Merge pull request #1488 from open-webui/dev

0.1.118
2024-04-10 15:38:47 -07:00 · 2024-04-10 15:38:47 -07:00 · 78284e49d7
commit 78284e49d7
parent 331fe04df7 64a6db4b55
61 changed files with 1837 additions and 723 deletions
--- a/.github/workflows/build-release.yml
+++ b/.github/workflows/build-release.yml
@ -57,3 +57,14 @@ 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 }}',
+          })
--- a/.github/workflows/docker-build.yaml
+++ b/.github/workflows/docker-build.yaml
@ -1,8 +1,7 @@
-#
-name: Create and publish a Docker image
+name: Create and publish Docker images with specific build args

-# Configures this workflow to run every time a change is pushed to the branch called `release`.
 on:
+  workflow_dispatch:
  push:
    branches:
      - main
@ -10,30 +9,39 @@ 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: ghcr.io
  IMAGE_NAME: ${{ github.repository }}
+  FULL_IMAGE_NAME: ghcr.io/${{ github.repository }}

-# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
 jobs:
-  build-and-push-image:
+  build-main-image:
    runs-on: ubuntu-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:
@ -41,12 +49,11 @@ jobs:
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

-      - name: Extract metadata for Docker images
+      - name: Extract metadata for Docker images (default latest tag)
        id: meta
        uses: docker/metadata-action@v5
        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
-          # This configuration dynamically generates tags based on the branch, tag, commit, and custom suffix for lite version.
+          images: ${{ env.FULL_IMAGE_NAME }}
          tags: |
            type=ref,event=branch
            type=ref,event=tag
@ -56,11 +63,322 @@ jobs:
          flavor: |
            latest=${{ github.ref == 'refs/heads/main' }}

-      - name: Build and push Docker image
+      - name: Build Docker image (latest)
        uses: docker/build-push-action@v5
+        id: build
        with:
          context: .
          push: true
-          platforms: linux/amd64,linux/arm64
-          tags: ${{ steps.meta.outputs.tags }}
+          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
+
+      - 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.GITHUB_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.GITHUB_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.GITHUB_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.GITHUB_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.GITHUB_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 }}
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@ -5,6 +5,26 @@ 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).

+## [0.1.118] - 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
--- a/128
+++ b/128
@ -1,82 +1,116 @@
 # 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 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.
+ARG USE_EMBEDDING_MODEL=all-MiniLM-L6-v2

-FROM node:alpine as build
+######## WebUI frontend ########
+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

-ENV ENV=prod
-ENV PORT ""
+# Use args
+ARG USE_CUDA
+ARG USE_OLLAMA
+ARG USE_CUDA_VER
+ARG USE_EMBEDDING_MODEL

-ENV OLLAMA_BASE_URL "/ollama"
+## Basis ##
+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}

-ENV OPENAI_API_BASE_URL ""
-ENV OPENAI_API_KEY ""
+## Basis URL Config ##
+ENV OLLAMA_BASE_URL="/ollama" \
+    OPENAI_API_BASE_URL=""

-ENV WEBUI_SECRET_KEY ""
-ENV WEBUI_AUTH_TRUSTED_EMAIL_HEADER ""
-
-ENV SCARF_NO_ANALYTICS true
-ENV DO_NOT_TRACK true
+## API Key and Security Config ##
+ENV OPENAI_API_KEY="" \
+    WEBUI_SECRET_KEY="" \
+    SCARF_NO_ANALYTICS=true \
+    DO_NOT_TRACK=true

 # Use locally bundled version of the LiteLLM cost map json
 # to avoid repetitive startup connections
 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"

-# RAG Embedding Model Settings
-# 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 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
+#### Other models #########################################################
+## whisper TTS model settings ##
+ENV WHISPER_MODEL="base" \
+    WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models"

-######## Preloaded models ########
+## RAG Embedding model settings ##
+ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
+    RAG_EMBEDDING_MODEL_DIR="/app/backend/data/cache/embedding/models" \
+    SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
+#### Other models ##########################################################

 WORKDIR /app/backend

+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 apt-get update && apt-get install ffmpeg libsm6 libxext6  -y
+RUN 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 && \
+        pip3 install -r requirements.txt --no-cache-dir && \
+        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'])" && \
+        python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
+    else \
+        pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
+        pip3 install -r requirements.txt --no-cache-dir && \
+        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'])" && \
+        python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
+    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
-COPY --from=build /app/onnx /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx
+# 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 built frontend files
 COPY --from=build /app/build /app/build
@ -86,4 +120,6 @@ COPY --from=build /app/package.json /app/package.json
 # copy backend files
 COPY ./backend .

+EXPOSE 8080
+
 CMD [ "bash", "start.sh"]
--- a/README.md
+++ b/README.md
@ -94,24 +94,27 @@ Don't forget to explore our sibling project, [Open WebUI Community](https://open

 ### Quick Start with Docker 🐳

-> [!IMPORTANT]
+> [!WARNING]
 > 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.

