            doc["collection_names"]
-                            if doc["type"] == "collection"
-                            else [doc["collection_name"]]
-                        ),
-                        query=query,
-                        embedding_function=embedding_function,
-                        k=k,
-                        reranking_function=reranking_function,
-                        r=r,
-                    )
-                else:
-                    context = query_collection(
-                        collection_names=(
-                            doc["collection_names"]
-                            if doc["type"] == "collection"
-                            else [doc["collection_name"]]
-                        ),
-                        query=query,
-                        embedding_function=embedding_function,
-                        k=k,
-                    )
-        except Exception as e:
-            log.exception(e)
-            context = None
-
-        if context:
-            relevant_contexts.append(context)
-
-        extracted_collections.extend(collection)
-
-    context_string = ""
-    for context in relevant_contexts:
-        try:
-            if "documents" in context:
-                items = [item for item in context["documents"][0] if item is not None]
-                context_string += "\n\n".join(items)
-        except Exception as e:
-            log.exception(e)
-    context_string = context_string.strip()
-
-    ra_content = rag_template(
-        template=template,
-        context=context_string,
-        query=query,
-    )
-
-    log.debug(f"ra_content: {ra_content}")
-
-    if content_type == "list":
-        new_content = []
-        for content_item in user_message["content"]:
-            if content_item["type"] == "text":
-                # Update the text item's content with ra_content
-                new_content.append({"type": "text", "text": ra_content})
-            else:
-                # Keep other types of content as they are
-                new_content.append(content_item)
-        new_user_message = {**user_message, "content": new_content}
-    else:
-        new_user_message = {
-            **user_message,
-            "content": ra_content,
-        }
-
-    messages[last_user_message_idx] = new_user_message
-
-    return messages
-
-
-def get_model_path(model: str, update_model: bool = False):
-    # Construct huggingface_hub kwargs with local_files_only to return the snapshot path
-    cache_dir = os.getenv("SENTENCE_TRANSFORMERS_HOME")
-
-    local_files_only = not update_model
-
-    snapshot_kwargs = {
-        "cache_dir": cache_dir,
-        "local_files_only": local_files_only,
-    }
-
-    log.debug(f"model: {model}")
-    log.debug(f"snapshot_kwargs: {snapshot_kwargs}")
-
-    # Inspiration from upstream sentence_transformers
-    if (
-        os.path.exists(model)
-        or ("\\" in model or model.count("/") > 1)
-        and local_files_only
-    ):
-        # If fully qualified path exists, return input, else set repo_id
-        return model
-    elif "/" not in model:
-        # Set valid repo_id for model short-name
-        model = "sentence-transformers" + "/" + model
-
-    snapshot_kwargs["repo_id"] = model
-
-    # Attempt to query the huggingface_hub library to determine the local path and/or to update
-    try:
-        model_repo_path = snapshot_download(**snapshot_kwargs)
-        log.debug(f"model_repo_path: {model_repo_path}")
-        return model_repo_path
-    except Exception as e:
-        log.exception(f"Cannot determine model snapshot path: {e}")
-        return model
-
-
-def generate_openai_embeddings(
-    model: str, text: str, key: str, url: str = "https://api.openai.com/v1"
-):
-    try:
-        r = requests.post(
-            f"{url}/embeddings",
-            headers={
-                "Content-Type": "application/json",
-                "Authorization": f"Bearer {key}",
-            },
-            json={"input": text, "model": model},
-        )
-        r.raise_for_status()
-        data = r.json()
-        if "data" in data:
-            return data["data"][0]["embedding"]
-        else:
-            raise "Something went wrong :/"
-    except Exception as e:
-        print(e)
-        return None
-
-
-from typing import Any
-
-from langchain_core.retrievers import BaseRetriever
-from langchain_core.callbacks import CallbackManagerForRetrieverRun
-
-
-class ChromaRetriever(BaseRetriever):
-    collection: Any
-    embedding_function: Any
-    top_n: int
-
-    def _get_relevant_documents(
-        self,
-        query: str,
-        *,
-        run_manager: CallbackManagerForRetrieverRun,
-    ) -> List[Document]:
-        query_embeddings = self.embedding_function(query)
-
-        results = self.collection.query(
-            query_embeddings=[query_embeddings],
-            n_results=self.top_n,
-        )
-
-        ids = results["ids"][0]
-        metadatas = results["metadatas"][0]
-        documents = results["documents"][0]
-
-        results = []
-        for idx in range(len(ids)):
-            results.append(
-                Document(
-                    metadata=metadatas[idx],
-                    page_content=documents[idx],
-                )
-            )
-        return results
-
-
-import operator
-
-from typing import Optional, Sequence
-
-from langchain_core.documents import BaseDocumentCompressor, Document
-from langchain_core.callbacks import Callbacks
-from langchain_core.pydantic_v1 import Extra
-
-from sentence_transformers import util
-
-
-class RerankCompressor(BaseDocumentCompressor):
-    embedding_function: Any
-    top_n: int
-    reranking_function: Any
-    r_score: float
-
-    class Config:
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
-
-    def compress_documents(
-        self,
-        documents: Sequence[Document],
-        query: str,
-        callbacks: Optional[Callbacks] = None,
-    ) -> Sequence[Document]:
-        reranking = self.reranking_function is not None
-
-        if reranking:
-            scores = self.reranking_function.predict(
-                [(query, doc.page_content) for doc in documents]
-            )
-        else:
-            query_embedding = self.embedding_function(query)
-            document_embedding = self.embedding_function(
-                [doc.page_content for doc in documents]
-            )
-            scores = util.cos_sim(query_embedding, document_embedding)[0]
-
-        docs_with_scores = list(zip(documents, scores.tolist()))
-        if self.r_score:
-            docs_with_scores = [
-                (d, s) for d, s in docs_with_scores if s >= self.r_score
-            ]
-
-        result = sorted(docs_with_scores, key=operator.itemgetter(1), reverse=True)
-        final_results = []
-        for doc, doc_score in result[: self.top_n]:
-            metadata = doc.metadata
-            metadata["score"] = doc_score
-            doc = Document(
-                page_content=doc.page_content,
-                metadata=metadata,
-            )
-            final_results.append(doc)
-        return final_results

backend/apps/web/internal/db.py

@@ -1,23 +1,16 @@
 from peewee import *
-from peewee_migrate import Router
+from config import DATA_DIR
-from playhouse.db_url import connect
-from config import SRC_LOG_LEVELS, DATA_DIR, DATABASE_URL
 import os
-import logging
 
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["DB"])
 
 # Check if the file exists
 if os.path.exists(f"{DATA_DIR}/ollama.db"):
     # Rename the file
     os.rename(f"{DATA_DIR}/ollama.db", f"{DATA_DIR}/webui.db")
-    log.info("Database migrated from Ollama-WebUI successfully.")
+    print("File renamed successfully.")
 else:
     pass
 
-DB = connect(DATABASE_URL)
+
-log.info(f"Connected to a {DB.__class__.__name__} database.")
+DB = SqliteDatabase(f"{DATA_DIR}/webui.db")
-router = Router(DB, migrate_dir="apps/web/internal/migrations", logger=log)
+DB.connect()
-router.run()
-DB.connect(reuse_if_open=True)

backend/apps/web/internal/migrations/001_initial_schema.py

@@ -1,254 +0,0 @@
-"""Peewee migrations -- 001_initial_schema.py.
-
-Some examples (model - class or model name)::
-
-    > Model = migrator.orm['table_name']            # Return model in current state by name
-    > Model = migrator.ModelClass                   # Return model in current state by name
-
-    > migrator.sql(sql)                             # Run custom SQL
-    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
-    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
-    > migrator.remove_model(model, cascade=True)    # Remove a model
-    > migrator.add_fields(model, **fields)          # Add fields to a model
-    > migrator.change_fields(model, **fields)       # Change fields
-    > migrator.remove_fields(model, *field_names, cascade=True)
-    > migrator.rename_field(model, old_field_name, new_field_name)
-    > migrator.rename_table(model, new_table_name)
-    > migrator.add_index(model, *col_names, unique=False)
-    > migrator.add_not_null(model, *field_names)
-    > migrator.add_default(model, field_name, default)
-    > migrator.add_constraint(model, name, sql)
-    > migrator.drop_index(model, *col_names)
-    > migrator.drop_not_null(model, *field_names)
-    > migrator.drop_constraints(model, *constraints)
-
-"""
-
-from contextlib import suppress
-
-import peewee as pw
-from peewee_migrate import Migrator
-
-
-with suppress(ImportError):
-    import playhouse.postgres_ext as pw_pext
-
-
-def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your migrations here."""
-
-    # We perform different migrations for SQLite and other databases
-    # This is because SQLite is very loose with enforcing its schema, and trying to migrate other databases like SQLite
-    # will require per-database SQL queries.
-    # Instead, we assume that because external DB support was added at a later date, it is safe to assume a newer base
-    # schema instead of trying to migrate from an older schema.
-    if isinstance(database, pw.SqliteDatabase):
-        migrate_sqlite(migrator, database, fake=fake)
-    else:
-        migrate_external(migrator, database, fake=fake)
-
-
-def migrate_sqlite(migrator: Migrator, database: pw.Database, *, fake=False):
-    @migrator.create_model
-    class Auth(pw.Model):
-        id = pw.CharField(max_length=255, unique=True)
-        email = pw.CharField(max_length=255)
-        password = pw.CharField(max_length=255)
-        active = pw.BooleanField()
-
-        class Meta:
-            table_name = "auth"
-
-    @migrator.create_model
-    class Chat(pw.Model):
-        id = pw.CharField(max_length=255, unique=True)
-        user_id = pw.CharField(max_length=255)
-        title = pw.CharField()
-        chat = pw.TextField()
-        timestamp = pw.BigIntegerField()
-
-        class Meta:
-            table_name = "chat"
-
-    @migrator.create_model
-    class ChatIdTag(pw.Model):
-        id = pw.CharField(max_length=255, unique=True)
-        tag_name = pw.CharField(max_length=255)
-        chat_id = pw.CharField(max_length=255)
-        user_id = pw.CharField(max_length=255)
-        timestamp = pw.BigIntegerField()
-
-        class Meta:
-            table_name = "chatidtag"
-
-    @migrator.create_model
-    class Document(pw.Model):
-        id = pw.AutoField()
-        collection_name = pw.CharField(max_length=255, unique=True)
-        name = pw.CharField(max_length=255, unique=True)
-        title = pw.CharField()
-        filename = pw.CharField()
-        content = pw.TextField(null=True)
-        user_id = pw.CharField(max_length=255)
-        timestamp = pw.BigIntegerField()
-
-        class Meta:
-            table_name = "document"
-
-    @migrator.create_model
-    class Modelfile(pw.Model):
-        id = pw.AutoField()
-        tag_name = pw.CharField(max_length=255, unique=True)
-        user_id = pw.CharField(max_length=255)
-        modelfile = pw.TextField()
-        timestamp = pw.BigIntegerField()
-
-        class Meta:
-            table_name = "modelfile"
-
-    @migrator.create_model
-    class Prompt(pw.Model):
-        id = pw.AutoField()
-        command = pw.CharField(max_length=255, unique=True)
-        user_id = pw.CharField(max_length=255)
-        title = pw.CharField()
-        content = pw.TextField()
-        timestamp = pw.BigIntegerField()
-
-        class Meta:
-            table_name = "prompt"
-
-    @migrator.create_model
-    class Tag(pw.Model):
-        id = pw.CharField(max_length=255, unique=True)
-        name = pw.CharField(max_length=255)
-        user_id = pw.CharField(max_length=255)
-        data = pw.TextField(null=True)
-
-        class Meta:
-            table_name = "tag"
-
-    @migrator.create_model
-    class User(pw.Model):
-        id = pw.CharField(max_length=255, unique=True)
-        name = pw.CharField(max_length=255)
-        email = pw.CharField(max_length=255)
-        role = pw.CharField(max_length=255)
-        profile_image_url = pw.CharField(max_length=255)
-        timestamp = pw.BigIntegerField()
-
-        class Meta:
-            table_name = "user"
-
-
-def migrate_external(migrator: Migrator, database: pw.Database, *, fake=False):
-    @migrator.create_model
-    class Auth(pw.Model):
-        id = pw.CharField(max_length=255, unique=True)
-        email = pw.CharField(max_length=255)
-        password = pw.TextField()
-        active = pw.BooleanField()
-
-        class Meta:
-            table_name = "auth"
-
-    @migrator.create_model
-    class Chat(pw.Model):
-        id = pw.CharField(max_length=255, unique=True)
-        user_id = pw.CharField(max_length=255)
-        title = pw.TextField()
-        chat = pw.TextField()
-        timestamp = pw.BigIntegerField()
-
-        class Meta:
-            table_name = "chat"
-
-    @migrator.create_model
-    class ChatIdTag(pw.Model):
-        id = pw.CharField(max_length=255, unique=True)
-        tag_name = pw.CharField(max_length=255)
-        chat_id = pw.CharField(max_length=255)
-        user_id = pw.CharField(max_length=255)
-        timestamp = pw.BigIntegerField()
-
-        class Meta:
-            table_name = "chatidtag"
-
-    @migrator.create_model
-    class Document(pw.Model):
-        id = pw.AutoField()
-        collection_name = pw.CharField(max_length=255, unique=True)
-        name = pw.CharField(max_length=255, unique=True)
-        title = pw.TextField()
-        filename = pw.TextField()
-        content = pw.TextField(null=True)
-        user_id = pw.CharField(max_length=255)
-        timestamp = pw.BigIntegerField()
-
-        class Meta:
-            table_name = "document"
-
-    @migrator.create_model
-    class Modelfile(pw.Model):
-        id = pw.AutoField()
-        tag_name = pw.CharField(max_length=255, unique=True)
-        user_id = pw.CharField(max_length=255)
-        modelfile = pw.TextField()
-        timestamp = pw.BigIntegerField()
-
-        class Meta:
-            table_name = "modelfile"
-
-    @migrator.create_model
-    class Prompt(pw.Model):
-        id = pw.AutoField()
-        command = pw.CharField(max_length=255, unique=True)
-        user_id = pw.CharField(max_length=255)
-        title = pw.TextField()
-        content = pw.TextField()
-        timestamp = pw.BigIntegerField()
-
-        class Meta:
-            table_name = "prompt"
-
-    @migrator.create_model
-    class Tag(pw.Model):
-        id = pw.CharField(max_length=255, unique=True)
-        name = pw.CharField(max_length=255)
-        user_id = pw.CharField(max_length=255)
-        data = pw.TextField(null=True)
-
-        class Meta:
-            table_name = "tag"
-
-    @migrator.create_model
-    class User(pw.Model):
-        id = pw.CharField(max_length=255, unique=True)
-        name = pw.CharField(max_length=255)
-        email = pw.CharField(max_length=255)
-        role = pw.CharField(max_length=255)
-        profile_image_url = pw.TextField()
-        timestamp = pw.BigIntegerField()
-
-        class Meta:
-            table_name = "user"
-
-
-def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your rollback migrations here."""
-
-    migrator.remove_model("user")
-
-    migrator.remove_model("tag")
-
-    migrator.remove_model("prompt")
-
-    migrator.remove_model("modelfile")
-
-    migrator.remove_model("document")
-
-    migrator.remove_model("chatidtag")
-
-    migrator.remove_model("chat")
-
-    migrator.remove_model("auth")

backend/apps/web/internal/migrations/002_add_local_sharing.py

@@ -1,48 +0,0 @@
-"""Peewee migrations -- 002_add_local_sharing.py.
-
-Some examples (model - class or model name)::
-
-    > Model = migrator.orm['table_name']            # Return model in current state by name
-    > Model = migrator.ModelClass                   # Return model in current state by name
-
-    > migrator.sql(sql)                             # Run custom SQL
-    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
-    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
-    > migrator.remove_model(model, cascade=True)    # Remove a model
-    > migrator.add_fields(model, **fields)          # Add fields to a model
-    > migrator.change_fields(model, **fields)       # Change fields
-    > migrator.remove_fields(model, *field_names, cascade=True)
-    > migrator.rename_field(model, old_field_name, new_field_name)
-    > migrator.rename_table(model, new_table_name)
-    > migrator.add_index(model, *col_names, unique=False)
-    > migrator.add_not_null(model, *field_names)
-    > migrator.add_default(model, field_name, default)
-    > migrator.add_constraint(model, name, sql)
-    > migrator.drop_index(model, *col_names)
-    > migrator.drop_not_null(model, *field_names)
-    > migrator.drop_constraints(model, *constraints)
-
-"""
-
-from contextlib import suppress
-
-import peewee as pw
-from peewee_migrate import Migrator
-
-
-with suppress(ImportError):
-    import playhouse.postgres_ext as pw_pext
-
-
-def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your migrations here."""
-
-    migrator.add_fields(
-        "chat", share_id=pw.CharField(max_length=255, null=True, unique=True)
-    )
-
-
-def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your rollback migrations here."""
-
-    migrator.remove_fields("chat", "share_id")

backend/apps/web/internal/migrations/003_add_auth_api_key.py

@@ -1,48 +0,0 @@
-"""Peewee migrations -- 002_add_local_sharing.py.
-
-Some examples (model - class or model name)::
-
-    > Model = migrator.orm['table_name']            # Return model in current state by name
-    > Model = migrator.ModelClass                   # Return model in current state by name
-
-    > migrator.sql(sql)                             # Run custom SQL
-    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
-    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
-    > migrator.remove_model(model, cascade=True)    # Remove a model
-    > migrator.add_fields(model, **fields)          # Add fields to a model
-    > migrator.change_fields(model, **fields)       # Change fields
-    > migrator.remove_fields(model, *field_names, cascade=True)
-    > migrator.rename_field(model, old_field_name, new_field_name)
-    > migrator.rename_table(model, new_table_name)
-    > migrator.add_index(model, *col_names, unique=False)
-    > migrator.add_not_null(model, *field_names)
-    > migrator.add_default(model, field_name, default)
-    > migrator.add_constraint(model, name, sql)
-    > migrator.drop_index(model, *col_names)
-    > migrator.drop_not_null(model, *field_names)
-    > migrator.drop_constraints(model, *constraints)
-
-"""
-
-from contextlib import suppress
-
-import peewee as pw
-from peewee_migrate import Migrator
-
-
-with suppress(ImportError):
-    import playhouse.postgres_ext as pw_pext
-
-
-def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your migrations here."""
-
-    migrator.add_fields(
-        "user", api_key=pw.CharField(max_length=255, null=True, unique=True)
-    )
-
-
-def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your rollback migrations here."""
-
-    migrator.remove_fields("user", "api_key")

backend/apps/web/internal/migrations/004_add_archived.py

@@ -1,46 +0,0 @@
-"""Peewee migrations -- 002_add_local_sharing.py.
-
-Some examples (model - class or model name)::
-
-    > Model = migrator.orm['table_name']            # Return model in current state by name
-    > Model = migrator.ModelClass                   # Return model in current state by name
-
-    > migrator.sql(sql)                             # Run custom SQL
-    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
-    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
-    > migrator.remove_model(model, cascade=True)    # Remove a model
-    > migrator.add_fields(model, **fields)          # Add fields to a model
-    > migrator.change_fields(model, **fields)       # Change fields
-    > migrator.remove_fields(model, *field_names, cascade=True)
-    > migrator.rename_field(model, old_field_name, new_field_name)
-    > migrator.rename_table(model, new_table_name)
-    > migrator.add_index(model, *col_names, unique=False)
-    > migrator.add_not_null(model, *field_names)
-    > migrator.add_default(model, field_name, default)
-    > migrator.add_constraint(model, name, sql)
-    > migrator.drop_index(model, *col_names)
-    > migrator.drop_not_null(model, *field_names)
-    > migrator.drop_constraints(model, *constraints)
-
-"""
-
-from contextlib import suppress
-
-import peewee as pw
-from peewee_migrate import Migrator
-
-
-with suppress(ImportError):
-    import playhouse.postgres_ext as pw_pext
-
-
-def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your migrations here."""
-
-    migrator.add_fields("chat", archived=pw.BooleanField(default=False))
-
-
-def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your rollback migrations here."""
-
-    migrator.remove_fields("chat", "archived")

backend/apps/web/internal/migrations/005_add_updated_at.py

@@ -1,130 +0,0 @@
-"""Peewee migrations -- 002_add_local_sharing.py.
-
-Some examples (model - class or model name)::
-
-    > Model = migrator.orm['table_name']            # Return model in current state by name
-    > Model = migrator.ModelClass                   # Return model in current state by name
-
-    > migrator.sql(sql)                             # Run custom SQL
-    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
-    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
-    > migrator.remove_model(model, cascade=True)    # Remove a model
-    > migrator.add_fields(model, **fields)          # Add fields to a model
-    > migrator.change_fields(model, **fields)       # Change fields
-    > migrator.remove_fields(model, *field_names, cascade=True)
-    > migrator.rename_field(model, old_field_name, new_field_name)
-    > migrator.rename_table(model, new_table_name)
-    > migrator.add_index(model, *col_names, unique=False)
-    > migrator.add_not_null(model, *field_names)
-    > migrator.add_default(model, field_name, default)
-    > migrator.add_constraint(model, name, sql)
-    > migrator.drop_index(model, *col_names)
-    > migrator.drop_not_null(model, *field_names)
-    > migrator.drop_constraints(model, *constraints)
-
-"""
-
-from contextlib import suppress
-
-import peewee as pw
-from peewee_migrate import Migrator
-
-
-with suppress(ImportError):
-    import playhouse.postgres_ext as pw_pext
-
-
-def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your migrations here."""
-
-    if isinstance(database, pw.SqliteDatabase):
-        migrate_sqlite(migrator, database, fake=fake)
-    else:
-        migrate_external(migrator, database, fake=fake)
-
-
-def migrate_sqlite(migrator: Migrator, database: pw.Database, *, fake=False):
-    # Adding fields created_at and updated_at to the 'chat' table
-    migrator.add_fields(
-        "chat",
-        created_at=pw.DateTimeField(null=True),  # Allow null for transition
-        updated_at=pw.DateTimeField(null=True),  # Allow null for transition
-    )
-
-    # Populate the new fields from an existing 'timestamp' field
-    migrator.sql(
-        "UPDATE chat SET created_at = timestamp, updated_at = timestamp WHERE timestamp IS NOT NULL"
-    )
-
-    # Now that the data has been copied, remove the original 'timestamp' field
-    migrator.remove_fields("chat", "timestamp")
-
-    # Update the fields to be not null now that they are populated
-    migrator.change_fields(
-        "chat",
-        created_at=pw.DateTimeField(null=False),
-        updated_at=pw.DateTimeField(null=False),
-    )
-
-
-def migrate_external(migrator: Migrator, database: pw.Database, *, fake=False):
-    # Adding fields created_at and updated_at to the 'chat' table
-    migrator.add_fields(
-        "chat",
-        created_at=pw.BigIntegerField(null=True),  # Allow null for transition
-        updated_at=pw.BigIntegerField(null=True),  # Allow null for transition
-    )
-
-    # Populate the new fields from an existing 'timestamp' field
-    migrator.sql(
-        "UPDATE chat SET created_at = timestamp, updated_at = timestamp WHERE timestamp IS NOT NULL"
-    )
-
-    # Now that the data has been copied, remove the original 'timestamp' field
-    migrator.remove_fields("chat", "timestamp")
-
-    # Update the fields to be not null now that they are populated
-    migrator.change_fields(
-        "chat",
-        created_at=pw.BigIntegerField(null=False),
-        updated_at=pw.BigIntegerField(null=False),
-    )
-
-
-def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your rollback migrations here."""
-
-    if isinstance(database, pw.SqliteDatabase):
-        rollback_sqlite(migrator, database, fake=fake)
-    else:
-        rollback_external(migrator, database, fake=fake)
-
-
-def rollback_sqlite(migrator: Migrator, database: pw.Database, *, fake=False):
-    # Recreate the timestamp field initially allowing null values for safe transition
-    migrator.add_fields("chat", timestamp=pw.DateTimeField(null=True))
-
-    # Copy the earliest created_at date back into the new timestamp field
-    # This assumes created_at was originally a copy of timestamp
-    migrator.sql("UPDATE chat SET timestamp = created_at")
-
-    # Remove the created_at and updated_at fields
-    migrator.remove_fields("chat", "created_at", "updated_at")
-
-    # Finally, alter the timestamp field to not allow nulls if that was the original setting
-    migrator.change_fields("chat", timestamp=pw.DateTimeField(null=False))
-
-
-def rollback_external(migrator: Migrator, database: pw.Database, *, fake=False):
-    # Recreate the timestamp field initially allowing null values for safe transition
-    migrator.add_fields("chat", timestamp=pw.BigIntegerField(null=True))
-
-    # Copy the earliest created_at date back into the new timestamp field
-    # This assumes created_at was originally a copy of timestamp
-    migrator.sql("UPDATE chat SET timestamp = created_at")
-
-    # Remove the created_at and updated_at fields
-    migrator.remove_fields("chat", "created_at", "updated_at")
-
-    # Finally, alter the timestamp field to not allow nulls if that was the original setting
-    migrator.change_fields("chat", timestamp=pw.BigIntegerField(null=False))

backend/apps/web/internal/migrations/006_migrate_timestamps_and_charfields.py

@@ -1,130 +0,0 @@
-"""Peewee migrations -- 006_migrate_timestamps_and_charfields.py.
-
-Some examples (model - class or model name)::
-
-    > Model = migrator.orm['table_name']            # Return model in current state by name
-    > Model = migrator.ModelClass                   # Return model in current state by name
-
-    > migrator.sql(sql)                             # Run custom SQL
-    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
-    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
-    > migrator.remove_model(model, cascade=True)    # Remove a model
-    > migrator.add_fields(model, **fields)          # Add fields to a model
-    > migrator.change_fields(model, **fields)       # Change fields
-    > migrator.remove_fields(model, *field_names, cascade=True)
-    > migrator.rename_field(model, old_field_name, new_field_name)
-    > migrator.rename_table(model, new_table_name)
-    > migrator.add_index(model, *col_names, unique=False)
-    > migrator.add_not_null(model, *field_names)
-    > migrator.add_default(model, field_name, default)
-    > migrator.add_constraint(model, name, sql)
-    > migrator.drop_index(model, *col_names)
-    > migrator.drop_not_null(model, *field_names)
-    > migrator.drop_constraints(model, *constraints)
-
-"""
-
-from contextlib import suppress
-
-import peewee as pw
-from peewee_migrate import Migrator
-
-
-with suppress(ImportError):
-    import playhouse.postgres_ext as pw_pext
-
-
-def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your migrations here."""
-
-    # Alter the tables with timestamps
-    migrator.change_fields(
-        "chatidtag",
-        timestamp=pw.BigIntegerField(),
-    )
-    migrator.change_fields(
-        "document",
-        timestamp=pw.BigIntegerField(),
-    )
-    migrator.change_fields(
-        "modelfile",
-        timestamp=pw.BigIntegerField(),
-    )
-    migrator.change_fields(
-        "prompt",
-        timestamp=pw.BigIntegerField(),
-    )
-    migrator.change_fields(
-        "user",
-        timestamp=pw.BigIntegerField(),
-    )
-    # Alter the tables with varchar to text where necessary
-    migrator.change_fields(
-        "auth",
-        password=pw.TextField(),
-    )
-    migrator.change_fields(
-        "chat",
-        title=pw.TextField(),
-    )
-    migrator.change_fields(
-        "document",
-        title=pw.TextField(),
-        filename=pw.TextField(),
-    )
-    migrator.change_fields(
-        "prompt",
-        title=pw.TextField(),
-    )
-    migrator.change_fields(
-        "user",
-        profile_image_url=pw.TextField(),
-    )
-
-
-def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your rollback migrations here."""
-
-    if isinstance(database, pw.SqliteDatabase):
-        # Alter the tables with timestamps
-        migrator.change_fields(
-            "chatidtag",
-            timestamp=pw.DateField(),
-        )
-        migrator.change_fields(
-            "document",
-            timestamp=pw.DateField(),
-        )
-        migrator.change_fields(
-            "modelfile",
-            timestamp=pw.DateField(),
-        )
-        migrator.change_fields(
-            "prompt",
-            timestamp=pw.DateField(),
-        )
-        migrator.change_fields(
-            "user",
-            timestamp=pw.DateField(),
-        )
-    migrator.change_fields(
-        "auth",
-        password=pw.CharField(max_length=255),
-    )
-    migrator.change_fields(
-        "chat",
-        title=pw.CharField(),
-    )
-    migrator.change_fields(
-        "document",
-        title=pw.CharField(),
-        filename=pw.CharField(),
-    )
-    migrator.change_fields(
-        "prompt",
-        title=pw.CharField(),
-    )
-    migrator.change_fields(
-        "user",
-        profile_image_url=pw.CharField(),
-    )

backend/apps/web/internal/migrations/007_add_user_last_active_at.py

@@ -1,79 +0,0 @@
-"""Peewee migrations -- 002_add_local_sharing.py.
-
-Some examples (model - class or model name)::
-
-    > Model = migrator.orm['table_name']            # Return model in current state by name
-    > Model = migrator.ModelClass                   # Return model in current state by name
-
-    > migrator.sql(sql)                             # Run custom SQL
-    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
-    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
-    > migrator.remove_model(model, cascade=True)    # Remove a model
-    > migrator.add_fields(model, **fields)          # Add fields to a model
-    > migrator.change_fields(model, **fields)       # Change fields
-    > migrator.remove_fields(model, *field_names, cascade=True)
-    > migrator.rename_field(model, old_field_name, new_field_name)
-    > migrator.rename_table(model, new_table_name)
-    > migrator.add_index(model, *col_names, unique=False)
-    > migrator.add_not_null(model, *field_names)
-    > migrator.add_default(model, field_name, default)
-    > migrator.add_constraint(model, name, sql)
-    > migrator.drop_index(model, *col_names)
-    > migrator.drop_not_null(model, *field_names)
-    > migrator.drop_constraints(model, *constraints)
-
-"""
-
-from contextlib import suppress
-
-import peewee as pw
-from peewee_migrate import Migrator
-
-
-with suppress(ImportError):
-    import playhouse.postgres_ext as pw_pext
-
-
-def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your migrations here."""
-
-    # Adding fields created_at and updated_at to the 'user' table
-    migrator.add_fields(
-        "user",
-        created_at=pw.BigIntegerField(null=True),  # Allow null for transition
-        updated_at=pw.BigIntegerField(null=True),  # Allow null for transition
-        last_active_at=pw.BigIntegerField(null=True),  # Allow null for transition
-    )
-
-    # Populate the new fields from an existing 'timestamp' field
-    migrator.sql(
-        'UPDATE "user" SET created_at = timestamp, updated_at = timestamp, last_active_at = timestamp WHERE timestamp IS NOT NULL'
-    )
-
-    # Now that the data has been copied, remove the original 'timestamp' field
-    migrator.remove_fields("user", "timestamp")
-
-    # Update the fields to be not null now that they are populated
-    migrator.change_fields(
-        "user",
-        created_at=pw.BigIntegerField(null=False),
-        updated_at=pw.BigIntegerField(null=False),
-        last_active_at=pw.BigIntegerField(null=False),
-    )
-
-
-def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
-    """Write your rollback migrations here."""
-
-    # Recreate the timestamp field initially allowing null values for safe transition
-    migrator.add_fields("user", timestamp=pw.BigIntegerField(null=True))
-
-    # Copy the earliest created_at date back into the new timestamp field
-    # This assumes created_at was originally a copy of timestamp
-    migrator.sql('UPDATE "user" SET timestamp = created_at')
-
-    # Remove the created_at and updated_at fields
-    migrator.remove_fields("user", "created_at", "updated_at", "last_active_at")
-
-    # Finally, alter the timestamp field to not allow nulls if that was the original setting
-    migrator.change_fields("user", timestamp=pw.BigIntegerField(null=False))

backend/apps/web/internal/migrations/README.md

@@ -1,21 +0,0 @@
-# Database Migrations
-
-This directory contains all the database migrations for the web app.
-Migrations are done using the [`peewee-migrate`](https://github.com/klen/peewee_migrate) library.
-
-Migrations are automatically ran at app startup.
-
-## Creating a migration
-
-Have you made a change to the schema of an existing model?
-You will need to create a migration file to ensure that existing databases are updated for backwards compatibility.
-
-1. Have a database file (`webui.db`) that has the old schema prior to any of your changes.
-2. Make your changes to the models.
-3. From the `backend` directory, run the following command:
-   ```bash
-   pw_migrate create --auto --auto-source apps.web.models --database sqlite:///${SQLITE_DB} --directory apps/web/internal/migrations ${MIGRATION_NAME}
-   ```
-   - `$SQLITE_DB` should be the path to the database file.
-   - `$MIGRATION_NAME` should be a descriptive name for the migration.
-4. The migration file will be created in the `apps/web/internal/migrations` directory.

backend/apps/web/main.py

@@ -19,8 +19,6 @@ from config import (
     DEFAULT_USER_ROLE,
     ENABLE_SIGNUP,
     USER_PERMISSIONS,
-    WEBHOOK_URL,
-    WEBUI_AUTH_TRUSTED_EMAIL_HEADER,
 )
 
 app = FastAPI()
@@ -34,8 +32,7 @@ app.state.DEFAULT_MODELS = DEFAULT_MODELS
 app.state.DEFAULT_PROMPT_SUGGESTIONS = DEFAULT_PROMPT_SUGGESTIONS
 app.state.DEFAULT_USER_ROLE = DEFAULT_USER_ROLE
 app.state.USER_PERMISSIONS = USER_PERMISSIONS
-app.state.WEBHOOK_URL = WEBHOOK_URL
+
-app.state.AUTH_TRUSTED_EMAIL_HEADER = WEBUI_AUTH_TRUSTED_EMAIL_HEADER
 
 app.add_middleware(
     CORSMiddleware,

backend/apps/web/models/auths.py

@@ -2,7 +2,6 @@ from pydantic import BaseModel
 from typing import List, Union, Optional
 import time
 import uuid
-import logging
 from peewee import *
 
 from apps.web.models.users import UserModel, Users
@@ -10,11 +9,6 @@ from utils.utils import verify_password
 
 from apps.web.internal.db import DB
 
-from config import SRC_LOG_LEVELS
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
-
 ####################
 # DB MODEL
 ####################
@@ -23,7 +17,7 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 class Auth(Model):
     id = CharField(unique=True)
     email = CharField()
-    password = TextField()
+    password = CharField()
     active = BooleanField()
 
     class Meta:
@@ -47,10 +41,6 @@ class Token(BaseModel):
     token_type: str
 
 
-class ApiKey(BaseModel):
-    api_key: Optional[str] = None
-
-
 class UserResponse(BaseModel):
     id: str
     email: str
@@ -86,11 +76,6 @@ class SignupForm(BaseModel):
     name: str
     email: str
     password: str
-    profile_image_url: Optional[str] = "/user.png"
-
-
-class AddUserForm(SignupForm):
-    role: Optional[str] = "pending"
 
 
 class AuthsTable:
@@ -99,14 +84,9 @@ class AuthsTable:
         self.db.create_tables([Auth])
 
     def insert_new_auth(
-        self,
+        self, email: str, password: str, name: str, role: str = "pending"
-        email: str,
-        password: str,
-        name: str,
-        profile_image_url: str = "/user.png",
-        role: str = "pending",
     ) -> Optional[UserModel]:
-        log.info("insert_new_auth")
+        print("insert_new_auth")
 
         id = str(uuid.uuid4())
 
@@ -115,7 +95,7 @@ class AuthsTable:
         )
         result = Auth.create(**auth.model_dump())
 
-        user = Users.insert_new_user(id, name, email, profile_image_url, role)
+        user = Users.insert_new_user(id, name, email, role)
 
         if result and user:
             return user
@@ -123,7 +103,7 @@ class AuthsTable:
             return None
 
     def authenticate_user(self, email: str, password: str) -> Optional[UserModel]:
-        log.info(f"authenticate_user: {email}")
+        print("authenticate_user", email)
         try:
             auth = Auth.get(Auth.email == email, Auth.active == True)
             if auth:
@@ -137,28 +117,6 @@ class AuthsTable:
         except:
             return None
 
-    def authenticate_user_by_api_key(self, api_key: str) -> Optional[UserModel]:
-        log.info(f"authenticate_user_by_api_key: {api_key}")
-        # if no api_key, return None
-        if not api_key:
-            return None
-
-        try:
-            user = Users.get_user_by_api_key(api_key)
-            return user if user else None
-        except:
-            return False
-
-    def authenticate_user_by_trusted_header(self, email: str) -> Optional[UserModel]:
-        log.info(f"authenticate_user_by_trusted_header: {email}")
-        try:
-            auth = Auth.get(Auth.email == email, Auth.active == True)
-            if auth:
-                user = Users.get_user_by_id(auth.id)
-                return user
-        except:
-            return None
-
     def update_user_password_by_id(self, id: str, new_password: str) -> bool:
         try:
             query = Auth.update(password=new_password).where(Auth.id == id)

backend/apps/web/models/chats.py

@@ -17,14 +17,9 @@ from apps.web.internal.db import DB
 class Chat(Model):
     id = CharField(unique=True)
     user_id = CharField()
-    title = TextField()
+    title = CharField()
     chat = TextField()  # Save Chat JSON as Text
-
+    timestamp = DateField()
-    created_at = BigIntegerField()
-    updated_at = BigIntegerField()
-
-    share_id = CharField(null=True, unique=True)
-    archived = BooleanField(default=False)
 
     class Meta:
         database = DB
@@ -35,12 +30,7 @@ class ChatModel(BaseModel):
     user_id: str
     title: str
     chat: str
-
+    timestamp: int  # timestamp in epoch
-    created_at: int  # timestamp in epoch
-    updated_at: int  # timestamp in epoch
-
-    share_id: Optional[str] = None
-    archived: bool = False
 
 
 ####################
@@ -61,17 +51,12 @@ class ChatResponse(BaseModel):
     user_id: str
     title: str
     chat: dict
-    updated_at: int  # timestamp in epoch
+    timestamp: int  # timestamp in epoch
-    created_at: int  # timestamp in epoch
-    share_id: Optional[str] = None  # id of the chat to be shared
-    archived: bool
 
 
 class ChatTitleIdResponse(BaseModel):
     id: str
     title: str
-    updated_at: int
-    created_at: int
 
 
 class ChatTable:
@@ -89,8 +74,7 @@ class ChatTable:
                     form_data.chat["title"] if "title" in form_data.chat else "New Chat"
                 ),
                 "chat": json.dumps(form_data.chat),
-                "created_at": int(time.time()),
+                "timestamp": int(time.time()),
-                "updated_at": int(time.time()),
             }
         )
 
@@ -102,7 +86,7 @@ class ChatTable:
             query = Chat.update(
                 chat=json.dumps(chat),
                 title=chat["title"] if "title" in chat else "New Chat",
-                updated_at=int(time.time()),
+                timestamp=int(time.time()),
             ).where(Chat.id == id)
             query.execute()
 
@@ -111,64 +95,12 @@ class ChatTable:
         except:
             return None
 
-    def insert_shared_chat_by_chat_id(self, chat_id: str) -> Optional[ChatModel]:
+    def update_chat_by_id(self, id: str, chat: dict) -> Optional[ChatModel]:
-        # Get the existing chat to share
-        chat = Chat.get(Chat.id == chat_id)
-        # Check if the chat is already shared
-        if chat.share_id:
-            return self.get_chat_by_id_and_user_id(chat.share_id, "shared")
-        # Create a new chat with the same data, but with a new ID
-        shared_chat = ChatModel(
-            **{
-                "id": str(uuid.uuid4()),
-                "user_id": f"shared-{chat_id}",
-                "title": chat.title,
-                "chat": chat.chat,
-                "created_at": chat.created_at,
-                "updated_at": int(time.time()),
-            }
-        )
-        shared_result = Chat.create(**shared_chat.model_dump())
-        # Update the original chat with the share_id
-        result = (
-            Chat.update(share_id=shared_chat.id).where(Chat.id == chat_id).execute()
-        )
-
-        return shared_chat if (shared_result and result) else None
-
-    def update_shared_chat_by_chat_id(self, chat_id: str) -> Optional[ChatModel]:
-        try:
-            print("update_shared_chat_by_id")
-            chat = Chat.get(Chat.id == chat_id)
-            print(chat)
-
-            query = Chat.update(
-                title=chat.title,
-                chat=chat.chat,
-            ).where(Chat.id == chat.share_id)
-
-            query.execute()
-
-            chat = Chat.get(Chat.id == chat.share_id)
-            return ChatModel(**model_to_dict(chat))
-        except:
-            return None
-
-    def delete_shared_chat_by_chat_id(self, chat_id: str) -> bool:
-        try:
-            query = Chat.delete().where(Chat.user_id == f"shared-{chat_id}")
-            query.execute()  # Remove the rows, return number of rows removed.
-
-            return True
-        except:
-            return False
-
-    def update_chat_share_id_by_id(
-        self, id: str, share_id: Optional[str]
-    ) -> Optional[ChatModel]:
         try:
             query = Chat.update(
-                share_id=share_id,
+                chat=json.dumps(chat),
+                title=chat["title"] if "title" in chat else "New Chat",
+                timestamp=int(time.time()),
             ).where(Chat.id == id)
             query.execute()
 
@@ -177,75 +109,41 @@ class ChatTable:
         except:
             return None
 
-    def toggle_chat_archive_by_id(self, id: str) -> Optional[ChatModel]:
+    def get_chat_lists_by_user_id(
-        try:
-            chat = self.get_chat_by_id(id)
-            query = Chat.update(
-                archived=(not chat.archived),
-            ).where(Chat.id == id)
-
-            query.execute()
-
-            chat = Chat.get(Chat.id == id)
-            return ChatModel(**model_to_dict(chat))
-        except:
-            return None
-
-    def get_archived_chat_list_by_user_id(
         self, user_id: str, skip: int = 0, limit: int = 50
     ) -> List[ChatModel]:
         return [
             ChatModel(**model_to_dict(chat))
             for chat in Chat.select()
-            .where(Chat.archived == True)
             .where(Chat.user_id == user_id)
-            .order_by(Chat.updated_at.desc())
+            .order_by(Chat.timestamp.desc())
             # .limit(limit)
             # .offset(skip)
         ]
 
-    def get_chat_list_by_user_id(
+    def get_chat_lists_by_chat_ids(
-        self, user_id: str, skip: int = 0, limit: int = 50
-    ) -> List[ChatModel]:
-        return [
-            ChatModel(**model_to_dict(chat))
-            for chat in Chat.select()
-            .where(Chat.archived == False)
-            .where(Chat.user_id == user_id)
-            .order_by(Chat.updated_at.desc())
-            # .limit(limit)
-            # .offset(skip)
-        ]
-
-    def get_chat_list_by_chat_ids(
         self, chat_ids: List[str], skip: int = 0, limit: int = 50
     ) -> List[ChatModel]:
         return [
             ChatModel(**model_to_dict(chat))
             for chat in Chat.select()
-            .where(Chat.archived == False)
             .where(Chat.id.in_(chat_ids))
-            .order_by(Chat.updated_at.desc())
+            .order_by(Chat.timestamp.desc())
         ]
 
-    def get_chat_by_id(self, id: str) -> Optional[ChatModel]:
+    def get_all_chats(self) -> List[ChatModel]:
-        try:
+        return [
-            chat = Chat.get(Chat.id == id)
+            ChatModel(**model_to_dict(chat))
-            return ChatModel(**model_to_dict(chat))
+            for chat in Chat.select().order_by(Chat.timestamp.desc())
-        except:
+        ]
-            return None
 
-    def get_chat_by_share_id(self, id: str) -> Optional[ChatModel]:
+    def get_all_chats_by_user_id(self, user_id: str) -> List[ChatModel]:
-        try:
+        return [
-            chat = Chat.get(Chat.share_id == id)
+            ChatModel(**model_to_dict(chat))
-
+            for chat in Chat.select()
-            if chat:
+            .where(Chat.user_id == user_id)
-                chat = Chat.get(Chat.id == id)
+            .order_by(Chat.timestamp.desc())
-                return ChatModel(**model_to_dict(chat))
+        ]
-            else:
-                return None
-        except:
-            return None
 
     def get_chat_by_id_and_user_id(self, id: str, user_id: str) -> Optional[ChatModel]:
         try:
@@ -257,42 +155,20 @@ class ChatTable:
     def get_chats(self, skip: int = 0, limit: int = 50) -> List[ChatModel]:
         return [
             ChatModel(**model_to_dict(chat))
-            for chat in Chat.select().order_by(Chat.updated_at.desc())
+            for chat in Chat.select().limit(limit).offset(skip)
-            # .limit(limit).offset(skip)
         ]
 
-    def get_chats_by_user_id(self, user_id: str) -> List[ChatModel]:
-        return [
-            ChatModel(**model_to_dict(chat))
-            for chat in Chat.select()
-            .where(Chat.user_id == user_id)
-            .order_by(Chat.updated_at.desc())
-            # .limit(limit).offset(skip)
-        ]
-
-    def delete_chat_by_id(self, id: str) -> bool:
-        try:
-            query = Chat.delete().where((Chat.id == id))
-            query.execute()  # Remove the rows, return number of rows removed.
-
-            return True and self.delete_shared_chat_by_chat_id(id)
-        except:
-            return False
-
     def delete_chat_by_id_and_user_id(self, id: str, user_id: str) -> bool:
         try:
             query = Chat.delete().where((Chat.id == id) & (Chat.user_id == user_id))
             query.execute()  # Remove the rows, return number of rows removed.
 
-            return True and self.delete_shared_chat_by_chat_id(id)
+            return True
         except:
             return False
 
     def delete_chats_by_user_id(self, user_id: str) -> bool:
         try:
-
-            self.delete_shared_chats_by_user_id(user_id)
-
             query = Chat.delete().where(Chat.user_id == user_id)
             query.execute()  # Remove the rows, return number of rows removed.
 
@@ -300,19 +176,5 @@ class ChatTable:
         except:
             return False
 
-    def delete_shared_chats_by_user_id(self, user_id: str) -> bool:
-        try:
-            shared_chat_ids = [
-                f"shared-{chat.id}"
-                for chat in Chat.select().where(Chat.user_id == user_id)
-            ]
-
-            query = Chat.delete().where(Chat.user_id << shared_chat_ids)
-            query.execute()  # Remove the rows, return number of rows removed.
-
-            return True
-        except:
-            return False
-
 
 Chats = ChatTable(DB)

backend/apps/web/models/documents.py

@@ -3,7 +3,6 @@ from peewee import *
 from playhouse.shortcuts import model_to_dict
 from typing import List, Union, Optional
 import time
-import logging
 
 from utils.utils import decode_token
 from utils.misc import get_gravatar_url
@@ -12,11 +11,6 @@ from apps.web.internal.db import DB
 
 import json
 
-from config import SRC_LOG_LEVELS
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
-
 ####################
 # Documents DB Schema
 ####################
@@ -25,11 +19,11 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 class Document(Model):
     collection_name = CharField(unique=True)
     name = CharField(unique=True)
-    title = TextField()
+    title = CharField()
-    filename = TextField()
+    filename = CharField()
     content = TextField(null=True)
     user_id = CharField()
-    timestamp = BigIntegerField()
+    timestamp = DateField()
 
     class Meta:
         database = DB
@@ -124,7 +118,7 @@ class DocumentsTable:
             doc = Document.get(Document.name == form_data.name)
             return DocumentModel(**model_to_dict(doc))
         except Exception as e:
-            log.exception(e)
+            print(e)
             return None
 
     def update_doc_content_by_name(
@@ -144,7 +138,7 @@ class DocumentsTable:
             doc = Document.get(Document.name == name)
             return DocumentModel(**model_to_dict(doc))
         except Exception as e:
-            log.exception(e)
+            print(e)
             return None
 
     def delete_doc_by_name(self, name: str) -> bool:

backend/apps/web/models/modelfiles.py

@@ -20,7 +20,7 @@ class Modelfile(Model):
     tag_name = CharField(unique=True)
     user_id = CharField()
     modelfile = TextField()
-    timestamp = BigIntegerField()
+    timestamp = DateField()
 
     class Meta:
         database = DB
@@ -64,8 +64,8 @@ class ModelfilesTable:
         self.db.create_tables([Modelfile])
 
     def insert_new_modelfile(
-        self, user_id: str, form_data: ModelfileForm
+            self, user_id: str,
-    ) -> Optional[ModelfileModel]:
+            form_data: ModelfileForm) -> Optional[ModelfileModel]:
         if "tagName" in form_data.modelfile:
             modelfile = ModelfileModel(
                 **{
@@ -73,8 +73,7 @@ class ModelfilesTable:
                     "tag_name": form_data.modelfile["tagName"],
                     "modelfile": json.dumps(form_data.modelfile),
                     "timestamp": int(time.time()),
-                }
+                })
-            )
 
             try:
                 result = Modelfile.create(**modelfile.model_dump())
@@ -88,28 +87,29 @@ class ModelfilesTable:
         else:
             return None
 
-    def get_modelfile_by_tag_name(self, tag_name: str) -> Optional[ModelfileModel]:
+    def get_modelfile_by_tag_name(self,
+                                  tag_name: str) -> Optional[ModelfileModel]:
         try:
             modelfile = Modelfile.get(Modelfile.tag_name == tag_name)
             return ModelfileModel(**model_to_dict(modelfile))
         except:
             return None
 
-    def get_modelfiles(self, skip: int = 0, limit: int = 50) -> List[ModelfileResponse]:
+    def get_modelfiles(self,
+                       skip: int = 0,
+                       limit: int = 50) -> List[ModelfileResponse]:
         return [
             ModelfileResponse(
                 **{
                     **model_to_dict(modelfile),
-                    "modelfile": json.loads(modelfile.modelfile),
+                    "modelfile":
-                }
+                    json.loads(modelfile.modelfile),
-            )
+                }) for modelfile in Modelfile.select()
-            for modelfile in Modelfile.select()
             # .limit(limit).offset(skip)
         ]
 
     def update_modelfile_by_tag_name(
-        self, tag_name: str, modelfile: dict
+            self, tag_name: str, modelfile: dict) -> Optional[ModelfileModel]:
-    ) -> Optional[ModelfileModel]:
         try:
             query = Modelfile.update(
                 modelfile=json.dumps(modelfile),

backend/apps/web/models/prompts.py

@@ -19,9 +19,9 @@ import json
 class Prompt(Model):
     command = CharField(unique=True)
     user_id = CharField()
-    title = TextField()
+    title = CharField()
     content = TextField()
-    timestamp = BigIntegerField()
+    timestamp = DateField()
 
     class Meta:
         database = DB
@@ -52,9 +52,8 @@ class PromptsTable:
         self.db = db
         self.db.create_tables([Prompt])
 
-    def insert_new_prompt(
+    def insert_new_prompt(self, user_id: str,
-        self, user_id: str, form_data: PromptForm
+                          form_data: PromptForm) -> Optional[PromptModel]:
-    ) -> Optional[PromptModel]:
         prompt = PromptModel(
             **{
                 "user_id": user_id,
@@ -62,8 +61,7 @@ class PromptsTable:
                 "title": form_data.title,
                 "content": form_data.content,
                 "timestamp": int(time.time()),
-            }
+            })
-        )
 
         try:
             result = Prompt.create(**prompt.model_dump())
@@ -83,14 +81,13 @@ class PromptsTable:
 
     def get_prompts(self) -> List[PromptModel]:
         return [
-            PromptModel(**model_to_dict(prompt))
+            PromptModel(**model_to_dict(prompt)) for prompt in Prompt.select()
-            for prompt in Prompt.select()
             # .limit(limit).offset(skip)
         ]
 
     def update_prompt_by_command(
-        self, command: str, form_data: PromptForm
+            self, command: str,
-    ) -> Optional[PromptModel]:
+            form_data: PromptForm) -> Optional[PromptModel]:
         try:
             query = Prompt.update(
                 title=form_data.title,

backend/apps/web/models/tags.py

@@ -6,15 +6,9 @@ from playhouse.shortcuts import model_to_dict
 import json
 import uuid
 import time
-import logging
 
 from apps.web.internal.db import DB
 
-from config import SRC_LOG_LEVELS
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
-
 ####################
 # Tag DB Schema
 ####################
@@ -35,7 +29,7 @@ class ChatIdTag(Model):
     tag_name = CharField()
     chat_id = CharField()
     user_id = CharField()
-    timestamp = BigIntegerField()
+    timestamp = DateField()
 
     class Meta:
         database = DB
@@ -136,9 +130,7 @@ class TagTable:
 
         return [
             TagModel(**model_to_dict(tag))
-            for tag in Tag.select()
+            for tag in Tag.select().where(Tag.name.in_(tag_names))
-            .where(Tag.user_id == user_id)
-            .where(Tag.name.in_(tag_names))
         ]
 
     def get_tags_by_chat_id_and_user_id(
@@ -153,9 +145,7 @@ class TagTable:
 
         return [
             TagModel(**model_to_dict(tag))
-            for tag in Tag.select()
+            for tag in Tag.select().where(Tag.name.in_(tag_names))
-            .where(Tag.user_id == user_id)
-            .where(Tag.name.in_(tag_names))
         ]
 
     def get_chat_ids_by_tag_name_and_user_id(
@@ -183,7 +173,7 @@ class TagTable:
                 (ChatIdTag.tag_name == tag_name) & (ChatIdTag.user_id == user_id)
             )
             res = query.execute()  # Remove the rows, return number of rows removed.
-            log.debug(f"res: {res}")
+            print(res)
 
             tag_count = self.count_chat_ids_by_tag_name_and_user_id(tag_name, user_id)
             if tag_count == 0:
@@ -195,7 +185,7 @@ class TagTable:
 
             return True
         except Exception as e:
-            log.error(f"delete_tag: {e}")
+            print("delete_tag", e)
             return False
 
     def delete_tag_by_tag_name_and_chat_id_and_user_id(
@@ -208,7 +198,7 @@ class TagTable:
                 & (ChatIdTag.user_id == user_id)
             )
             res = query.execute()  # Remove the rows, return number of rows removed.
-            log.debug(f"res: {res}")
+            print(res)
 
             tag_count = self.count_chat_ids_by_tag_name_and_user_id(tag_name, user_id)
             if tag_count == 0:
@@ -220,7 +210,7 @@ class TagTable:
 
             return True
         except Exception as e:
-            log.error(f"delete_tag: {e}")
+            print("delete_tag", e)
             return False
 
     def delete_tags_by_chat_id_and_user_id(self, chat_id: str, user_id: str) -> bool:

backend/apps/web/models/users.py

@@ -18,13 +18,8 @@ class User(Model):
     name = CharField()
     email = CharField()
     role = CharField()
-    profile_image_url = TextField()
+    profile_image_url = CharField()
-
+    timestamp = DateField()
-    last_active_at = BigIntegerField()
-    updated_at = BigIntegerField()
-    created_at = BigIntegerField()
-
-    api_key = CharField(null=True, unique=True)
 
     class Meta:
         database = DB
@@ -35,13 +30,8 @@ class UserModel(BaseModel):
     name: str
     email: str
     role: str = "pending"
-    profile_image_url: str
+    profile_image_url: str = "/user.png"
-
+    timestamp: int  # timestamp in epoch
-    last_active_at: int  # timestamp in epoch
-    updated_at: int  # timestamp in epoch
-    created_at: int  # timestamp in epoch
-
-    api_key: Optional[str] = None
 
 
 ####################
@@ -67,12 +57,7 @@ class UsersTable:
         self.db.create_tables([User])
 
     def insert_new_user(
-        self,
+        self, id: str, name: str, email: str, role: str = "pending"
-        id: str,
-        name: str,
-        email: str,
-        profile_image_url: str = "/user.png",
-        role: str = "pending",
     ) -> Optional[UserModel]:
         user = UserModel(
             **{
@@ -80,10 +65,8 @@ class UsersTable:
                 "name": name,
                 "email": email,
                 "role": role,
-                "profile_image_url": profile_image_url,
+                "profile_image_url": "/user.png",
-                "last_active_at": int(time.time()),
+                "timestamp": int(time.time()),
-                "created_at": int(time.time()),
-                "updated_at": int(time.time()),
             }
         )
         result = User.create(**user.model_dump())
@@ -99,13 +82,6 @@ class UsersTable:
         except:
             return None
 
-    def get_user_by_api_key(self, api_key: str) -> Optional[UserModel]:
-        try:
-            user = User.get(User.api_key == api_key)
-            return UserModel(**model_to_dict(user))
-        except:
-            return None
-
     def get_user_by_email(self, email: str) -> Optional[UserModel]:
         try:
             user = User.get(User.email == email)
@@ -123,13 +99,6 @@ class UsersTable:
     def get_num_users(self) -> Optional[int]:
         return User.select().count()
 
-    def get_first_user(self) -> UserModel:
-        try:
-            user = User.select().order_by(User.created_at).first()
-            return UserModel(**model_to_dict(user))
-        except:
-            return None
-
     def update_user_role_by_id(self, id: str, role: str) -> Optional[UserModel]:
         try:
             query = User.update(role=role).where(User.id == id)
@@ -154,16 +123,6 @@ class UsersTable:
         except:
             return None
 
-    def update_user_last_active_by_id(self, id: str) -> Optional[UserModel]:
-        try:
-            query = User.update(last_active_at=int(time.time())).where(User.id == id)
-            query.execute()
-
-            user = User.get(User.id == id)
-            return UserModel(**model_to_dict(user))
-        except:
-            return None
-
     def update_user_by_id(self, id: str, updated: dict) -> Optional[UserModel]:
         try:
             query = User.update(**updated).where(User.id == id)
@@ -190,21 +149,5 @@ class UsersTable:
         except:
             return False
 
-    def update_user_api_key_by_id(self, id: str, api_key: str) -> str:
-        try:
-            query = User.update(api_key=api_key).where(User.id == id)
-            result = query.execute()
-
-            return True if result == 1 else False
-        except:
-            return False
-
-    def get_user_api_key_by_id(self, id: str) -> Optional[str]:
-        try:
-            user = User.get(User.id == id)
-            return user.api_key
-        except:
-            return None
-
 
 Users = UsersTable(DB)

backend/apps/web/routers/auths.py

@@ -1,25 +1,22 @@
-import logging
+from fastapi import Response, Request
+from fastapi import Depends, FastAPI, HTTPException, status
+from datetime import datetime, timedelta
+from typing import List, Union
 
-from fastapi import Request, UploadFile, File
+from fastapi import APIRouter, status
-from fastapi import Depends, HTTPException, status
-
-from fastapi import APIRouter
 from pydantic import BaseModel
-import re
+import time
 import uuid
-import csv
+import re
-
 
 from apps.web.models.auths import (
     SigninForm,
     SignupForm,
-    AddUserForm,
     UpdateProfileForm,
     UpdatePasswordForm,
     UserResponse,
     SigninResponse,
     Auths,
-    ApiKey,
 )
 from apps.web.models.users import Users
 
@@ -28,12 +25,9 @@ from utils.utils import (
     get_current_user,
     get_admin_user,
     create_token,
-    create_api_key,
 )
 from utils.misc import parse_duration, validate_email_format
-from utils.webhook import post_webhook
+from constants import ERROR_MESSAGES
-from constants import ERROR_MESSAGES, WEBHOOK_MESSAGES
-from config import WEBUI_AUTH_TRUSTED_EMAIL_HEADER
 
 router = APIRouter()
 
@@ -84,8 +78,6 @@ async def update_profile(
 async def update_password(
     form_data: UpdatePasswordForm, session_user=Depends(get_current_user)
 ):
-    if WEBUI_AUTH_TRUSTED_EMAIL_HEADER:
-        raise HTTPException(400, detail=ERROR_MESSAGES.ACTION_PROHIBITED)
     if session_user:
         user = Auths.authenticate_user(session_user.email, form_data.password)
 
@@ -105,22 +97,7 @@ async def update_password(
 
 @router.post("/signin", response_model=SigninResponse)
 async def signin(request: Request, form_data: SigninForm):
-    if WEBUI_AUTH_TRUSTED_EMAIL_HEADER:
+    user = Auths.authenticate_user(form_data.email.lower(), form_data.password)
-        if WEBUI_AUTH_TRUSTED_EMAIL_HEADER not in request.headers:
-            raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_TRUSTED_HEADER)
-
-        trusted_email = request.headers[WEBUI_AUTH_TRUSTED_EMAIL_HEADER].lower()
-        if not Users.get_user_by_email(trusted_email.lower()):
-            await signup(
-                request,
-                SignupForm(
-                    email=trusted_email, password=str(uuid.uuid4()), name=trusted_email
-                ),
-            )
-        user = Auths.authenticate_user_by_trusted_header(trusted_email)
-    else:
-        user = Auths.authenticate_user(form_data.email.lower(), form_data.password)
-
     if user:
         token = create_token(
             data={"id": user.id},
@@ -168,11 +145,7 @@ async def signup(request: Request, form_data: SignupForm):
         )
         hashed = get_password_hash(form_data.password)
         user = Auths.insert_new_auth(
-            form_data.email.lower(),
+            form_data.email.lower(), hashed, form_data.name, role
-            hashed,
-            form_data.name,
-            form_data.profile_image_url,
-            role,
         )
 
         if user:
@@ -182,62 +155,6 @@ async def signup(request: Request, form_data: SignupForm):
             )
             # response.set_cookie(key='token', value=token, httponly=True)
 
-            if request.app.state.WEBHOOK_URL:
-                post_webhook(
-                    request.app.state.WEBHOOK_URL,
-                    WEBHOOK_MESSAGES.USER_SIGNUP(user.name),
-                    {
-                        "action": "signup",
-                        "message": WEBHOOK_MESSAGES.USER_SIGNUP(user.name),
-                        "user": user.model_dump_json(exclude_none=True),
-                    },
-                )
-
-            return {
-                "token": token,
-                "token_type": "Bearer",
-                "id": user.id,
-                "email": user.email,
-                "name": user.name,
-                "role": user.role,
-                "profile_image_url": user.profile_image_url,
-            }
-        else:
-            raise HTTPException(500, detail=ERROR_MESSAGES.CREATE_USER_ERROR)
-    except Exception as err:
-        raise HTTPException(500, detail=ERROR_MESSAGES.DEFAULT(err))
-
-
-############################
-# AddUser
-############################
-
-
-@router.post("/add", response_model=SigninResponse)
-async def add_user(form_data: AddUserForm, user=Depends(get_admin_user)):
-
-    if not validate_email_format(form_data.email.lower()):
-        raise HTTPException(
-            status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.INVALID_EMAIL_FORMAT
-        )
-
-    if Users.get_user_by_email(form_data.email.lower()):
-        raise HTTPException(400, detail=ERROR_MESSAGES.EMAIL_TAKEN)
-
-    try:
-
-        print(form_data)
-        hashed = get_password_hash(form_data.password)
-        user = Auths.insert_new_auth(
-            form_data.email.lower(),
-            hashed,
-            form_data.name,
-            form_data.profile_image_url,
-            form_data.role,
-        )
-
-        if user:
-            token = create_token(data={"id": user.id})
             return {
                 "token": token,
                 "token_type": "Bearer",
@@ -320,40 +237,3 @@ async def update_token_expires_duration(
         return request.app.state.JWT_EXPIRES_IN
     else:
         return request.app.state.JWT_EXPIRES_IN
-
-
-############################
-# API Key
-############################
-
-
-# create api key
-@router.post("/api_key", response_model=ApiKey)
-async def create_api_key_(user=Depends(get_current_user)):
-    api_key = create_api_key()
-    success = Users.update_user_api_key_by_id(user.id, api_key)
-    if success:
-        return {
-            "api_key": api_key,
-        }
-    else:
-        raise HTTPException(500, detail=ERROR_MESSAGES.CREATE_API_KEY_ERROR)
-
-
-# delete api key
-@router.delete("/api_key", response_model=bool)
-async def delete_api_key(user=Depends(get_current_user)):
-    success = Users.update_user_api_key_by_id(user.id, None)
-    return success
-
-
-# get api key
-@router.get("/api_key", response_model=ApiKey)
-async def get_api_key(user=Depends(get_current_user)):
-    api_key = Users.get_user_api_key_by_id(user.id)
-    if api_key:
-        return {
-            "api_key": api_key,
-        }
-    else:
-        raise HTTPException(404, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)

backend/apps/web/routers/chats.py

@@ -5,7 +5,6 @@ from utils.utils import get_current_user, get_admin_user
 from fastapi import APIRouter
 from pydantic import BaseModel
 import json
-import logging
 
 from apps.web.models.users import Users
 from apps.web.models.chats import (
@@ -28,81 +27,30 @@ from apps.web.models.tags import (
 
 from constants import ERROR_MESSAGES
 
-from config import SRC_LOG_LEVELS, ENABLE_ADMIN_EXPORT
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
-
 router = APIRouter()
 
-############################
-# GetChatList
-############################
-
-
-@router.get("/", response_model=List[ChatTitleIdResponse])
-@router.get("/list", response_model=List[ChatTitleIdResponse])
-async def get_session_user_chat_list(
-    user=Depends(get_current_user), skip: int = 0, limit: int = 50
-):
-    return Chats.get_chat_list_by_user_id(user.id, skip, limit)
-
-
-############################
-# DeleteAllChats
-############################
-
-
-@router.delete("/", response_model=bool)
-async def delete_all_user_chats(request: Request, user=Depends(get_current_user)):
-
-    if (
-        user.role == "user"
-        and not request.app.state.USER_PERMISSIONS["chat"]["deletion"]
-    ):
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-        )
-
-    result = Chats.delete_chats_by_user_id(user.id)
-    return result
-
-
-############################
-# GetUserChatList
-############################
-
-
-@router.get("/list/user/{user_id}", response_model=List[ChatTitleIdResponse])
-async def get_user_chat_list_by_user_id(
-    user_id: str, user=Depends(get_admin_user), skip: int = 0, limit: int = 50
-):
-    return Chats.get_chat_list_by_user_id(user_id, skip, limit)
-
-
-############################
-# GetArchivedChats
-############################
-
-
-@router.get("/archived", response_model=List[ChatTitleIdResponse])
-async def get_archived_session_user_chat_list(
-    user=Depends(get_current_user), skip: int = 0, limit: int = 50
-):
-    return Chats.get_archived_chat_list_by_user_id(user.id, skip, limit)
-
-
 ############################
 # GetChats
 ############################
 
 
+@router.get("/", response_model=List[ChatTitleIdResponse])
+async def get_user_chats(
+    user=Depends(get_current_user), skip: int = 0, limit: int = 50
+):
+    return Chats.get_chat_lists_by_user_id(user.id, skip, limit)
+
+
+############################
+# GetAllChats
+############################
+
+
 @router.get("/all", response_model=List[ChatResponse])
-async def get_user_chats(user=Depends(get_current_user)):
+async def get_all_user_chats(user=Depends(get_current_user)):
     return [
         ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
-        for chat in Chats.get_chats_by_user_id(user.id)
+        for chat in Chats.get_all_chats_by_user_id(user.id)
     ]
 
 
@@ -113,14 +61,9 @@ async def get_user_chats(user=Depends(get_current_user)):
 
 @router.get("/all/db", response_model=List[ChatResponse])
 async def get_all_user_chats_in_db(user=Depends(get_admin_user)):
-    if not ENABLE_ADMIN_EXPORT:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-        )
     return [
         ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
-        for chat in Chats.get_chats()
+        for chat in Chats.get_all_chats()
     ]
 
 
@@ -135,12 +78,51 @@ async def create_new_chat(form_data: ChatForm, user=Depends(get_current_user)):
         chat = Chats.insert_new_chat(user.id, form_data)
         return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
     except Exception as e:
-        log.exception(e)
+        print(e)
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
         )
 
 
+############################
+# GetAllTags
+############################
+
+
+@router.get("/tags/all", response_model=List[TagModel])
+async def get_all_tags(user=Depends(get_current_user)):
+    try:
+        tags = Tags.get_tags_by_user_id(user.id)
+        return tags
+    except Exception as e:
+        print(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
+        )
+
+
+############################
+# GetChatsByTags
+############################
+
+
+@router.get("/tags/tag/{tag_name}", response_model=List[ChatTitleIdResponse])
+async def get_user_chats_by_tag_name(
+    tag_name: str, user=Depends(get_current_user), skip: int = 0, limit: int = 50
+):
+    chat_ids = [
+        chat_id_tag.chat_id
+        for chat_id_tag in Tags.get_chat_ids_by_tag_name_and_user_id(tag_name, user.id)
+    ]
+
+    chats = Chats.get_chat_lists_by_chat_ids(chat_ids, skip, limit)
+
+    if len(chats) == 0:
+        Tags.delete_tag_by_tag_name_and_user_id(tag_name, user.id)
+
+    return chats
+
+
 ############################
 # GetChatById
 ############################
@@ -188,154 +170,17 @@ async def update_chat_by_id(
 @router.delete("/{id}", response_model=bool)
 async def delete_chat_by_id(request: Request, id: str, user=Depends(get_current_user)):
 
-    if user.role == "admin":
+    if (
-        result = Chats.delete_chat_by_id(id)
+        user.role == "user"
-        return result
+        and not request.app.state.USER_PERMISSIONS["chat"]["deletion"]
-    else:
+    ):
-        if not request.app.state.USER_PERMISSIONS["chat"]["deletion"]:
-            raise HTTPException(
-                status_code=status.HTTP_401_UNAUTHORIZED,
-                detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-            )
-
-        result = Chats.delete_chat_by_id_and_user_id(id, user.id)
-        return result
-
-
-############################
-# ArchiveChat
-############################
-
-
-@router.get("/{id}/archive", response_model=Optional[ChatResponse])
-async def archive_chat_by_id(id: str, user=Depends(get_current_user)):
-    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
-    if chat:
-        chat = Chats.toggle_chat_archive_by_id(id)
-        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.DEFAULT()
-        )
-
-
-############################
-# ShareChatById
-############################
-
-
-@router.post("/{id}/share", response_model=Optional[ChatResponse])
-async def share_chat_by_id(id: str, user=Depends(get_current_user)):
-    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
-    if chat:
-        if chat.share_id:
-            shared_chat = Chats.update_shared_chat_by_chat_id(chat.id)
-            return ChatResponse(
-                **{**shared_chat.model_dump(), "chat": json.loads(shared_chat.chat)}
-            )
-
-        shared_chat = Chats.insert_shared_chat_by_chat_id(chat.id)
-        if not shared_chat:
-            raise HTTPException(
-                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                detail=ERROR_MESSAGES.DEFAULT(),
-            )
-
-        return ChatResponse(
-            **{**shared_chat.model_dump(), "chat": json.loads(shared_chat.chat)}
-        )
-    else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
             detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
         )
 
-
+    result = Chats.delete_chat_by_id_and_user_id(id, user.id)
-############################
+    return result
-# DeletedSharedChatById
-############################
-
-
-@router.delete("/{id}/share", response_model=Optional[bool])
-async def delete_shared_chat_by_id(id: str, user=Depends(get_current_user)):
-    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
-    if chat:
-        if not chat.share_id:
-            return False
-
-        result = Chats.delete_shared_chat_by_chat_id(id)
-        update_result = Chats.update_chat_share_id_by_id(id, None)
-
-        return result and update_result != None
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-        )
-
-
-############################
-# GetSharedChatById
-############################
-
-
-@router.get("/share/{share_id}", response_model=Optional[ChatResponse])
-async def get_shared_chat_by_id(share_id: str, user=Depends(get_current_user)):
-    if user.role == "pending":
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
-        )
-
-    if user.role == "user":
-        chat = Chats.get_chat_by_share_id(share_id)
-    elif user.role == "admin":
-        chat = Chats.get_chat_by_id(share_id)
-
-    if chat:
-        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
-        )
-
-
-############################
-# GetAllTags
-############################
-
-
-@router.get("/tags/all", response_model=List[TagModel])
-async def get_all_tags(user=Depends(get_current_user)):
-    try:
-        tags = Tags.get_tags_by_user_id(user.id)
-        return tags
-    except Exception as e:
-        log.exception(e)
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
-        )
-
-
-############################
-# GetChatsByTags
-############################
-
-
-@router.get("/tags/tag/{tag_name}", response_model=List[ChatTitleIdResponse])
-async def get_user_chat_list_by_tag_name(
-    tag_name: str, user=Depends(get_current_user), skip: int = 0, limit: int = 50
-):
-    chat_ids = [
-        chat_id_tag.chat_id
-        for chat_id_tag in Tags.get_chat_ids_by_tag_name_and_user_id(tag_name, user.id)
-    ]
-
-    chats = Chats.get_chat_list_by_chat_ids(chat_ids, skip, limit)
-
-    if len(chats) == 0:
-        Tags.delete_tag_by_tag_name_and_user_id(tag_name, user.id)
-
-    return chats
 
 
 ############################
@@ -418,3 +263,24 @@ async def delete_all_chat_tags_by_id(id: str, user=Depends(get_current_user)):
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
         )
+
+
+############################
+# DeleteAllChats
+############################
+
+
+@router.delete("/", response_model=bool)
+async def delete_all_user_chats(request: Request, user=Depends(get_current_user)):
+
+    if (
+        user.role == "user"
+        and not request.app.state.USER_PERMISSIONS["chat"]["deletion"]
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+    result = Chats.delete_chats_by_user_id(user.id)
+    return result

backend/apps/web/routers/configs.py

@@ -10,12 +10,7 @@ import uuid
 
 from apps.web.models.users import Users
 
-from utils.utils import (
+from utils.utils import get_password_hash, get_current_user, get_admin_user, create_token
-    get_password_hash,
-    get_current_user,
-    get_admin_user,
-    create_token,
-)
 from utils.misc import get_gravatar_url, validate_email_format
 from constants import ERROR_MESSAGES
 
@@ -48,6 +43,7 @@ async def set_global_default_models(
     return request.app.state.DEFAULT_MODELS
 
 
+
 @router.post("/default/suggestions", response_model=List[PromptSuggestion])
 async def set_global_default_suggestions(
     request: Request,

backend/apps/web/routers/modelfiles.py

@@ -24,9 +24,9 @@ router = APIRouter()
 
 
 @router.get("/", response_model=List[ModelfileResponse])
-async def get_modelfiles(
+async def get_modelfiles(skip: int = 0,
-    skip: int = 0, limit: int = 50, user=Depends(get_current_user)
+                         limit: int = 50,
-):
+                         user=Depends(get_current_user)):
     return Modelfiles.get_modelfiles(skip, limit)
 
 
@@ -36,16 +36,17 @@ async def get_modelfiles(
 
 
 @router.post("/create", response_model=Optional[ModelfileResponse])
-async def create_new_modelfile(form_data: ModelfileForm, user=Depends(get_admin_user)):
+async def create_new_modelfile(form_data: ModelfileForm,
+                               user=Depends(get_admin_user)):
     modelfile = Modelfiles.insert_new_modelfile(user.id, form_data)
 
     if modelfile:
         return ModelfileResponse(
             **{
                 **modelfile.model_dump(),
-                "modelfile": json.loads(modelfile.modelfile),
+                "modelfile":
-            }
+                json.loads(modelfile.modelfile),
-        )
+            })
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
@@ -59,18 +60,17 @@ async def create_new_modelfile(form_data: ModelfileForm, user=Depends(get_admin_
 
 
 @router.post("/", response_model=Optional[ModelfileResponse])
-async def get_modelfile_by_tag_name(
+async def get_modelfile_by_tag_name(form_data: ModelfileTagNameForm,
-    form_data: ModelfileTagNameForm, user=Depends(get_current_user)
+                                    user=Depends(get_current_user)):
-):
     modelfile = Modelfiles.get_modelfile_by_tag_name(form_data.tag_name)
 
     if modelfile:
         return ModelfileResponse(
             **{
                 **modelfile.model_dump(),
-                "modelfile": json.loads(modelfile.modelfile),
+                "modelfile":
-            }
+                json.loads(modelfile.modelfile),
-        )
+            })
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
@@ -84,9 +84,8 @@ async def get_modelfile_by_tag_name(
 
 
 @router.post("/update", response_model=Optional[ModelfileResponse])
-async def update_modelfile_by_tag_name(
+async def update_modelfile_by_tag_name(form_data: ModelfileUpdateForm,
-    form_data: ModelfileUpdateForm, user=Depends(get_admin_user)
+                                       user=Depends(get_admin_user)):
-):
     modelfile = Modelfiles.get_modelfile_by_tag_name(form_data.tag_name)
     if modelfile:
         updated_modelfile = {
@@ -95,15 +94,14 @@ async def update_modelfile_by_tag_name(
         }
 
         modelfile = Modelfiles.update_modelfile_by_tag_name(
-            form_data.tag_name, updated_modelfile
+            form_data.tag_name, updated_modelfile)
-        )
 
         return ModelfileResponse(
             **{
                 **modelfile.model_dump(),
-                "modelfile": json.loads(modelfile.modelfile),
+                "modelfile":
-            }
+                json.loads(modelfile.modelfile),
-        )
+            })
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
@@ -117,8 +115,7 @@ async def update_modelfile_by_tag_name(
 
 
 @router.delete("/delete", response_model=bool)
-async def delete_modelfile_by_tag_name(
+async def delete_modelfile_by_tag_name(form_data: ModelfileTagNameForm,
-    form_data: ModelfileTagNameForm, user=Depends(get_admin_user)
+                                       user=Depends(get_admin_user)):
-):
     result = Modelfiles.delete_modelfile_by_tag_name(form_data.tag_name)
     return result

backend/apps/web/routers/users.py

@@ -7,7 +7,6 @@ from fastapi import APIRouter
 from pydantic import BaseModel
 import time
 import uuid
-import logging
 
 from apps.web.models.users import UserModel, UserUpdateForm, UserRoleUpdateForm, Users
 from apps.web.models.auths import Auths
@@ -15,11 +14,6 @@ from apps.web.models.auths import Auths
 from utils.utils import get_current_user, get_password_hash, get_admin_user
 from constants import ERROR_MESSAGES
 
-from config import SRC_LOG_LEVELS
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
-
 router = APIRouter()
 
 ############################
@@ -58,7 +52,7 @@ async def update_user_permissions(
 @router.post("/update/role", response_model=Optional[UserModel])
 async def update_user_role(form_data: UserRoleUpdateForm, user=Depends(get_admin_user)):
 
-    if user.id != form_data.id and form_data.id != Users.get_first_user().id:
+    if user.id != form_data.id:
         return Users.update_user_role_by_id(form_data.id, form_data.role)
 
     raise HTTPException(
@@ -89,7 +83,7 @@ async def update_user_by_id(
 
         if form_data.password:
             hashed = get_password_hash(form_data.password)
-            log.debug(f"hashed: {hashed}")
+            print(hashed)
             Auths.update_user_password_by_id(user_id, hashed)
 
         Auths.update_email_by_id(user_id, form_data.email.lower())

backend/apps/web/routers/utils.py

@@ -1,24 +1,175 @@
-from fastapi import APIRouter, UploadFile, File, Response
+from fastapi import APIRouter, UploadFile, File, BackgroundTasks
 from fastapi import Depends, HTTPException, status
-from peewee import SqliteDatabase
 from starlette.responses import StreamingResponse, FileResponse
+
+
 from pydantic import BaseModel
 
+import requests
+import os
+import aiohttp
+import json
 
-from fpdf import FPDF
-import markdown
 
-from apps.web.internal.db import DB
 from utils.utils import get_admin_user
 from utils.misc import calculate_sha256, get_gravatar_url
 
-from config import OLLAMA_BASE_URLS, DATA_DIR, UPLOAD_DIR, ENABLE_ADMIN_EXPORT
+from config import OLLAMA_BASE_URLS, DATA_DIR, UPLOAD_DIR
 from constants import ERROR_MESSAGES
-from typing import List
+
 
 router = APIRouter()
 
 
+class UploadBlobForm(BaseModel):
+    filename: str
+
+
+from urllib.parse import urlparse
+
+
+def parse_huggingface_url(hf_url):
+    try:
+        # Parse the URL
+        parsed_url = urlparse(hf_url)
+
+        # Get the path and split it into components
+        path_components = parsed_url.path.split("/")
+
+        # Extract the desired output
+        user_repo = "/".join(path_components[1:3])
+        model_file = path_components[-1]
+
+        return model_file
+    except ValueError:
+        return None
+
+
+async def download_file_stream(url, file_path, file_name, chunk_size=1024 * 1024):
+    done = False
+
+    if os.path.exists(file_path):
+        current_size = os.path.getsize(file_path)
+    else:
+        current_size = 0
+
+    headers = {"Range": f"bytes={current_size}-"} if current_size > 0 else {}
+
+    timeout = aiohttp.ClientTimeout(total=600)  # Set the timeout
+
+    async with aiohttp.ClientSession(timeout=timeout) as session:
+        async with session.get(url, headers=headers) as response:
+            total_size = int(response.headers.get("content-length", 0)) + current_size
+
+            with open(file_path, "ab+") as file:
+                async for data in response.content.iter_chunked(chunk_size):
+                    current_size += len(data)
+                    file.write(data)
+
+                    done = current_size == total_size
+                    progress = round((current_size / total_size) * 100, 2)
+                    yield f'data: {{"progress": {progress}, "completed": {current_size}, "total": {total_size}}}\n\n'
+
+                if done:
+                    file.seek(0)
+                    hashed = calculate_sha256(file)
+                    file.seek(0)
+
+                    url = f"{OLLAMA_BASE_URLS[0]}/blobs/sha256:{hashed}"
+                    response = requests.post(url, data=file)
+
+                    if response.ok:
+                        res = {
+                            "done": done,
+                            "blob": f"sha256:{hashed}",
+                            "name": file_name,
+                        }
+                        os.remove(file_path)
+
+                        yield f"data: {json.dumps(res)}\n\n"
+                    else:
+                        raise "Ollama: Could not create blob, Please try again."
+
+
+@router.get("/download")
+async def download(
+    url: str,
+):
+    # url = "https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF/resolve/main/stablelm-zephyr-3b.Q2_K.gguf"
+    file_name = parse_huggingface_url(url)
+
+    if file_name:
+        file_path = f"{UPLOAD_DIR}/{file_name}"
+
+        return StreamingResponse(
+            download_file_stream(url, file_path, file_name),
+            media_type="text/event-stream",
+        )
+    else:
+        return None
+
+
+@router.post("/upload")
+def upload(file: UploadFile = File(...)):
+    file_path = f"{UPLOAD_DIR}/{file.filename}"
+
+    # Save file in chunks
+    with open(file_path, "wb+") as f:
+        for chunk in file.file:
+            f.write(chunk)
+
+    def file_process_stream():
+        total_size = os.path.getsize(file_path)
+        chunk_size = 1024 * 1024
+        try:
+            with open(file_path, "rb") as f:
+                total = 0
+                done = False
+
+                while not done:
+                    chunk = f.read(chunk_size)
+                    if not chunk:
+                        done = True
+                        continue
+
+                    total += len(chunk)
+                    progress = round((total / total_size) * 100, 2)
+
+                    res = {
+                        "progress": progress,
+                        "total": total_size,
+                        "completed": total,
+                    }
+                    yield f"data: {json.dumps(res)}\n\n"
+
+                if done:
+                    f.seek(0)
+                    hashed = calculate_sha256(f)
+                    f.seek(0)
+
+                    url = f"{OLLAMA_BASE_URLS[0]}/blobs/sha256:{hashed}"
+                    response = requests.post(url, data=f)
+
+                    if response.ok:
+                        res = {
+                            "done": done,
+                            "blob": f"sha256:{hashed}",
+                            "name": file.filename,
+                        }
+                        os.remove(file_path)
+                        yield f"data: {json.dumps(res)}\n\n"
+                    else:
+                        raise Exception(
+                            "Ollama: Could not create blob, Please try again."
+                        )
+
+        except Exception as e:
+            res = {"error": str(e)}
+            yield f"data: {json.dumps(res)}\n\n"
+
+    return StreamingResponse(file_process_stream(), media_type="text/event-stream")
+
+
 @router.get("/gravatar")
 async def get_gravatar(
     email: str,
@@ -26,84 +177,11 @@ async def get_gravatar(
     return get_gravatar_url(email)
 
 
-class MarkdownForm(BaseModel):
-    md: str
-
-
-@router.post("/markdown")
-async def get_html_from_markdown(
-    form_data: MarkdownForm,
-):
-    return {"html": markdown.markdown(form_data.md)}
-
-
-class ChatForm(BaseModel):
-    title: str
-    messages: List[dict]
-
-
-@router.post("/pdf")
-async def download_chat_as_pdf(
-    form_data: ChatForm,
-):
-    pdf = FPDF()
-    pdf.add_page()
-
-    STATIC_DIR = "./static"
-    FONTS_DIR = f"{STATIC_DIR}/fonts"
-
-    pdf.add_font("NotoSans", "", f"{FONTS_DIR}/NotoSans-Regular.ttf")
-    pdf.add_font("NotoSans", "b", f"{FONTS_DIR}/NotoSans-Bold.ttf")
-    pdf.add_font("NotoSans", "i", f"{FONTS_DIR}/NotoSans-Italic.ttf")
-    pdf.add_font("NotoSansKR", "", f"{FONTS_DIR}/NotoSansKR-Regular.ttf")
-    pdf.add_font("NotoSansJP", "", f"{FONTS_DIR}/NotoSansJP-Regular.ttf")
-
-    pdf.set_font("NotoSans", size=12)
-    pdf.set_fallback_fonts(["NotoSansKR", "NotoSansJP"])
-
-    pdf.set_auto_page_break(auto=True, margin=15)
-
-    # Adjust the effective page width for multi_cell
-    effective_page_width = (
-        pdf.w - 2 * pdf.l_margin - 10
-    )  # Subtracted an additional 10 for extra padding
-
-    # Add chat messages
-    for message in form_data.messages:
-        role = message["role"]
-        content = message["content"]
-        pdf.set_font("NotoSans", "B", size=14)  # Bold for the role
-        pdf.multi_cell(effective_page_width, 10, f"{role.upper()}", 0, "L")
-        pdf.ln(1)  # Extra space between messages
-
-        pdf.set_font("NotoSans", size=10)  # Regular for content
-        pdf.multi_cell(effective_page_width, 6, content, 0, "L")
-        pdf.ln(1.5)  # Extra space between messages
-
-    # Save the pdf with name .pdf
-    pdf_bytes = pdf.output()
-
-    return Response(
-        content=bytes(pdf_bytes),
-        media_type="application/pdf",
-        headers={"Content-Disposition": f"attachment;filename=chat.pdf"},
-    )
-
-
 @router.get("/db/download")
 async def download_db(user=Depends(get_admin_user)):
-    if not ENABLE_ADMIN_EXPORT:
+
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-        )
-    if not isinstance(DB, SqliteDatabase):
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=ERROR_MESSAGES.DB_NOT_SQLITE,
-        )
     return FileResponse(
-        DB.database,
+        f"{DATA_DIR}/webui.db",
         media_type="application/octet-stream",
         filename="webui.db",
     )

backend/config.py

@@ -1,6 +1,4 @@
 import os
-import sys
-import logging
 import chromadb
 from chromadb import Settings
 from base64 import b64encode
@@ -18,63 +16,15 @@ from secrets import token_bytes
 from constants import ERROR_MESSAGES
 
 
-####################################
-# LOGGING
-####################################
-
-log_levels = ["CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"]
-
-GLOBAL_LOG_LEVEL = os.environ.get("GLOBAL_LOG_LEVEL", "").upper()
-if GLOBAL_LOG_LEVEL in log_levels:
-    logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL, force=True)
-else:
-    GLOBAL_LOG_LEVEL = "INFO"
-
-log = logging.getLogger(__name__)
-log.info(f"GLOBAL_LOG_LEVEL: {GLOBAL_LOG_LEVEL}")
-
-log_sources = [
-    "AUDIO",
-    "COMFYUI",
-    "CONFIG",
-    "DB",
-    "IMAGES",
-    "LITELLM",
-    "MAIN",
-    "MODELS",
-    "OLLAMA",
-    "OPENAI",
-    "RAG",
-    "WEBHOOK",
-]
-
-SRC_LOG_LEVELS = {}
-
-for source in log_sources:
-    log_env_var = source + "_LOG_LEVEL"
-    SRC_LOG_LEVELS[source] = os.environ.get(log_env_var, "").upper()
-    if SRC_LOG_LEVELS[source] not in log_levels:
-        SRC_LOG_LEVELS[source] = GLOBAL_LOG_LEVEL
-    log.info(f"{log_env_var}: {SRC_LOG_LEVELS[source]}")
-
-log.setLevel(SRC_LOG_LEVELS["CONFIG"])
-
-####################################
-# Load .env file
-####################################
-
 try:
     from dotenv import load_dotenv, find_dotenv
 
     load_dotenv(find_dotenv("../.env"))
 except ImportError:
-    log.warning("dotenv not installed, skipping...")
+    print("dotenv not installed, skipping...")
 
-WEBUI_NAME = os.environ.get("WEBUI_NAME", "Open WebUI")
+WEBUI_NAME = "Open WebUI"
-if WEBUI_NAME != "Open WebUI":
+shutil.copyfile("../build/favicon.png", "./static/favicon.png")
-    WEBUI_NAME += " (Open WebUI)"
-
-WEBUI_FAVICON_URL = "https://openwebui.com/favicon.png"
 
 ####################################
 # ENV (dev,test,prod)
@@ -149,6 +99,36 @@ for version in soup.find_all("h2"):
 
 CHANGELOG = changelog_json
 
+
+####################################
+# CUSTOM_NAME
+####################################
+
+CUSTOM_NAME = os.environ.get("CUSTOM_NAME", "")
+if CUSTOM_NAME:
+    try:
+        r = requests.get(f"https://api.openwebui.com/api/v1/custom/{CUSTOM_NAME}")
+        data = r.json()
+        if r.ok:
+            if "logo" in data:
+                url = (
+                    f"https://api.openwebui.com{data['logo']}"
+                    if data["logo"][0] == "/"
+                    else data["logo"]
+                )
+
+                r = requests.get(url, stream=True)
+                if r.status_code == 200:
+                    with open("./static/favicon.png", "wb") as f:
+                        r.raw.decode_content = True
+                        shutil.copyfileobj(r.raw, f)
+
+            WEBUI_NAME = data["name"]
+    except Exception as e:
+        print(e)
+        pass
+
+
 ####################################
 # DATA/FRONTEND BUILD DIR
 ####################################
@@ -162,48 +142,6 @@ try:
 except:
     CONFIG_DATA = {}
 
-####################################
-# Static DIR
-####################################
-
-STATIC_DIR = str(Path(os.getenv("STATIC_DIR", "./static")).resolve())
-
-frontend_favicon = f"{FRONTEND_BUILD_DIR}/favicon.png"
-if os.path.exists(frontend_favicon):
-    shutil.copyfile(frontend_favicon, f"{STATIC_DIR}/favicon.png")
-else:
-    logging.warning(f"Frontend favicon not found at {frontend_favicon}")
-
-####################################
-# CUSTOM_NAME
-####################################
-
-CUSTOM_NAME = os.environ.get("CUSTOM_NAME", "")
-
-if CUSTOM_NAME:
-    try:
-        r = requests.get(f"https://api.openwebui.com/api/v1/custom/{CUSTOM_NAME}")
-        data = r.json()
-        if r.ok:
-            if "logo" in data:
-                WEBUI_FAVICON_URL = url = (
-                    f"https://api.openwebui.com{data['logo']}"
-                    if data["logo"][0] == "/"
-                    else data["logo"]
-                )
-
-                r = requests.get(url, stream=True)
-                if r.status_code == 200:
-                    with open(f"{STATIC_DIR}/favicon.png", "wb") as f:
-                        r.raw.decode_content = True
-                        shutil.copyfileobj(r.raw, f)
-
-            WEBUI_NAME = data["name"]
-    except Exception as e:
-        log.exception(e)
-        pass
-
-
 ####################################
 # File Upload DIR
 ####################################
@@ -224,7 +162,7 @@ Path(CACHE_DIR).mkdir(parents=True, exist_ok=True)
 # Docs DIR
 ####################################
 
-DOCS_DIR = os.getenv("DOCS_DIR", f"{DATA_DIR}/docs")
+DOCS_DIR = f"{DATA_DIR}/docs"
 Path(DOCS_DIR).mkdir(parents=True, exist_ok=True)
 
 
@@ -256,9 +194,9 @@ def create_config_file(file_path):
 LITELLM_CONFIG_PATH = f"{DATA_DIR}/litellm/config.yaml"
 
 if not os.path.exists(LITELLM_CONFIG_PATH):
-    log.info("Config file doesn't exist. Creating...")
+    print("Config file doesn't exist. Creating...")
     create_config_file(LITELLM_CONFIG_PATH)
-    log.info("Config file created successfully.")
+    print("Config file created successfully.")
 
 
 ####################################
@@ -270,8 +208,11 @@ OLLAMA_API_BASE_URL = os.environ.get(
 )
 
 OLLAMA_BASE_URL = os.environ.get("OLLAMA_BASE_URL", "")
-K8S_FLAG = os.environ.get("K8S_FLAG", "")
+
-USE_OLLAMA_DOCKER = os.environ.get("USE_OLLAMA_DOCKER", "false")
+if ENV == "prod":
+    if OLLAMA_BASE_URL == "/ollama":
+        OLLAMA_BASE_URL = "http://host.docker.internal:11434"
+
 
 if OLLAMA_BASE_URL == "" and OLLAMA_API_BASE_URL != "":
     OLLAMA_BASE_URL = (
@@ -280,18 +221,6 @@ if OLLAMA_BASE_URL == "" and OLLAMA_API_BASE_URL != "":
         else OLLAMA_API_BASE_URL
     )
 
-if ENV == "prod":
-    if OLLAMA_BASE_URL == "/ollama" and not K8S_FLAG:
-        if USE_OLLAMA_DOCKER.lower() == "true":
-            # if you use all-in-one docker container (Open WebUI + Ollama)
-            # with the docker build arg USE_OLLAMA=true (--build-arg="USE_OLLAMA=true") this only works with http://localhost:11434
-            OLLAMA_BASE_URL = "http://localhost:11434"
-        else:
-            OLLAMA_BASE_URL = "http://host.docker.internal:11434"
-    elif K8S_FLAG:
-        OLLAMA_BASE_URL = "http://ollama-service.open-webui.svc.cluster.local:11434"
-
-
 OLLAMA_BASE_URLS = os.environ.get("OLLAMA_BASE_URLS", "")
 OLLAMA_BASE_URLS = OLLAMA_BASE_URLS if OLLAMA_BASE_URLS != "" else OLLAMA_BASE_URL
 
@@ -305,6 +234,8 @@ OLLAMA_BASE_URLS = [url.strip() for url in OLLAMA_BASE_URLS.split(";")]
 OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "")
 OPENAI_API_BASE_URL = os.environ.get("OPENAI_API_BASE_URL", "")
 
+if OPENAI_API_KEY == "":
+    OPENAI_API_KEY = "none"
 
 if OPENAI_API_BASE_URL == "":
     OPENAI_API_BASE_URL = "https://api.openai.com/v1"
@@ -320,21 +251,7 @@ OPENAI_API_BASE_URLS = (
     OPENAI_API_BASE_URLS if OPENAI_API_BASE_URLS != "" else OPENAI_API_BASE_URL
 )
 
-OPENAI_API_BASE_URLS = [
+OPENAI_API_BASE_URLS = [url.strip() for url in OPENAI_API_BASE_URLS.split(";")]
-    url.strip() if url != "" else "https://api.openai.com/v1"
-    for url in OPENAI_API_BASE_URLS.split(";")
-]
-
-OPENAI_API_KEY = ""
-
-try:
-    OPENAI_API_KEY = OPENAI_API_KEYS[
-        OPENAI_API_BASE_URLS.index("https://api.openai.com/v1")
-    ]
-except:
-    pass
-
-OPENAI_API_BASE_URL = "https://api.openai.com/v1"
 
 
 ####################################
@@ -367,36 +284,13 @@ DEFAULT_PROMPT_SUGGESTIONS = (
             "title": ["Show me a code snippet", "of a website's sticky header"],
             "content": "Show me a code snippet of a website's sticky header in CSS and JavaScript.",
         },
-        {
-            "title": [
-                "Explain options trading",
-                "if I'm familiar with buying and selling stocks",
-            ],
-            "content": "Explain options trading in simple terms if I'm familiar with buying and selling stocks.",
-        },
-        {
-            "title": ["Overcome procrastination", "give me tips"],
-            "content": "Could you start by asking me about instances when I procrastinate the most and then give me some suggestions to overcome it?",
-        },
     ]
 )
 
 
 DEFAULT_USER_ROLE = os.getenv("DEFAULT_USER_ROLE", "pending")
+USER_PERMISSIONS = {"chat": {"deletion": True}}
 
-USER_PERMISSIONS_CHAT_DELETION = (
-    os.environ.get("USER_PERMISSIONS_CHAT_DELETION", "True").lower() == "true"
-)
-
-USER_PERMISSIONS = {"chat": {"deletion": USER_PERMISSIONS_CHAT_DELETION}}
-
-ENABLE_MODEL_FILTER = os.environ.get("ENABLE_MODEL_FILTER", "False").lower() == "true"
-MODEL_FILTER_LIST = os.environ.get("MODEL_FILTER_LIST", "")
-MODEL_FILTER_LIST = [model.strip() for model in MODEL_FILTER_LIST.split(";")]
-
-WEBHOOK_URL = os.environ.get("WEBHOOK_URL", "")
-
-ENABLE_ADMIN_EXPORT = os.environ.get("ENABLE_ADMIN_EXPORT", "True").lower() == "true"
 
 ####################################
 # WEBUI_VERSION
@@ -409,9 +303,6 @@ WEBUI_VERSION = os.environ.get("WEBUI_VERSION", "v1.0.0-alpha.100")
 ####################################
 
 WEBUI_AUTH = True
-WEBUI_AUTH_TRUSTED_EMAIL_HEADER = os.environ.get(
-    "WEBUI_AUTH_TRUSTED_EMAIL_HEADER", None
-)
 
 ####################################
 # WEBUI_SECRET_KEY
@@ -432,87 +323,21 @@ if WEBUI_AUTH and WEBUI_SECRET_KEY == "":
 ####################################
 
 CHROMA_DATA_PATH = f"{DATA_DIR}/vector_db"
-CHROMA_TENANT = os.environ.get("CHROMA_TENANT", chromadb.DEFAULT_TENANT)
+# this uses the model defined in the Dockerfile ENV variable. If you dont use docker or docker based deployments such as k8s, the default embedding model will be used (all-MiniLM-L6-v2)
-CHROMA_DATABASE = os.environ.get("CHROMA_DATABASE", chromadb.DEFAULT_DATABASE)
+RAG_EMBEDDING_MODEL = os.environ.get("RAG_EMBEDDING_MODEL", "all-MiniLM-L6-v2")
-CHROMA_HTTP_HOST = os.environ.get("CHROMA_HTTP_HOST", "")
+# device type ebbeding models - "cpu" (default), "cuda" (nvidia gpu required) or "mps" (apple silicon) - choosing this right can lead to better performance
-CHROMA_HTTP_PORT = int(os.environ.get("CHROMA_HTTP_PORT", "8000"))
+RAG_EMBEDDING_MODEL_DEVICE_TYPE = os.environ.get(
-# Comma-separated list of header=value pairs
+    "RAG_EMBEDDING_MODEL_DEVICE_TYPE", "cpu"
-CHROMA_HTTP_HEADERS = os.environ.get("CHROMA_HTTP_HEADERS", "")
-if CHROMA_HTTP_HEADERS:
-    CHROMA_HTTP_HEADERS = dict(
-        [pair.split("=") for pair in CHROMA_HTTP_HEADERS.split(",")]
-    )
-else:
-    CHROMA_HTTP_HEADERS = None
-CHROMA_HTTP_SSL = os.environ.get("CHROMA_HTTP_SSL", "false").lower() == "true"
-# this uses the model defined in the Dockerfile ENV variable. If you dont use docker or docker based deployments such as k8s, the default embedding model will be used (sentence-transformers/all-MiniLM-L6-v2)
-
-RAG_TOP_K = int(os.environ.get("RAG_TOP_K", "5"))
-RAG_RELEVANCE_THRESHOLD = float(os.environ.get("RAG_RELEVANCE_THRESHOLD", "0.0"))
-
-ENABLE_RAG_HYBRID_SEARCH = (
-    os.environ.get("ENABLE_RAG_HYBRID_SEARCH", "").lower() == "true"
 )
-
+CHROMA_CLIENT = chromadb.PersistentClient(
-RAG_EMBEDDING_ENGINE = os.environ.get("RAG_EMBEDDING_ENGINE", "")
+    path=CHROMA_DATA_PATH,
-
+    settings=Settings(allow_reset=True, anonymized_telemetry=False),
-PDF_EXTRACT_IMAGES = os.environ.get("PDF_EXTRACT_IMAGES", "False").lower() == "true"
-
-RAG_EMBEDDING_MODEL = os.environ.get(
-    "RAG_EMBEDDING_MODEL", "sentence-transformers/all-MiniLM-L6-v2"
 )
-log.info(f"Embedding model set: {RAG_EMBEDDING_MODEL}"),
+CHUNK_SIZE = 1500
+CHUNK_OVERLAP = 100
 
-RAG_EMBEDDING_MODEL_AUTO_UPDATE = (
-    os.environ.get("RAG_EMBEDDING_MODEL_AUTO_UPDATE", "").lower() == "true"
-)
 
-RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE = (
+RAG_TEMPLATE = """Use the following context as your learned knowledge, inside <context></context> XML tags.
-    os.environ.get("RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE", "").lower() == "true"
-)
-
-RAG_RERANKING_MODEL = os.environ.get("RAG_RERANKING_MODEL", "")
-if not RAG_RERANKING_MODEL == "":
-    log.info(f"Reranking model set: {RAG_RERANKING_MODEL}"),
-
-RAG_RERANKING_MODEL_AUTO_UPDATE = (
-    os.environ.get("RAG_RERANKING_MODEL_AUTO_UPDATE", "").lower() == "true"
-)
-
-RAG_RERANKING_MODEL_TRUST_REMOTE_CODE = (
-    os.environ.get("RAG_RERANKING_MODEL_TRUST_REMOTE_CODE", "").lower() == "true"
-)
-
-# device type embedding models - "cpu" (default), "cuda" (nvidia gpu required) or "mps" (apple silicon) - choosing this right can lead to better performance
-USE_CUDA = os.environ.get("USE_CUDA_DOCKER", "false")
-
-if USE_CUDA.lower() == "true":
-    DEVICE_TYPE = "cuda"
-else:
-    DEVICE_TYPE = "cpu"
-
-if CHROMA_HTTP_HOST != "":
-    CHROMA_CLIENT = chromadb.HttpClient(
-        host=CHROMA_HTTP_HOST,
-        port=CHROMA_HTTP_PORT,
-        headers=CHROMA_HTTP_HEADERS,
-        ssl=CHROMA_HTTP_SSL,
-        tenant=CHROMA_TENANT,
-        database=CHROMA_DATABASE,
-        settings=Settings(allow_reset=True, anonymized_telemetry=False),
-    )
-else:
-    CHROMA_CLIENT = chromadb.PersistentClient(
-        path=CHROMA_DATA_PATH,
-        settings=Settings(allow_reset=True, anonymized_telemetry=False),
-        tenant=CHROMA_TENANT,
-        database=CHROMA_DATABASE,
-    )
-
-CHUNK_SIZE = int(os.environ.get("CHUNK_SIZE", "1500"))
-CHUNK_OVERLAP = int(os.environ.get("CHUNK_OVERLAP", "100"))
-
-DEFAULT_RAG_TEMPLATE = """Use the following context as your learned knowledge, inside <context></context> XML tags.
 <context>
     [context]
 </context>
@@ -526,70 +351,16 @@ And answer according to the language of the user's question.
 Given the context information, answer the query.
 Query: [query]"""
 
-RAG_TEMPLATE = os.environ.get("RAG_TEMPLATE", DEFAULT_RAG_TEMPLATE)
-
-RAG_OPENAI_API_BASE_URL = os.getenv("RAG_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL)
-RAG_OPENAI_API_KEY = os.getenv("RAG_OPENAI_API_KEY", OPENAI_API_KEY)
-
-ENABLE_LOCAL_WEB_FETCH = os.getenv("ENABLE_LOCAL_WEB_FETCH", "False").lower() == "true"
-
 ####################################
 # Transcribe
 ####################################
 
 WHISPER_MODEL = os.getenv("WHISPER_MODEL", "base")
 WHISPER_MODEL_DIR = os.getenv("WHISPER_MODEL_DIR", f"{CACHE_DIR}/whisper/models")
-WHISPER_MODEL_AUTO_UPDATE = (
-    os.environ.get("WHISPER_MODEL_AUTO_UPDATE", "").lower() == "true"
-)
 
 
 ####################################
 # Images
 ####################################
 
-IMAGE_GENERATION_ENGINE = os.getenv("IMAGE_GENERATION_ENGINE", "")
-
-ENABLE_IMAGE_GENERATION = (
-    os.environ.get("ENABLE_IMAGE_GENERATION", "").lower() == "true"
-)
 AUTOMATIC1111_BASE_URL = os.getenv("AUTOMATIC1111_BASE_URL", "")
-
-COMFYUI_BASE_URL = os.getenv("COMFYUI_BASE_URL", "")
-
-IMAGES_OPENAI_API_BASE_URL = os.getenv(
-    "IMAGES_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL
-)
-IMAGES_OPENAI_API_KEY = os.getenv("IMAGES_OPENAI_API_KEY", OPENAI_API_KEY)
-
-IMAGE_SIZE = os.getenv("IMAGE_SIZE", "512x512")
-
-IMAGE_STEPS = int(os.getenv("IMAGE_STEPS", 50))
-
-IMAGE_GENERATION_MODEL = os.getenv("IMAGE_GENERATION_MODEL", "")
-
-####################################
-# Audio
-####################################
-
-AUDIO_OPENAI_API_BASE_URL = os.getenv("AUDIO_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL)
-AUDIO_OPENAI_API_KEY = os.getenv("AUDIO_OPENAI_API_KEY", OPENAI_API_KEY)
-
-####################################
-# LiteLLM
-####################################
-
-
-ENABLE_LITELLM = os.environ.get("ENABLE_LITELLM", "True").lower() == "true"
-
-LITELLM_PROXY_PORT = int(os.getenv("LITELLM_PROXY_PORT", "14365"))
-if LITELLM_PROXY_PORT < 0 or LITELLM_PROXY_PORT > 65535:
-    raise ValueError("Invalid port number for LITELLM_PROXY_PORT")
-LITELLM_PROXY_HOST = os.getenv("LITELLM_PROXY_HOST", "127.0.0.1")
-
-
-####################################
-# Database
-####################################
-
-DATABASE_URL = os.environ.get("DATABASE_URL", f"sqlite:///{DATA_DIR}/webui.db")

backend/constants.py

@@ -3,17 +3,6 @@ from enum import Enum
 
 class MESSAGES(str, Enum):
     DEFAULT = lambda msg="": f"{msg if msg else ''}"
-    MODEL_ADDED = lambda model="": f"The model '{model}' has been added successfully."
-    MODEL_DELETED = (
-        lambda model="": f"The model '{model}' has been deleted successfully."
-    )
-
-
-class WEBHOOK_MESSAGES(str, Enum):
-    DEFAULT = lambda msg="": f"{msg if msg else ''}"
-    USER_SIGNUP = lambda username="": (
-        f"New user signed up: {username}" if username else "New user signed up"
-    )
 
 
 class ERROR_MESSAGES(str, Enum):
@@ -24,7 +13,6 @@ class ERROR_MESSAGES(str, Enum):
     ENV_VAR_NOT_FOUND = "Required environment variable not found. Terminating now."
     CREATE_USER_ERROR = "Oops! Something went wrong while creating your account. Please try again later. If the issue persists, contact support for assistance."
     DELETE_USER_ERROR = "Oops! Something went wrong. We encountered an issue while trying to delete the user. Please give it another shot."
-    EMAIL_MISMATCH = "Uh-oh! This email does not match the email your provider is registered with. Please check your email and try again."
     EMAIL_TAKEN = "Uh-oh! This email is already registered. Sign in with your existing account or choose another email to start anew."
     USERNAME_TAKEN = (
         "Uh-oh! This username is already registered. Please choose another username."
@@ -41,7 +29,6 @@ class ERROR_MESSAGES(str, Enum):
     INVALID_PASSWORD = (
         "The password provided is incorrect. Please check for typos and try again."
     )
-    INVALID_TRUSTED_HEADER = "Your provider has not provided a trusted header. Please contact your administrator for assistance."
     UNAUTHORIZED = "401 Unauthorized"
     ACCESS_PROHIBITED = "You do not have permission to access this resource. Please contact your administrator for assistance."
     ACTION_PROHIBITED = (
@@ -59,19 +46,9 @@ class ERROR_MESSAGES(str, Enum):
 
     PANDOC_NOT_INSTALLED = "Pandoc is not installed on the server. Please contact your administrator for assistance."
     INCORRECT_FORMAT = (
-        lambda err="": f"Invalid format. Please use the correct format{err}"
+        lambda err="": f"Invalid format. Please use the correct format{err if err else ''}"
     )
     RATE_LIMIT_EXCEEDED = "API rate limit exceeded"
 
     MODEL_NOT_FOUND = lambda name="": f"Model '{name}' was not found"
-    OPENAI_NOT_FOUND = lambda name="": "OpenAI API was not found"
+    OPENAI_NOT_FOUND = lambda name="": f"OpenAI API was not found"
-    OLLAMA_NOT_FOUND = "WebUI could not connect to Ollama"
-    CREATE_API_KEY_ERROR = "Oops! Something went wrong while creating your API key. Please try again later. If the issue persists, contact support for assistance."
-
-    EMPTY_CONTENT = "The content provided is empty. Please ensure that there is text or data present before proceeding."
-
-    DB_NOT_SQLITE = "This feature is only available when running with SQLite databases."
-
-    INVALID_URL = (
-        "Oops! The URL you provided is invalid. Please double-check and try again."
-    )

backend/data/config.json

@@ -1,36 +1,34 @@
 {
-	"version": 0,
+    "ui": {
-	"ui": {
+        "prompt_suggestions": [
-		"default_locale": "en-US",
+            {
-		"prompt_suggestions": [
+                "title": [
-			{
+                    "Help me study",
-				"title": ["Help me study", "vocabulary for a college entrance exam"],
+                    "vocabulary for a college entrance exam"
-				"content": "Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option."
+                ],
-			},
+                "content": "Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option."
-			{
+            },
-				"title": ["Give me ideas", "for what to do with my kids' art"],
+            {
-				"content": "What are 5 creative things I could do with my kids' art? I don't want to throw them away, but it's also so much clutter."
+                "title": [
-			},
+                    "Give me ideas",
-			{
+                    "for what to do with my kids' art"
-				"title": ["Tell me a fun fact", "about the Roman Empire"],
+                ],
-				"content": "Tell me a random fun fact about the Roman Empire"
+                "content": "What are 5 creative things I could do with my kids' art? I don't want to throw them away, but it's also so much clutter."
-			},
+            },
-			{
+            {
-				"title": ["Show me a code snippet", "of a website's sticky header"],
+                "title": [
-				"content": "Show me a code snippet of a website's sticky header in CSS and JavaScript."
+                    "Tell me a fun fact",
-			},
+                    "about the Roman Empire"
-			{
+                ],
-				"title": ["Explain options trading", "if I'm familiar with buying and selling stocks"],
+                "content": "Tell me a random fun fact about the Roman Empire"
-				"content": "Explain options trading in simple terms if I'm familiar with buying and selling stocks."
+            },
-			},
+            {
-			{
+                "title": [
-				"title": ["Overcome procrastination", "give me tips"],
+                    "Show me a code snippet",
-				"content": "Could you start by asking me about instances when I procrastinate the most and then give me some suggestions to overcome it?"
+                    "of a website's sticky header"
-			},
+                ],
-			{
+                "content": "Show me a code snippet of a website's sticky header in CSS and JavaScript."
-				"title": ["Grammar check", "rewrite it for better readability "],
+            }
-				"content": "Check the following sentence for grammar and clarity: \"[sentence]\". Rewrite it for better readability while maintaining its original meaning."
+        ]
-			}
+    }
-		]
-	}
 }

backend/main.py

@@ -4,8 +4,6 @@ import markdown
 import time
 import os
 import sys
-import logging
-import aiohttp
 import requests
 
 from fastapi import FastAPI, Request, Depends, status
@@ -19,48 +17,22 @@ from starlette.middleware.base import BaseHTTPMiddleware
 
 from apps.ollama.main import app as ollama_app
 from apps.openai.main import app as openai_app
-
+from apps.litellm.main import app as litellm_app, startup as litellm_app_startup
-from apps.litellm.main import (
-    app as litellm_app,
-    start_litellm_background,
-    shutdown_litellm_background,
-)
 from apps.audio.main import app as audio_app
 from apps.images.main import app as images_app
 from apps.rag.main import app as rag_app
 from apps.web.main import app as webui_app
 
-import asyncio
 from pydantic import BaseModel
 from typing import List
 
 
 from utils.utils import get_admin_user
-from apps.rag.utils import rag_messages
+from apps.rag.utils import query_doc, query_collection, rag_template
 
-from config import (
+from config import WEBUI_NAME, ENV, VERSION, CHANGELOG, FRONTEND_BUILD_DIR
-    CONFIG_DATA,
-    WEBUI_NAME,
-    ENV,
-    VERSION,
-    CHANGELOG,
-    FRONTEND_BUILD_DIR,
-    CACHE_DIR,
-    STATIC_DIR,
-    ENABLE_LITELLM,
-    ENABLE_MODEL_FILTER,
-    MODEL_FILTER_LIST,
-    GLOBAL_LOG_LEVEL,
-    SRC_LOG_LEVELS,
-    WEBHOOK_URL,
-    ENABLE_ADMIN_EXPORT,
-)
 from constants import ERROR_MESSAGES
 
-logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
-
 
 class SPAStaticFiles(StaticFiles):
     async def get_response(self, path: str, scope):
@@ -73,37 +45,33 @@ class SPAStaticFiles(StaticFiles):
                 raise ex
 
 
-print(
-    f"""
-  ___                    __        __   _     _   _ ___ 
- / _ \ _ __   ___ _ __   \ \      / /__| |__ | | | |_ _|
-| | | | '_ \ / _ \ '_ \   \ \ /\ / / _ \ '_ \| | | || | 
-| |_| | |_) |  __/ | | |   \ V  V /  __/ |_) | |_| || | 
- \___/| .__/ \___|_| |_|    \_/\_/ \___|_.__/ \___/|___|
-      |_|                                               
-
-      
-v{VERSION} - building the best open-source AI user interface.      
-https://github.com/open-webui/open-webui
-"""
-)
-
 app = FastAPI(docs_url="/docs" if ENV == "dev" else None, redoc_url=None)
 
-app.state.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
+app.state.MODEL_FILTER_ENABLED = False
-app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
+app.state.MODEL_LIST = []
-
-app.state.WEBHOOK_URL = WEBHOOK_URL
 
 origins = ["*"]
 
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.on_event("startup")
+async def on_startup():
+    await litellm_app_startup()
+
 
 class RAGMiddleware(BaseHTTPMiddleware):
     async def dispatch(self, request: Request, call_next):
         if request.method == "POST" and (
             "/api/chat" in request.url.path or "/chat/completions" in request.url.path
         ):
-            log.debug(f"request.url.path: {request.url.path}")
+            print(request.url.path)
 
             # Read the original request body
             body = await request.body()
@@ -115,35 +83,96 @@ class RAGMiddleware(BaseHTTPMiddleware):
             # Example: Add a new key-value pair or modify existing ones
             # data["modified"] = True  # Example modification
             if "docs" in data:
-                data = {**data}
+                docs = data["docs"]
-                data["messages"] = rag_messages(
+                print(docs)
-                    docs=data["docs"],
-                    messages=data["messages"],
-                    template=rag_app.state.RAG_TEMPLATE,
-                    embedding_function=rag_app.state.EMBEDDING_FUNCTION,
-                    k=rag_app.state.TOP_K,
-                    reranking_function=rag_app.state.sentence_transformer_rf,
-                    r=rag_app.state.RELEVANCE_THRESHOLD,
-                    hybrid_search=rag_app.state.ENABLE_RAG_HYBRID_SEARCH,
-                )
-                del data["docs"]
 
-                log.debug(f"data['messages']: {data['messages']}")
+                last_user_message_idx = None
+                for i in range(len(data["messages"]) - 1, -1, -1):
+                    if data["messages"][i]["role"] == "user":
+                        last_user_message_idx = i
+                        break
+
+                user_message = data["messages"][last_user_message_idx]
+
+                if isinstance(user_message["content"], list):
+                    # Handle list content input
+                    content_type = "list"
+                    query = ""
+                    for content_item in user_message["content"]:
+                        if content_item["type"] == "text":
+                            query = content_item["text"]
+                            break
+                elif isinstance(user_message["content"], str):
+                    # Handle text content input
+                    content_type = "text"
+                    query = user_message["content"]
+                else:
+                    # Fallback in case the input does not match expected types
+                    content_type = None
+                    query = ""
+
+                relevant_contexts = []
+
+                for doc in docs:
+                    context = None
+
+                    try:
+                        if doc["type"] == "collection":
+                            context = query_collection(
+                                collection_names=doc["collection_names"],
+                                query=query,
+                                k=rag_app.state.TOP_K,
+                                embedding_function=rag_app.state.sentence_transformer_ef,
+                            )
+                        else:
+                            context = query_doc(
+                                collection_name=doc["collection_name"],
+                                query=query,
+                                k=rag_app.state.TOP_K,
+                                embedding_function=rag_app.state.sentence_transformer_ef,
+                            )
+                    except Exception as e:
+                        print(e)
+                        context = None
+
+                    relevant_contexts.append(context)
+
+                context_string = ""
+                for context in relevant_contexts:
+                    if context:
+                        context_string += " ".join(context["documents"][0]) + "\n"
+
+                ra_content = rag_template(
+                    template=rag_app.state.RAG_TEMPLATE,
+                    context=context_string,
+                    query=query,
+                )
+
+                if content_type == "list":
+                    new_content = []
+                    for content_item in user_message["content"]:
+                        if content_item["type"] == "text":
+                            # Update the text item's content with ra_content
+                            new_content.append({"type": "text", "text": ra_content})
+                        else:
+                            # Keep other types of content as they are
+                            new_content.append(content_item)
+                    new_user_message = {**user_message, "content": new_content}
+                else:
+                    new_user_message = {
+                        **user_message,
+                        "content": ra_content,
+                    }
+
+                data["messages"][last_user_message_idx] = new_user_message
+                del data["docs"]
 
             modified_body_bytes = json.dumps(data).encode("utf-8")
 
-            # Replace the request body with the modified one
+            # Create a new request with the modified body
-            request._body = modified_body_bytes
+            scope = request.scope
-
+            scope["body"] = modified_body_bytes
-            # Set custom header to ensure content-length matches new body length
+            request = Request(scope, receive=lambda: self._receive(modified_body_bytes))
-            request.headers.__dict__["_list"] = [
-                (b"content-length", str(len(modified_body_bytes)).encode("utf-8")),
-                *[
-                    (k, v)
-                    for k, v in request.headers.raw
-                    if k.lower() != b"content-length"
-                ],
-            ]
 
         response = await call_next(request)
         return response
@@ -155,15 +184,6 @@ class RAGMiddleware(BaseHTTPMiddleware):
 app.add_middleware(RAGMiddleware)
 
 
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=origins,
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-
 @app.middleware("http")
 async def check_url(request: Request, call_next):
     start_time = int(time.time())
@@ -174,12 +194,6 @@ async def check_url(request: Request, call_next):
     return response
 
 
-@app.on_event("startup")
-async def on_startup():
-    if ENABLE_LITELLM:
-        asyncio.create_task(start_litellm_background())
-
-
 app.mount("/api/v1", webui_app)
 app.mount("/litellm/api", litellm_app)
 
@@ -193,32 +207,20 @@ app.mount("/rag/api/v1", rag_app)
 
 @app.get("/api/config")
 async def get_app_config():
-    # Checking and Handling the Absence of 'ui' in CONFIG_DATA
 
-    default_locale = "en-US"
-    if "ui" in CONFIG_DATA:
-        default_locale = CONFIG_DATA["ui"].get("default_locale", "en-US")
-
-    # The Rest of the Function Now Uses the Variables Defined Above
     return {
         "status": True,
         "name": WEBUI_NAME,
         "version": VERSION,
-        "default_locale": default_locale,
         "images": images_app.state.ENABLED,
         "default_models": webui_app.state.DEFAULT_MODELS,
         "default_prompt_suggestions": webui_app.state.DEFAULT_PROMPT_SUGGESTIONS,
-        "trusted_header_auth": bool(webui_app.state.AUTH_TRUSTED_EMAIL_HEADER),
-        "admin_export_enabled": ENABLE_ADMIN_EXPORT,
     }
 
 
 @app.get("/api/config/model/filter")
 async def get_model_filter_config(user=Depends(get_admin_user)):
-    return {
+    return {"enabled": app.state.MODEL_FILTER_ENABLED, "models": app.state.MODEL_LIST}
-        "enabled": app.state.ENABLE_MODEL_FILTER,
-        "models": app.state.MODEL_FILTER_LIST,
-    }
 
 
 class ModelFilterConfigForm(BaseModel):
@@ -227,51 +229,25 @@ class ModelFilterConfigForm(BaseModel):
 
 
 @app.post("/api/config/model/filter")
-async def update_model_filter_config(
+async def get_model_filter_config(
     form_data: ModelFilterConfigForm, user=Depends(get_admin_user)
 ):
-    app.state.ENABLE_MODEL_FILTER = form_data.enabled
-    app.state.MODEL_FILTER_LIST = form_data.models
 
-    ollama_app.state.ENABLE_MODEL_FILTER = app.state.ENABLE_MODEL_FILTER
+    app.state.MODEL_FILTER_ENABLED = form_data.enabled
-    ollama_app.state.MODEL_FILTER_LIST = app.state.MODEL_FILTER_LIST
+    app.state.MODEL_LIST = form_data.models
 
-    openai_app.state.ENABLE_MODEL_FILTER = app.state.ENABLE_MODEL_FILTER
+    ollama_app.state.MODEL_FILTER_ENABLED = app.state.MODEL_FILTER_ENABLED
-    openai_app.state.MODEL_FILTER_LIST = app.state.MODEL_FILTER_LIST
+    ollama_app.state.MODEL_LIST = app.state.MODEL_LIST
 
-    litellm_app.state.ENABLE_MODEL_FILTER = app.state.ENABLE_MODEL_FILTER
+    openai_app.state.MODEL_FILTER_ENABLED = app.state.MODEL_FILTER_ENABLED
-    litellm_app.state.MODEL_FILTER_LIST = app.state.MODEL_FILTER_LIST
+    openai_app.state.MODEL_LIST = app.state.MODEL_LIST
 
-    return {
+    return {"enabled": app.state.MODEL_FILTER_ENABLED, "models": app.state.MODEL_LIST}
-        "enabled": app.state.ENABLE_MODEL_FILTER,
-        "models": app.state.MODEL_FILTER_LIST,
-    }
-
-
-@app.get("/api/webhook")
-async def get_webhook_url(user=Depends(get_admin_user)):
-    return {
-        "url": app.state.WEBHOOK_URL,
-    }
-
-
-class UrlForm(BaseModel):
-    url: str
-
-
-@app.post("/api/webhook")
-async def update_webhook_url(form_data: UrlForm, user=Depends(get_admin_user)):
-    app.state.WEBHOOK_URL = form_data.url
-
-    webui_app.state.WEBHOOK_URL = app.state.WEBHOOK_URL
-
-    return {
-        "url": app.state.WEBHOOK_URL,
-    }
 
 
 @app.get("/api/version")
 async def get_app_config():
+
     return {
         "version": VERSION,
     }
@@ -279,58 +255,32 @@ async def get_app_config():
 
 @app.get("/api/changelog")
 async def get_app_changelog():
-    return {key: CHANGELOG[key] for idx, key in enumerate(CHANGELOG) if idx < 5}
+    return CHANGELOG
 
 
 @app.get("/api/version/updates")
 async def get_app_latest_release_version():
     try:
-        async with aiohttp.ClientSession() as session:
+        response = requests.get(
-            async with session.get(
+            f"https://api.github.com/repos/open-webui/open-webui/releases/latest"
-                "https://api.github.com/repos/open-webui/open-webui/releases/latest"
+        )
-            ) as response:
+        response.raise_for_status()
-                response.raise_for_status()
+        latest_version = response.json()["tag_name"]
-                data = await response.json()
-                latest_version = data["tag_name"]
 
-                return {"current": VERSION, "latest": latest_version[1:]}
+        return {"current": VERSION, "latest": latest_version[1:]}
-    except aiohttp.ClientError as e:
+    except Exception as e:
         raise HTTPException(
             status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
             detail=ERROR_MESSAGES.RATE_LIMIT_EXCEEDED,
         )
 
 
-@app.get("/manifest.json")
+app.mount("/static", StaticFiles(directory="static"), name="static")
-async def get_manifest_json():
+app.mount("/cache", StaticFiles(directory="data/cache"), name="cache")
-    return {
-        "name": WEBUI_NAME,
-        "short_name": WEBUI_NAME,
-        "start_url": "/",
-        "display": "standalone",
-        "background_color": "#343541",
-        "theme_color": "#343541",
-        "orientation": "portrait-primary",
-        "icons": [{"src": "/static/logo.png", "type": "image/png", "sizes": "500x500"}],
-    }
 
 
-app.mount("/static", StaticFiles(directory=STATIC_DIR), name="static")
+app.mount(
-app.mount("/cache", StaticFiles(directory=CACHE_DIR), name="cache")
+    "/",
-
+    SPAStaticFiles(directory=FRONTEND_BUILD_DIR, html=True),
-if os.path.exists(FRONTEND_BUILD_DIR):
+    name="spa-static-files",
-    app.mount(
+)
-        "/",
-        SPAStaticFiles(directory=FRONTEND_BUILD_DIR, html=True),
-        name="spa-static-files",
-    )
-else:
-    log.warning(
-        f"Frontend build directory not found at '{FRONTEND_BUILD_DIR}'. Serving API only."
-    )
-
-
-@app.on_event("shutdown")
-async def shutdown_event():
-    if ENABLE_LITELLM:
-        await shutdown_litellm_background()

backend/requirements.txt

@@ -1,62 +1,46 @@
-fastapi==0.109.2
+fastapi
-uvicorn[standard]==0.22.0
+uvicorn[standard]
-pydantic==2.7.1
+pydantic
-python-multipart==0.0.9
+python-multipart
 
-Flask==3.0.3
+flask
-Flask-Cors==4.0.0
+flask_cors
 
-python-socketio==5.11.2
+python-socketio
-python-jose==3.3.0
+python-jose
-passlib[bcrypt]==1.7.4
+passlib[bcrypt]
-uuid==1.30
+uuid
 
-requests==2.31.0
+requests
-aiohttp==3.9.5
+aiohttp
-peewee==3.17.3
+peewee
-peewee-migrate==1.12.2
+bcrypt
-psycopg2-binary==2.9.9
-PyMySQL==1.1.0
-bcrypt==4.1.2
 
-litellm==1.35.28
+litellm
-litellm[proxy]==1.35.28
+apscheduler
+google-generativeai
 
-boto3==1.34.95
+langchain
+langchain-community
+fake_useragent
+chromadb
+sentence_transformers
+pypdf
+docx2txt
+unstructured
+markdown
+pypandoc
+pandas
+openpyxl
+pyxlsb
+xlrd
 
-argon2-cffi==23.1.0
+opencv-python-headless
-APScheduler==3.10.4
+rapidocr-onnxruntime
-google-generativeai==0.5.2
 
-langchain==0.1.16
+faster-whisper
-langchain-community==0.0.34
-langchain-chroma==0.1.0
 
-fake-useragent==1.5.1
+PyJWT
-chromadb==0.4.24
+pyjwt[crypto]
-sentence-transformers==2.7.0
-pypdf==4.2.0
-docx2txt==0.8
-unstructured==0.11.8
-Markdown==3.6
-pypandoc==1.13
-pandas==2.2.2
-openpyxl==3.1.2
-pyxlsb==1.0.10
-xlrd==2.0.1
-validators==0.28.1
 
-opencv-python-headless==4.9.0.80
+black
-rapidocr-onnxruntime==1.2.3
-
-fpdf2==2.7.8
-rank-bm25==0.2.2
-
-faster-whisper==1.0.1
-
-PyJWT==2.8.0
-PyJWT[crypto]==2.8.0
-
-black==24.4.2
-langfuse==2.27.3
-youtube-transcript-api

backend/start.sh

@@ -6,28 +6,17 @@ cd "$SCRIPT_DIR" || exit
 KEY_FILE=.webui_secret_key
 
 PORT="${PORT:-8080}"
-HOST="${HOST:-0.0.0.0}"
 if test "$WEBUI_SECRET_KEY $WEBUI_JWT_SECRET_KEY" = " "; then
-  echo "No WEBUI_SECRET_KEY provided"
+  echo No WEBUI_SECRET_KEY provided
 
   if ! [ -e "$KEY_FILE" ]; then
-    echo "Generating WEBUI_SECRET_KEY"
+    echo Generating WEBUI_SECRET_KEY
     # Generate a random value to use as a WEBUI_SECRET_KEY in case the user didn't provide one.
-    echo $(head -c 12 /dev/random | base64) > "$KEY_FILE"
+    echo $(head -c 12 /dev/random | base64) > $KEY_FILE
   fi
 
-  echo "Loading WEBUI_SECRET_KEY from $KEY_FILE"
+  echo Loading WEBUI_SECRET_KEY from $KEY_FILE
-  WEBUI_SECRET_KEY=$(cat "$KEY_FILE")
+  WEBUI_SECRET_KEY=`cat $KEY_FILE`
 fi
 
-if [ "$USE_OLLAMA_DOCKER" = "true" ]; then
+WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec uvicorn main:app --host 0.0.0.0 --port "$PORT" --forwarded-allow-ips '*'
-    echo "USE_OLLAMA is set to true, starting ollama serve."
-    ollama serve &
-fi
-
-if [ "$USE_CUDA_DOCKER" = "true" ]; then
-  echo "CUDA is enabled, appending LD_LIBRARY_PATH to include torch/cudnn & cublas libraries."
-  export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/python3.11/site-packages/torch/lib:/usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib"
-fi
-
-WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec uvicorn main:app --host "$HOST" --port "$PORT" --forwarded-allow-ips '*'

backend/start_windows.bat

@@ -7,7 +7,7 @@ SET "SCRIPT_DIR=%~dp0"
 cd /d "%SCRIPT_DIR%" || exit /b
 
 SET "KEY_FILE=.webui_secret_key"
-IF "%PORT%"=="" SET PORT=8080
+SET "PORT=%PORT:8080%"
 SET "WEBUI_SECRET_KEY=%WEBUI_SECRET_KEY%"
 SET "WEBUI_JWT_SECRET_KEY=%WEBUI_JWT_SECRET_KEY%"
 

backend/static/user-import.csv

@@ -1 +0,0 @@
-Name,Email,Password,Role

backend/utils/utils.py

@@ -1,8 +1,6 @@
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
 from fastapi import HTTPException, status, Depends
-
 from apps.web.models.users import Users
-
 from pydantic import BaseModel
 from typing import Union, Optional
 from constants import ERROR_MESSAGES
@@ -10,7 +8,6 @@ from passlib.context import CryptContext
 from datetime import datetime, timedelta
 import requests
 import jwt
-import uuid
 import logging
 import config
 
@@ -61,11 +58,6 @@ def extract_token_from_auth_header(auth_header: str):
     return auth_header[len("Bearer ") :]
 
 
-def create_api_key():
-    key = str(uuid.uuid4()).replace("-", "")
-    return f"sk-{key}"
-
-
 def get_http_authorization_cred(auth_header: str):
     try:
         scheme, credentials = auth_header.split(" ")
@@ -77,10 +69,6 @@ def get_http_authorization_cred(auth_header: str):
 def get_current_user(
     auth_token: HTTPAuthorizationCredentials = Depends(bearer_security),
 ):
-    # auth by api key
-    if auth_token.credentials.startswith("sk-"):
-        return get_current_user_by_api_key(auth_token.credentials)
-    # auth by jwt token
     data = decode_token(auth_token.credentials)
     if data != None and "id" in data:
         user = Users.get_user_by_id(data["id"])
@@ -89,8 +77,6 @@ def get_current_user(
                 status_code=status.HTTP_401_UNAUTHORIZED,
                 detail=ERROR_MESSAGES.INVALID_TOKEN,
             )
-        else:
-            Users.update_user_last_active_by_id(user.id)
         return user
     else:
         raise HTTPException(
@@ -99,20 +85,6 @@ def get_current_user(
         )
 
 
-def get_current_user_by_api_key(api_key: str):
-    user = Users.get_user_by_api_key(api_key)
-
-    if user is None:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.INVALID_TOKEN,
-        )
-    else:
-        Users.update_user_last_active_by_id(user.id)
-
-    return user
-
-
 def get_verified_user(user=Depends(get_current_user)):
     if user.role not in {"user", "admin"}:
         raise HTTPException(

backend/utils/webhook.py

@@ -1,54 +0,0 @@
-import json
-import requests
-import logging
-
-from config import SRC_LOG_LEVELS, VERSION, WEBUI_FAVICON_URL, WEBUI_NAME
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["WEBHOOK"])
-
-
-def post_webhook(url: str, message: str, event_data: dict) -> bool:
-    try:
-        payload = {}
-
-        # Slack and Google Chat Webhooks
-        if "https://hooks.slack.com" in url or "https://chat.googleapis.com" in url:
-            payload["text"] = message
-        # Discord Webhooks
-        elif "https://discord.com/api/webhooks" in url:
-            payload["content"] = message
-        # Microsoft Teams Webhooks
-        elif "webhook.office.com" in url:
-            action = event_data.get("action", "undefined")
-            facts = [
-                {"name": name, "value": value}
-                for name, value in json.loads(event_data.get("user", {})).items()
-            ]
-            payload = {
-                "@type": "MessageCard",
-                "@context": "http://schema.org/extensions",
-                "themeColor": "0076D7",
-                "summary": message,
-                "sections": [
-                    {
-                        "activityTitle": message,
-                        "activitySubtitle": f"{WEBUI_NAME} ({VERSION}) - {action}",
-                        "activityImage": WEBUI_FAVICON_URL,
-                        "facts": facts,
-                        "markdown": True,
-                    }
-                ],
-            }
-        # Default Payload
-        else:
-            payload = {**event_data}
-
-        log.debug(f"payload: {payload}")
-        r = requests.post(url, json=payload)
-        r.raise_for_status()
-        log.debug(f"r.text: {r.text}")
-        return True
-    except Exception as e:
-        log.exception(e)
-        return False

confirm_remove.sh

@@ -2,12 +2,7 @@
 echo "Warning: This will remove all containers and volumes, including persistent data. Do you want to continue? [Y/N]"
 read ans
 if [ "$ans" == "Y" ] || [ "$ans" == "y" ]; then
-  command docker-compose 2>/dev/null
+  docker-compose down -v
-  if [ "$?" == "0" ]; then
-    docker-compose down -v
-  else
-    docker compose down -v
-  fi
 else
   echo "Operation cancelled."
 fi

cypress.config.ts

@@ -1,8 +0,0 @@
-import { defineConfig } from 'cypress';
-
-export default defineConfig({
-	e2e: {
-		baseUrl: 'http://localhost:8080'
-	},
-	video: true
-});

cypress/e2e/chat.cy.ts

@@ -1,46 +0,0 @@
-// eslint-disable-next-line @typescript-eslint/triple-slash-reference
-/// <reference path="../support/index.d.ts" />
-
-// These tests run through the chat flow.
-describe('Settings', () => {
-	// Wait for 2 seconds after all tests to fix an issue with Cypress's video recording missing the last few frames
-	after(() => {
-		// eslint-disable-next-line cypress/no-unnecessary-waiting
-		cy.wait(2000);
-	});
-
-	beforeEach(() => {
-		// Login as the admin user
-		cy.loginAdmin();
-		// Visit the home page
-		cy.visit('/');
-	});
-
-	context('Ollama', () => {
-		it('user can select a model', () => {
-			// Click on the model selector
-			cy.get('button[aria-label="Select a model"]').click();
-			// Select the first model
-			cy.get('button[aria-label="model-item"]').first().click();
-		});
-
-		it('user can perform text chat', () => {
-			// Click on the model selector
-			cy.get('button[aria-label="Select a model"]').click();
-			// Select the first model
-			cy.get('button[aria-label="model-item"]').first().click();
-			// Type a message
-			cy.get('#chat-textarea').type('Hi, what can you do? A single sentence only please.', {
-				force: true
-			});
-			// Send the message
-			cy.get('button[type="submit"]').click();
-			// User's message should be visible
-			cy.get('.chat-user').should('exist');
-			// Wait for the response
-			cy.get('.chat-assistant', { timeout: 120_000 }) // .chat-assistant is created after the first token is received
-				.find('div[aria-label="Generation Info"]', { timeout: 120_000 }) // Generation Info is created after the stop token is received
-				.should('exist');
-		});
-	});
-});

cypress/e2e/registration.cy.ts

@@ -1,52 +0,0 @@
-// eslint-disable-next-line @typescript-eslint/triple-slash-reference
-/// <reference path="../support/index.d.ts" />
-import { adminUser } from '../support/e2e';
-
-// These tests assume the following defaults:
-// 1. No users exist in the database or that the test admin user is an admin
-// 2. Language is set to English
-// 3. The default role for new users is 'pending'
-describe('Registration and Login', () => {
-	// Wait for 2 seconds after all tests to fix an issue with Cypress's video recording missing the last few frames
-	after(() => {
-		// eslint-disable-next-line cypress/no-unnecessary-waiting
-		cy.wait(2000);
-	});
-
-	beforeEach(() => {
-		cy.visit('/');
-	});
-
-	it('should register a new user as pending', () => {
-		const userName = `Test User - ${Date.now()}`;
-		const userEmail = `cypress-${Date.now()}@example.com`;
-		// Toggle from sign in to sign up
-		cy.contains('Sign up').click();
-		// Fill out the form
-		cy.get('input[autocomplete="name"]').type(userName);
-		cy.get('input[autocomplete="email"]').type(userEmail);
-		cy.get('input[type="password"]').type('password');
-		// Submit the form
-		cy.get('button[type="submit"]').click();
-		// Wait until the user is redirected to the home page
-		cy.contains(userName);
-		// Expect the user to be pending
-		cy.contains('Check Again');
-	});
-
-	it('can login with the admin user', () => {
-		// Fill out the form
-		cy.get('input[autocomplete="email"]').type(adminUser.email);
-		cy.get('input[type="password"]').type(adminUser.password);
-		// Submit the form
-		cy.get('button[type="submit"]').click();
-		// Wait until the user is redirected to the home page
-		cy.contains(adminUser.name);
-		// Dismiss the changelog dialog if it is visible
-		cy.getAllLocalStorage().then((ls) => {
-			if (!ls['version']) {
-				cy.get('button').contains("Okay, Let's Go!").click();
-			}
-		});
-	});
-});

cypress/e2e/settings.cy.ts

@@ -1,88 +0,0 @@
-// eslint-disable-next-line @typescript-eslint/triple-slash-reference
-/// <reference path="../support/index.d.ts" />
-import { adminUser } from '../support/e2e';
-
-// These tests run through the various settings pages, ensuring that the user can interact with them as expected
-describe('Settings', () => {
-	// Wait for 2 seconds after all tests to fix an issue with Cypress's video recording missing the last few frames
-	after(() => {
-		// eslint-disable-next-line cypress/no-unnecessary-waiting
-		cy.wait(2000);
-	});
-
-	beforeEach(() => {
-		// Login as the admin user
-		cy.loginAdmin();
-		// Visit the home page
-		cy.visit('/');
-		// Open the sidebar if it is not already open
-		cy.get('[aria-label="Open sidebar"]').then(() => {
-			cy.get('button[id="sidebar-toggle-button"]').click();
-		});
-		// Click on the profile link
-		cy.get('button').contains(adminUser.name).click();
-		// Click on the settings link
-		cy.get('button').contains('Settings').click();
-	});
-
-	context('General', () => {
-		it('user can open the General modal and hit save', () => {
-			cy.get('button').contains('General').click();
-			cy.get('button').contains('Save').click();
-		});
-	});
-
-	context('Connections', () => {
-		it('user can open the Connections modal and hit save', () => {
-			cy.get('button').contains('Connections').click();
-			cy.get('button').contains('Save').click();
-		});
-	});
-
-	context('Models', () => {
-		it('user can open the Models modal', () => {
-			cy.get('button').contains('Models').click();
-		});
-	});
-
-	context('Interface', () => {
-		it('user can open the Interface modal and hit save', () => {
-			cy.get('button').contains('Interface').click();
-			cy.get('button').contains('Save').click();
-		});
-	});
-
-	context('Audio', () => {
-		it('user can open the Audio modal and hit save', () => {
-			cy.get('button').contains('Audio').click();
-			cy.get('button').contains('Save').click();
-		});
-	});
-
-	context('Images', () => {
-		it('user can open the Images modal and hit save', () => {
-			cy.get('button').contains('Images').click();
-			// Currently fails because the backend requires a valid URL
-			// cy.get('button').contains('Save').click();
-		});
-	});
-
-	context('Chats', () => {
-		it('user can open the Chats modal', () => {
-			cy.get('button').contains('Chats').click();
-		});
-	});
-
-	context('Account', () => {
-		it('user can open the Account modal and hit save', () => {
-			cy.get('button').contains('Account').click();
-			cy.get('button').contains('Save').click();
-		});
-	});
-
-	context('About', () => {
-		it('user can open the About modal', () => {
-			cy.get('button').contains('About').click();
-		});
-	});
-});

cypress/support/e2e.ts

@@ -1,73 +0,0 @@
-/// <reference types="cypress" />
-
-export const adminUser = {
-	name: 'Admin User',
-	email: 'admin@example.com',
-	password: 'password'
-};
-
-const login = (email: string, password: string) => {
-	return cy.session(
-		email,
-		() => {
-			// Visit auth page
-			cy.visit('/auth');
-			// Fill out the form
-			cy.get('input[autocomplete="email"]').type(email);
-			cy.get('input[type="password"]').type(password);
-			// Submit the form
-			cy.get('button[type="submit"]').click();
-			// Wait until the user is redirected to the home page
-			cy.get('#chat-search').should('exist');
-			// Get the current version to skip the changelog dialog
-			if (localStorage.getItem('version') === null) {
-				cy.get('button').contains("Okay, Let's Go!").click();
-			}
-		},
-		{
-			validate: () => {
-				cy.request({
-					method: 'GET',
-					url: '/api/v1/auths/',
-					headers: {
-						Authorization: 'Bearer ' + localStorage.getItem('token')
-					}
-				});
-			}
-		}
-	);
-};
-
-const register = (name: string, email: string, password: string) => {
-	return cy
-		.request({
-			method: 'POST',
-			url: '/api/v1/auths/signup',
-			body: {
-				name: name,
-				email: email,
-				password: password
-			},
-			failOnStatusCode: false
-		})
-		.then((response) => {
-			expect(response.status).to.be.oneOf([200, 400]);
-		});
-};
-
-const registerAdmin = () => {
-	return register(adminUser.name, adminUser.email, adminUser.password);
-};
-
-const loginAdmin = () => {
-	return login(adminUser.email, adminUser.password);
-};
-
-Cypress.Commands.add('login', (email, password) => login(email, password));
-Cypress.Commands.add('register', (name, email, password) => register(name, email, password));
-Cypress.Commands.add('registerAdmin', () => registerAdmin());
-Cypress.Commands.add('loginAdmin', () => loginAdmin());
-
-before(() => {
-	cy.registerAdmin();
-});

cypress/support/index.d.ts

@@ -1,11 +0,0 @@
-// load the global Cypress types
-/// <reference types="cypress" />
-
-declare namespace Cypress {
-	interface Chainable {
-		login(email: string, password: string): Chainable<Element>;
-		register(name: string, email: string, password: string): Chainable<Element>;
-		registerAdmin(): Chainable<Element>;
-		loginAdmin(): Chainable<Element>;
-	}
-}

cypress/tsconfig.json

@@ -1,7 +0,0 @@
-{
-	"extends": "../tsconfig.json",
-	"compilerOptions": {
-		"inlineSourceMap": true,
-		"sourceMap": false
-	}
-}

docker-compose.amdgpu.yaml

@@ -1,8 +0,0 @@
-services:
-  ollama:
-    devices:
-      - /dev/kfd:/dev/kfd
-      - /dev/dri:/dev/dri
-    image: ollama/ollama:${OLLAMA_DOCKER_TAG-rocm}
-    environment:
-      - 'HSA_OVERRIDE_GFX_VERSION=${HSA_OVERRIDE_GFX_VERSION-11.0.0}'

docker-compose.yaml

@@ -8,7 +8,7 @@ services:
     pull_policy: always
     tty: true
     restart: unless-stopped
-    image: ollama/ollama:${OLLAMA_DOCKER_TAG-latest}
+    image: ollama/ollama:latest
 
   open-webui:
     build:
@@ -16,7 +16,7 @@ services:
       args:
         OLLAMA_BASE_URL: '/ollama'
       dockerfile: Dockerfile
-    image: ghcr.io/open-webui/open-webui:${WEBUI_DOCKER_TAG-main}
+    image: ghcr.io/open-webui/open-webui:main
     container_name: open-webui
     volumes:
       - open-webui:/app/backend/data

docs/CONTRIBUTING.md

@@ -50,18 +50,6 @@ We welcome pull requests. Before submitting one, please:
 
 Help us make Open WebUI more accessible by improving documentation, writing tutorials, or creating guides on setting up and optimizing the web UI.
 
-### 🌐 Translations and Internationalization
-
-Help us make Open WebUI available to a wider audience. In this section, we'll guide you through the process of adding new translations to the project.
-
-We use JSON files to store translations. You can find the existing translation files in the `src/lib/i18n/locales` directory. Each directory corresponds to a specific language, for example, `en-US` for English (US), `fr-FR` for French (France) and so on. You can refer to [ISO 639 Language Codes][http://www.lingoes.net/en/translator/langcode.htm] to find the appropriate code for a specific language.
-
-To add a new language:
-
-- Create a new directory in the `src/lib/i18n/locales` path with the appropriate language code as its name. For instance, if you're adding translations for Spanish (Spain), create a new directory named `es-ES`.
-- Copy the American English translation file(s) (from `en-US` directory in `src/lib/i18n/locale`) to this new directory and update the string values in JSON format according to your language. Make sure to preserve the structure of the JSON object.
-- Add the language code and its respective title to languages file at `src/lib/i18n/locales/languages.json`.
-
 ### 🤔 Questions & Feedback
 
 Got questions or feedback? Join our [Discord community](https://discord.gg/5rJgQTnV4s) or open an issue. We're here to help!

i18next-parser.config.ts

@@ -1,38 +0,0 @@
-// i18next-parser.config.ts
-import { getLanguages } from './src/lib/i18n/index.ts';
-
-const getLangCodes = async () => {
-	const languages = await getLanguages();
-	return languages.map((l) => l.code);
-};
-
-export default {
-	contextSeparator: '_',
-	createOldCatalogs: false,
-	defaultNamespace: 'translation',
-	defaultValue: '',
-	indentation: 2,
-	keepRemoved: false,
-	keySeparator: false,
-	lexers: {
-		svelte: ['JavascriptLexer'],
-		js: ['JavascriptLexer'],
-		ts: ['JavascriptLexer'],
-
-		default: ['JavascriptLexer']
-	},
-	lineEnding: 'auto',
-	locales: await getLangCodes(),
-	namespaceSeparator: false,
-	output: 'src/lib/i18n/locales/$LOCALE/$NAMESPACE.json',
-	pluralSeparator: '_',
-	input: 'src/**/*.{js,svelte}',
-	sort: true,
-	verbose: true,
-	failOnWarnings: false,
-	failOnUpdate: false,
-	customValueTemplate: null,
-	resetDefaultValueLocale: null,
-	i18nextOptions: null,
-	yamlOptions: null
-};

kubernetes/helm/templates/_helpers.tpl

@@ -7,11 +7,7 @@ ollama
 {{- end -}}
 
 {{- define "ollama.url" -}}
-{{- if .Values.ollama.externalHost }}
+{{- printf "http://%s.%s.svc.cluster.local:%d/api" (include "ollama.name" .) (.Release.Namespace) (.Values.ollama.service.port | int) }}
-{{- printf .Values.ollama.externalHost }}
-{{- else }}
-{{- printf "http://%s.%s.svc.cluster.local:%d" (include "ollama.name" .) (.Release.Namespace) (.Values.ollama.service.port | int) }}
-{{- end }}
 {{- end }}
 
 {{- define "chart.name" -}}

kubernetes/helm/templates/ollama-service.yaml

@@ -1,4 +1,3 @@
-{{- if not .Values.ollama.externalHost }}
 apiVersion: v1
 kind: Service
 metadata:
@@ -20,4 +19,3 @@ spec:
     port: {{ .port }}
     targetPort: http
 {{- end }}
-{{- end }}

kubernetes/helm/templates/ollama-statefulset.yaml

@@ -1,4 +1,3 @@
-{{- if not .Values.ollama.externalHost }}
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
@@ -89,10 +88,9 @@ spec:
       resources:
         requests:
           storage: {{ .Values.ollama.persistence.size | quote }}
-      storageClassName: {{ .Values.ollama.persistence.storageClass }}
+      storageClass: {{ .Values.ollama.persistence.storageClass }}
       {{- with .Values.ollama.persistence.selector }}
       selector:
         {{- toYaml . | nindent 8 }}
       {{- end }}
       {{- end }}
-{{- end }}

kubernetes/helm/templates/webui-pvc.yaml

@@ -17,9 +17,7 @@ spec:
   resources:
     requests:
       storage: {{ .Values.webui.persistence.size }}
-  {{- if .Values.webui.persistence.storageClass }}
+  storageClass: {{ .Values.webui.persistence.storageClass }}
-  storageClassName: {{ .Values.webui.persistence.storageClass }}
-  {{- end }}
   {{- with .Values.webui.persistence.selector }}
   selector:
     {{- toYaml . | nindent 4 }}

kubernetes/helm/templates/webui-service.yaml

@@ -4,9 +4,6 @@ metadata:
   name: {{ include "open-webui.name" . }}
   labels:
     {{- include "open-webui.labels" . | nindent 4 }}
-    {{- with .Values.webui.service.labels }}
-    {{- toYaml . | nindent 4 }}
-    {{- end }}
   {{- with .Values.webui.service.annotations }}
   annotations:
     {{- toYaml . | nindent 4 }}
@@ -14,16 +11,14 @@ metadata:
 spec:
   selector:
     {{- include "open-webui.selectorLabels" . | nindent 4 }}
-  type: {{ .Values.webui.service.type | default "ClusterIP" }}
+{{- with .Values.webui.service }}
+  type: {{ .type }}
   ports:
   - protocol: TCP
     name: http
-    port: {{ .Values.webui.service.port }}
+    port: {{ .port }}
     targetPort: http
-    {{- if .Values.webui.service.nodePort }}
+    {{- if .nodePort }}
-    nodePort: {{ .Values.webui.service.nodePort | int }}
+    nodePort: {{ .nodePort | int }}
     {{- end }}
-  {{- if .Values.webui.service.loadBalancerClass }}
+{{- end }}
-  loadBalancerClass: {{ .Values.webui.service.loadBalancerClass | quote }}
-  {{- end }}
-

kubernetes/helm/values.yaml

@@ -1,7 +1,6 @@
 nameOverride: ""
 
 ollama:
-  externalHost: ""
   annotations: {}
   podAnnotations: {}
   replicaCount: 1
@@ -71,5 +70,3 @@ webui:
     port: 80
     containerPort: 8080
     nodePort: ""
-    labels: {}
-    loadBalancerClass: "" 

kubernetes/manifest/base/webui-deployment.yaml

@@ -35,4 +35,4 @@ spec:
       volumes:
       - name: webui-volume
         persistentVolumeClaim:
-          claimName: open-webui-pvc          
+          claimName: ollama-webui-pvc          

kubernetes/manifest/base/webui-pvc.yaml

@@ -2,8 +2,8 @@ apiVersion: v1
 kind: PersistentVolumeClaim
 metadata:
   labels:
-    app: open-webui
+    app: ollama-webui
-  name: open-webui-pvc
+  name: ollama-webui-pvc
   namespace: open-webui
 spec:
   accessModes: ["ReadWriteOnce"]

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.1.123",
+	"version": "0.1.110",
 	"private": true,
 	"scripts": {
 		"dev": "vite dev --host",
@@ -13,9 +13,7 @@
 		"lint:types": "npm run check",
 		"lint:backend": "pylint backend/",
 		"format": "prettier --plugin-search-dir --write '**/*.{js,ts,svelte,css,md,html,json}'",
-		"format:backend": "black . --exclude \"/venv/\"",
+		"format:backend": "yapf --recursive backend -p -i"
-		"i18n:parse": "i18next --config i18next-parser.config.ts && prettier --write 'src/lib/i18n/**/*.{js,json}'",
-		"cy:open": "cypress open"
 	},
 	"devDependencies": {
 		"@sveltejs/adapter-auto": "^2.0.0",
@@ -26,12 +24,9 @@
 		"@typescript-eslint/eslint-plugin": "^6.17.0",
 		"@typescript-eslint/parser": "^6.17.0",
 		"autoprefixer": "^10.4.16",
-		"cypress": "^13.8.1",
 		"eslint": "^8.56.0",
 		"eslint-config-prettier": "^8.5.0",
-		"eslint-plugin-cypress": "^3.0.2",
 		"eslint-plugin-svelte": "^2.30.0",
-		"i18next-parser": "^8.13.0",
 		"postcss": "^8.4.31",
 		"prettier": "^2.8.0",
 		"prettier-plugin-svelte": "^2.10.1",
@@ -47,14 +42,9 @@
 	"dependencies": {
 		"@sveltejs/adapter-node": "^1.3.1",
 		"async": "^3.2.5",
-		"bits-ui": "^0.19.7",
 		"dayjs": "^1.11.10",
-		"eventsource-parser": "^1.1.2",
 		"file-saver": "^2.0.5",
 		"highlight.js": "^11.9.0",
-		"i18next": "^23.10.0",
-		"i18next-browser-languagedetector": "^7.2.0",
-		"i18next-resources-to-backend": "^1.2.0",
 		"idb": "^7.1.1",
 		"js-sha256": "^0.10.1",
 		"katex": "^0.16.9",

run-compose.sh

@@ -82,7 +82,6 @@ usage() {
     echo "Examples:"
     echo "  $0 --drop"
     echo "  $0 --enable-gpu[count=1]"
-    echo "  $0 --enable-gpu[count=all]"
     echo "  $0 --enable-api[port=11435]"
     echo "  $0 --enable-gpu[count=1] --enable-api[port=12345] --webui[port=3000]"
     echo "  $0 --enable-gpu[count=1] --enable-api[port=12345] --webui[port=3000] --data[folder=./ollama-data]"
@@ -161,7 +160,7 @@ else
     if [[ $enable_gpu == true ]]; then
         # Validate and process command-line arguments
         if [[ -n $gpu_count ]]; then
-            if ! [[ $gpu_count =~ ^([0-9]+|all)$ ]]; then
+            if ! [[ $gpu_count =~ ^[0-9]+$ ]]; then
                 echo "Invalid GPU count: $gpu_count"
                 exit 1
             fi

src/app.css

@@ -78,7 +78,3 @@ select {
 	/* for Chrome */
 	-webkit-appearance: none;
 }
-
-.katex-mathml {
-	display: none;
-}

src/app.html

@@ -3,86 +3,28 @@
 	<head>
 		<meta charset="utf-8" />
 		<link rel="icon" href="%sveltekit.assets%/favicon.png" />
-		<link rel="manifest" href="%sveltekit.assets%/manifest.json" crossorigin="use-credentials" />
+		<link rel="manifest" href="%sveltekit.assets%/manifest.json" />
 		<meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1" />
 		<meta name="robots" content="noindex,nofollow" />
 		<script>
 			// On page load or when changing themes, best to add inline in `head` to avoid FOUC
-			(() => {
+			if (
-				if (localStorage?.theme && localStorage?.theme.includes('oled')) {
+				localStorage.theme === 'light' ||
-					document.documentElement.style.setProperty('--color-gray-900', '#000000');
+				(!('theme' in localStorage) && window.matchMedia('(prefers-color-scheme: light)').matches)
-					document.documentElement.style.setProperty('--color-gray-950', '#000000');
+			) {
-					document.documentElement.classList.add('dark');
+				document.documentElement.classList.add('light');
-				} else if (
+			} else if (localStorage.theme) {
-					localStorage.theme === 'light' ||
+				localStorage.theme.split(' ').forEach((e) => {
-					(!('theme' in localStorage) && window.matchMedia('(prefers-color-scheme: light)').matches)
+					document.documentElement.classList.add(e);
-				) {
-					document.documentElement.classList.add('light');
-				} else if (localStorage.theme && localStorage.theme !== 'system') {
-					localStorage.theme.split(' ').forEach((e) => {
-						document.documentElement.classList.add(e);
-					});
-				} else if (localStorage.theme && localStorage.theme === 'system') {
-					systemTheme = window.matchMedia('(prefers-color-scheme: dark)').matches;
-					document.documentElement.classList.add(systemTheme ? 'dark' : 'light');
-				} else {
-					document.documentElement.classList.add('dark');
-				}
-
-				window.matchMedia('(prefers-color-scheme: dark)').addListener((e) => {
-					if (localStorage.theme === 'system') {
-						if (e.matches) {
-							document.documentElement.classList.add('dark');
-							document.documentElement.classList.remove('light');
-						} else {
-							document.documentElement.classList.add('light');
-							document.documentElement.classList.remove('dark');
-						}
-					}
 				});
-			})();
+			} else {
+				document.documentElement.classList.add('dark');
+			}
 		</script>
 
-		<title>Open WebUI</title>
-
 		%sveltekit.head%
 	</head>
 	<body data-sveltekit-preload-data="hover">
 		<div style="display: contents">%sveltekit.body%</div>
-
-		<div
-			id="splash-screen"
-			style="
-				position: fixed;
-				z-index: 100;
-				background: #fff;
-				top: 0;
-				left: 0;
-				width: 100%;
-				height: 100%;
-			"
-		>
-			<style type="text/css" nonce="">
-				html {
-					overflow-y: scroll !important;
-				}
-			</style>
-
-			<img
-				style="
-					position: absolute;
-					width: 6rem;
-					height: 6rem;
-					top: 46%;
-					left: 50%;
-					margin: -40px 0 0 -40px;
-				"
-				src="/logo.svg"
-			/>
-
-			<!-- <span style="position: absolute; bottom: 32px; left: 50%; margin: -36px 0 0 -36px">
-				Footer content
-			</span> -->
-		</div>
 	</body>
 </html>

src/lib/apis/audio/index.ts

@@ -1,73 +1,11 @@
 import { AUDIO_API_BASE_URL } from '$lib/constants';
 
-export const getAudioConfig = async (token: string) => {
-	let error = null;
-
-	const res = await fetch(`${AUDIO_API_BASE_URL}/config`, {
-		method: 'GET',
-		headers: {
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = err.detail;
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
-type OpenAIConfigForm = {
-	url: string;
-	key: string;
-};
-
-export const updateAudioConfig = async (token: string, payload: OpenAIConfigForm) => {
-	let error = null;
-
-	const res = await fetch(`${AUDIO_API_BASE_URL}/config/update`, {
-		method: 'POST',
-		headers: {
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			...payload
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = err.detail;
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
 export const transcribeAudio = async (token: string, file: File) => {
 	const data = new FormData();
 	data.append('file', file);
 
 	let error = null;
-	const res = await fetch(`${AUDIO_API_BASE_URL}/transcriptions`, {
+	const res = await fetch(`${AUDIO_API_BASE_URL}/transcribe`, {
 		method: 'POST',
 		headers: {
 			Accept: 'application/json',
@@ -91,40 +29,3 @@ export const transcribeAudio = async (token: string, file: File) => {
 
 	return res;
 };
-
-export const synthesizeOpenAISpeech = async (
-	token: string = '',
-	speaker: string = 'alloy',
-	text: string = ''
-) => {
-	let error = null;
-
-	const res = await fetch(`${AUDIO_API_BASE_URL}/speech`, {
-		method: 'POST',
-		headers: {
-			Authorization: `Bearer ${token}`,
-			'Content-Type': 'application/json'
-		},
-		body: JSON.stringify({
-			model: 'tts-1',
-			input: text,
-			voice: speaker
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res;
-		})
-		.catch((err) => {
-			error = err.detail;
-			console.log(err);
-
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};

src/lib/apis/auths/index.ts

@@ -58,12 +58,7 @@ export const userSignIn = async (email: string, password: string) => {
 	return res;
 };
 
-export const userSignUp = async (
+export const userSignUp = async (name: string, email: string, password: string) => {
-	name: string,
-	email: string,
-	password: string,
-	profile_image_url: string
-) => {
 	let error = null;
 
 	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/signup`, {
@@ -74,47 +69,7 @@ export const userSignUp = async (
 		body: JSON.stringify({
 			name: name,
 			email: email,
-			password: password,
+			password: password
-			profile_image_url: profile_image_url
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = err.detail;
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
-export const addUser = async (
-	token: string,
-	name: string,
-	email: string,
-	password: string,
-	role: string = 'pending'
-) => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/add`, {
-		method: 'POST',
-		headers: {
-			'Content-Type': 'application/json',
-			...(token && { authorization: `Bearer ${token}` })
-		},
-		body: JSON.stringify({
-			name: name,
-			email: email,
-			password: password,
-			role: role
 		})
 	})
 		.then(async (res) => {
@@ -363,78 +318,3 @@ export const updateJWTExpiresDuration = async (token: string, duration: string)
 
 	return res;
 };
-
-export const createAPIKey = async (token: string) => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/api_key`, {
-		method: 'POST',
-		headers: {
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = err.detail;
-			return null;
-		});
-	if (error) {
-		throw error;
-	}
-	return res.api_key;
-};
-
-export const getAPIKey = async (token: string) => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/api_key`, {
-		method: 'GET',
-		headers: {
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = err.detail;
-			return null;
-		});
-	if (error) {
-		throw error;
-	}
-	return res.api_key;
-};
-
-export const deleteAPIKey = async (token: string) => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/api_key`, {
-		method: 'DELETE',
-		headers: {
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = err.detail;
-			return null;
-		});
-	if (error) {
-		throw error;
-	}
-	return res;
-};

src/lib/apis/chats/index.ts

@@ -62,68 +62,6 @@ export const getChatList = async (token: string = '') => {
 	return res;
 };
 
-export const getChatListByUserId = async (token: string = '', userId: string) => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/list/user/${userId}`, {
-		method: 'GET',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			...(token && { authorization: `Bearer ${token}` })
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.then((json) => {
-			return json;
-		})
-		.catch((err) => {
-			error = err;
-			console.log(err);
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
-export const getArchivedChatList = async (token: string = '') => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/archived`, {
-		method: 'GET',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			...(token && { authorization: `Bearer ${token}` })
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.then((json) => {
-			return json;
-		})
-		.catch((err) => {
-			error = err;
-			console.log(err);
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
 export const getAllChats = async (token: string) => {
 	let error = null;
 
@@ -280,134 +218,6 @@ export const getChatById = async (token: string, id: string) => {
 	return res;
 };
 
-export const getChatByShareId = async (token: string, share_id: string) => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/share/${share_id}`, {
-		method: 'GET',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			...(token && { authorization: `Bearer ${token}` })
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.then((json) => {
-			return json;
-		})
-		.catch((err) => {
-			error = err;
-
-			console.log(err);
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
-export const shareChatById = async (token: string, id: string) => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/share`, {
-		method: 'POST',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			...(token && { authorization: `Bearer ${token}` })
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.then((json) => {
-			return json;
-		})
-		.catch((err) => {
-			error = err;
-
-			console.log(err);
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
-export const archiveChatById = async (token: string, id: string) => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/archive`, {
-		method: 'GET',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			...(token && { authorization: `Bearer ${token}` })
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.then((json) => {
-			return json;
-		})
-		.catch((err) => {
-			error = err;
-
-			console.log(err);
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
-export const deleteSharedChatById = async (token: string, id: string) => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/share`, {
-		method: 'DELETE',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			...(token && { authorization: `Bearer ${token}` })
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.then((json) => {
-			return json;
-		})
-		.catch((err) => {
-			error = err;
-
-			console.log(err);
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
 export const updateChatById = async (token: string, id: string, chat: object) => {
 	let error = null;
 

src/lib/apis/images/index.ts

@@ -72,10 +72,10 @@ export const updateImageGenerationConfig = async (
 	return res;
 };
 
-export const getOpenAIConfig = async (token: string = '') => {
+export const getOpenAIKey = async (token: string = '') => {
 	let error = null;
 
-	const res = await fetch(`${IMAGES_API_BASE_URL}/openai/config`, {
+	const res = await fetch(`${IMAGES_API_BASE_URL}/key`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -101,13 +101,13 @@ export const getOpenAIConfig = async (token: string = '') => {
 		throw error;
 	}
 
-	return res;
+	return res.OPENAI_API_KEY;
 };
 
-export const updateOpenAIConfig = async (token: string = '', url: string, key: string) => {
+export const updateOpenAIKey = async (token: string = '', key: string) => {
 	let error = null;
 
-	const res = await fetch(`${IMAGES_API_BASE_URL}/openai/config/update`, {
+	const res = await fetch(`${IMAGES_API_BASE_URL}/key/update`, {
 		method: 'POST',
 		headers: {
 			Accept: 'application/json',
@@ -115,7 +115,6 @@ export const updateOpenAIConfig = async (token: string = '', url: string, key: s
 			...(token && { authorization: `Bearer ${token}` })
 		},
 		body: JSON.stringify({
-			url: url,
 			key: key
 		})
 	})
@@ -137,10 +136,10 @@ export const updateOpenAIConfig = async (token: string = '', url: string, key: s
 		throw error;
 	}
 
-	return res;
+	return res.OPENAI_API_KEY;
 };
 
-export const getImageGenerationEngineUrls = async (token: string = '') => {
+export const getAUTOMATIC1111Url = async (token: string = '') => {
 	let error = null;
 
 	const res = await fetch(`${IMAGES_API_BASE_URL}/url`, {
@@ -169,10 +168,10 @@ export const getImageGenerationEngineUrls = async (token: string = '') => {
 		throw error;
 	}
 
-	return res;
+	return res.AUTOMATIC1111_BASE_URL;
 };
 
-export const updateImageGenerationEngineUrls = async (token: string = '', urls: object = {}) => {
+export const updateAUTOMATIC1111Url = async (token: string = '', url: string) => {
 	let error = null;
 
 	const res = await fetch(`${IMAGES_API_BASE_URL}/url/update`, {
@@ -183,7 +182,7 @@ export const updateImageGenerationEngineUrls = async (token: string = '', urls:
 			...(token && { authorization: `Bearer ${token}` })
 		},
 		body: JSON.stringify({
-			...urls
+			url: url
 		})
 	})
 		.then(async (res) => {
@@ -204,7 +203,7 @@ export const updateImageGenerationEngineUrls = async (token: string = '', urls:
 		throw error;
 	}
 
-	return res;
+	return res.AUTOMATIC1111_BASE_URL;
 };
 
 export const getImageSize = async (token: string = '') => {

src/lib/apis/index.ts

@@ -139,60 +139,3 @@ export const updateModelFilterConfig = async (
 
 	return res;
 };
-
-export const getWebhookUrl = async (token: string) => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_BASE_URL}/api/webhook`, {
-		method: 'GET',
-		headers: {
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = err;
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res.url;
-};
-
-export const updateWebhookUrl = async (token: string, url: string) => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_BASE_URL}/api/webhook`, {
-		method: 'POST',
-		headers: {
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			url: url
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = err;
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res.url;
-};

src/lib/apis/litellm/index.ts

@@ -33,7 +33,7 @@ export const getLiteLLMModels = async (token: string = '') => {
 					id: model.id,
 					name: model.name ?? model.id,
 					external: true,
-					source: 'LiteLLM'
+					source: 'litellm'
 				}))
 				.sort((a, b) => {
 					return a.name.localeCompare(b.name);

src/lib/apis/ollama/index.ts

@@ -1,5 +1,4 @@
 import { OLLAMA_API_BASE_URL } from '$lib/constants';
-import { promptTemplate } from '$lib/utils';
 
 export const getOllamaUrls = async (token: string = '') => {
 	let error = null;
@@ -145,7 +144,7 @@ export const generateTitle = async (
 ) => {
 	let error = null;
 
-	template = promptTemplate(template, prompt);
+	template = template.replace(/{{prompt}}/g, prompt);
 
 	console.log(template);
 
@@ -220,32 +219,6 @@ export const generatePrompt = async (token: string = '', model: string, conversa
 	return res;
 };
 
-export const generateEmbeddings = async (token: string = '', model: string, text: string) => {
-	let error = null;
-
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/embeddings`, {
-		method: 'POST',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			model: model,
-			prompt: text
-		})
-	}).catch((err) => {
-		error = err;
-		return null;
-	});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
 export const generateTextCompletion = async (token: string = '', model: string, text: string) => {
 	let error = null;
 
@@ -298,7 +271,7 @@ export const generateChatCompletion = async (token: string = '', body: object) =
 	return [res, controller];
 };
 
-export const cancelOllamaRequest = async (token: string = '', requestId: string) => {
+export const cancelChatCompletion = async (token: string = '', requestId: string) => {
 	let error = null;
 
 	const res = await fetch(`${OLLAMA_API_BASE_URL}/cancel/${requestId}`, {
@@ -417,73 +390,6 @@ export const pullModel = async (token: string, tagName: string, urlIdx: string |
 	return res;
 };
 
-export const downloadModel = async (
-	token: string,
-	download_url: string,
-	urlIdx: string | null = null
-) => {
-	let error = null;
-
-	const res = await fetch(
-		`${OLLAMA_API_BASE_URL}/models/download${urlIdx !== null ? `/${urlIdx}` : ''}`,
-		{
-			method: 'POST',
-			headers: {
-				Accept: 'application/json',
-				'Content-Type': 'application/json',
-				Authorization: `Bearer ${token}`
-			},
-			body: JSON.stringify({
-				url: download_url
-			})
-		}
-	).catch((err) => {
-		console.log(err);
-		error = err;
-
-		if ('detail' in err) {
-			error = err.detail;
-		}
-
-		return null;
-	});
-	if (error) {
-		throw error;
-	}
-	return res;
-};
-
-export const uploadModel = async (token: string, file: File, urlIdx: string | null = null) => {
-	let error = null;
-
-	const formData = new FormData();
-	formData.append('file', file);
-
-	const res = await fetch(
-		`${OLLAMA_API_BASE_URL}/models/upload${urlIdx !== null ? `/${urlIdx}` : ''}`,
-		{
-			method: 'POST',
-			headers: {
-				Authorization: `Bearer ${token}`
-			},
-			body: formData
-		}
-	).catch((err) => {
-		console.log(err);
-		error = err;
-
-		if ('detail' in err) {
-			error = err.detail;
-		}
-
-		return null;
-	});
-	if (error) {
-		throw error;
-	}
-	return res;
-};
-
 // export const pullModel = async (token: string, tagName: string) => {
 // 	return await fetch(`${OLLAMA_API_BASE_URL}/pull`, {
 // 		method: 'POST',

src/lib/apis/openai/index.ts

@@ -1,5 +1,4 @@
 import { OPENAI_API_BASE_URL } from '$lib/constants';
-import { promptTemplate } from '$lib/utils';
 
 export const getOpenAIUrls = async (token: string = '') => {
 	let error = null;
@@ -211,12 +210,10 @@ export const generateOpenAIChatCompletion = async (
 	token: string = '',
 	body: object,
 	url: string = OPENAI_API_BASE_URL
-): Promise<[Response | null, AbortController]> => {
+) => {
-	const controller = new AbortController();
 	let error = null;
 
 	const res = await fetch(`${url}/chat/completions`, {
-		signal: controller.signal,
 		method: 'POST',
 		headers: {
 			Authorization: `Bearer ${token}`,
@@ -233,7 +230,7 @@ export const generateOpenAIChatCompletion = async (
 		throw error;
 	}
 
-	return [res, controller];
+	return res;
 };
 
 export const synthesizeOpenAISpeech = async (
@@ -266,53 +263,3 @@ export const synthesizeOpenAISpeech = async (
 
 	return res;
 };
-
-export const generateTitle = async (
-	token: string = '',
-	template: string,
-	model: string,
-	prompt: string,
-	url: string = OPENAI_API_BASE_URL
-) => {
-	let error = null;
-
-	template = promptTemplate(template, prompt);
-
-	console.log(template);
-
-	const res = await fetch(`${url}/chat/completions`, {
-		method: 'POST',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			model: model,
-			messages: [
-				{
-					role: 'user',
-					content: template
-				}
-			],
-			stream: false
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			if ('detail' in err) {
-				error = err.detail;
-			}
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res?.choices[0]?.message?.content ?? 'New Chat';
-};

src/lib/apis/rag/index.ts

@@ -1,9 +1,9 @@
 import { RAG_API_BASE_URL } from '$lib/constants';
 
-export const getRAGConfig = async (token: string) => {
+export const getChunkParams = async (token: string) => {
 	let error = null;
 
-	const res = await fetch(`${RAG_API_BASE_URL}/config`, {
+	const res = await fetch(`${RAG_API_BASE_URL}/chunk`, {
 		method: 'GET',
 		headers: {
 			'Content-Type': 'application/json',
@@ -27,27 +27,18 @@ export const getRAGConfig = async (token: string) => {
 	return res;
 };
 
-type ChunkConfigForm = {
+export const updateChunkParams = async (token: string, size: number, overlap: number) => {
-	chunk_size: number;
-	chunk_overlap: number;
-};
-
-type RAGConfigForm = {
-	pdf_extract_images: boolean;
-	chunk: ChunkConfigForm;
-};
-
-export const updateRAGConfig = async (token: string, payload: RAGConfigForm) => {
 	let error = null;
 
-	const res = await fetch(`${RAG_API_BASE_URL}/config/update`, {
+	const res = await fetch(`${RAG_API_BASE_URL}/chunk/update`, {
 		method: 'POST',
 		headers: {
 			'Content-Type': 'application/json',
 			Authorization: `Bearer ${token}`
 		},
 		body: JSON.stringify({
-			...payload
+			chunk_size: size,
+			chunk_overlap: overlap
 		})
 	})
 		.then(async (res) => {
@@ -123,7 +114,6 @@ export const getQuerySettings = async (token: string) => {
 
 type QuerySettings = {
 	k: number | null;
-	r: number | null;
 	template: string | null;
 };
 
@@ -221,37 +211,6 @@ export const uploadWebToVectorDB = async (token: string, collection_name: string
 	return res;
 };
 
-export const uploadYoutubeTranscriptionToVectorDB = async (token: string, url: string) => {
-	let error = null;
-
-	const res = await fetch(`${RAG_API_BASE_URL}/youtube`, {
-		method: 'POST',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			url: url
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			error = err.detail;
-			console.log(err);
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
 export const queryDoc = async (
 	token: string,
 	collection_name: string,
@@ -377,132 +336,3 @@ export const resetVectorDB = async (token: string) => {
 
 	return res;
 };
-
-export const getEmbeddingConfig = async (token: string) => {
-	let error = null;
-
-	const res = await fetch(`${RAG_API_BASE_URL}/embedding`, {
-		method: 'GET',
-		headers: {
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = err.detail;
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
-type OpenAIConfigForm = {
-	key: string;
-	url: string;
-};
-
-type EmbeddingModelUpdateForm = {
-	openai_config?: OpenAIConfigForm;
-	embedding_engine: string;
-	embedding_model: string;
-};
-
-export const updateEmbeddingConfig = async (token: string, payload: EmbeddingModelUpdateForm) => {
-	let error = null;
-
-	const res = await fetch(`${RAG_API_BASE_URL}/embedding/update`, {
-		method: 'POST',
-		headers: {
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			...payload
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = err.detail;
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
-export const getRerankingConfig = async (token: string) => {
-	let error = null;
-
-	const res = await fetch(`${RAG_API_BASE_URL}/reranking`, {
-		method: 'GET',
-		headers: {
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = err.detail;
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
-type RerankingModelUpdateForm = {
-	reranking_model: string;
-};
-
-export const updateRerankingConfig = async (token: string, payload: RerankingModelUpdateForm) => {
-	let error = null;
-
-	const res = await fetch(`${RAG_API_BASE_URL}/reranking/update`, {
-		method: 'POST',
-		headers: {
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			...payload
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = err.detail;
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};