- **If Ollama is on your computer**, use this command:
+> [!TIP]  
+> 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
 ```

- **If Ollama is on a Different Server**, use this command:
+**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
 ```

- After installation, you can access Open WebUI at [http://localhost:3000](http://localhost:3000). Enjoy! 😄
+After installation, you can access Open WebUI at [http://localhost:3000](http://localhost:3000). Enjoy! 😄

 #### Open WebUI: Server Connection Error

--- a/backend/apps/audio/main.py
+++ b/backend/apps/audio/main.py
@ -28,6 +28,7 @@ from config import (
    UPLOAD_DIR,
    WHISPER_MODEL,
    WHISPER_MODEL_DIR,
+    DEVICE_TYPE,
 )

 log = logging.getLogger(__name__)
@ -42,6 +43,10 @@ app.add_middleware(
    allow_headers=["*"],
 )

+# 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}")
+

@app.post("/transcribe")
 def transcribe(
@ -66,7 +71,7 @@ def transcribe(

        model = WhisperModel(
            WHISPER_MODEL,
-            device="auto",
+            device=whisper_device_type,
            compute_type="int8",
            download_root=WHISPER_MODEL_DIR,
        )
--- a/backend/apps/ollama/main.py
+++ b/backend/apps/ollama/main.py
@ -215,7 +215,8 @@ async def get_ollama_versions(url_idx: Optional[int] = None):

        if len(responses) > 0:
            lowest_version = min(
-                responses, key=lambda x: tuple(map(int, x["version"].split(".")))
+                responses,
+                key=lambda x: tuple(map(int, x["version"].split("-")[0].split("."))),
            )

            return {"version": lowest_version["version"]}
--- a/backend/apps/rag/main.py
+++ b/backend/apps/rag/main.py
@ -13,8 +13,8 @@ import os, shutil, logging, re
 from pathlib import Path
 from typing import List

-from sentence_transformers import SentenceTransformer
 from chromadb.utils import embedding_functions
+from chromadb.utils.batch_utils import create_batches

 from langchain_community.document_loaders import (
    WebBaseLoader,
@ -45,7 +45,7 @@ from apps.web.models.documents import (
    DocumentResponse,
 )

-from apps.rag.utils import query_doc, query_collection
+from apps.rag.utils import query_doc, query_collection, get_embedding_model_path

 from utils.misc import (
    calculate_sha256,
@ -59,7 +59,8 @@ from config import (
    UPLOAD_DIR,
    DOCS_DIR,
    RAG_EMBEDDING_MODEL,
-    RAG_EMBEDDING_MODEL_DEVICE_TYPE,
+    RAG_EMBEDDING_MODEL_AUTO_UPDATE,
+    DEVICE_TYPE,
    CHROMA_CLIENT,
    CHUNK_SIZE,
    CHUNK_OVERLAP,
@ -71,28 +72,25 @@ 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.PDF_EXTRACT_IMAGES = False
 app.state.CHUNK_SIZE = CHUNK_SIZE
 app.state.CHUNK_OVERLAP = CHUNK_OVERLAP
 app.state.RAG_TEMPLATE = RAG_TEMPLATE
+
+
 app.state.RAG_EMBEDDING_MODEL = RAG_EMBEDDING_MODEL
+
+
 app.state.TOP_K = 4

 app.state.sentence_transformer_ef = (
    embedding_functions.SentenceTransformerEmbeddingFunction(
-        model_name=app.state.RAG_EMBEDDING_MODEL,
-        device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
+        model_name=get_embedding_model_path(
+            app.state.RAG_EMBEDDING_MODEL, RAG_EMBEDDING_MODEL_AUTO_UPDATE
+        ),
+        device=DEVICE_TYPE,
    )
 )

@ -143,19 +141,34 @@ class EmbeddingModelUpdateForm(BaseModel):
 async def update_embedding_model(
    form_data: EmbeddingModelUpdateForm, user=Depends(get_admin_user)
 ):
-    app.state.RAG_EMBEDDING_MODEL = form_data.embedding_model
-    app.state.sentence_transformer_ef = (
+
+    log.info(
+        f"Updating embedding model: {app.state.RAG_EMBEDDING_MODEL} to {form_data.embedding_model}"
+    )
+
+    try:
+        sentence_transformer_ef = (
            embedding_functions.SentenceTransformerEmbeddingFunction(
-            model_name=app.state.RAG_EMBEDDING_MODEL,
-            device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
+                model_name=get_embedding_model_path(form_data.embedding_model, True),
+                device=DEVICE_TYPE,
            )
        )

+        app.state.RAG_EMBEDDING_MODEL = form_data.embedding_model
+        app.state.sentence_transformer_ef = sentence_transformer_ef
+
        return {
            "status": True,
            "embedding_model": app.state.RAG_EMBEDDING_MODEL,
        }

+    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),
+        )
+

@app.get("/config")
 async def get_rag_config(user=Depends(get_admin_user)):
@ -341,9 +354,14 @@ def store_docs_in_vector_db(docs, collection_name, overwrite: bool = False) -> b
            embedding_function=app.state.sentence_transformer_ef,
        )

-        collection.add(
-            documents=texts, metadatas=metadatas, ids=[str(uuid.uuid1()) for _ in texts]
-        )
+        for batch in create_batches(
+            api=CHROMA_CLIENT,
+            ids=[str(uuid.uuid1()) for _ in texts],
+            metadatas=metadatas,
+            documents=texts,
+        ):
+            collection.add(*batch)
+
        return True
    except Exception as e:
        log.exception(e)
--- a/backend/apps/rag/utils.py
+++ b/backend/apps/rag/utils.py
@ -1,6 +1,8 @@
+import os
 import re
 import logging
 from typing import List
+from huggingface_hub import snapshot_download

 from config import SRC_LOG_LEVELS, CHROMA_CLIENT

@ -188,3 +190,43 @@ def rag_messages(docs, messages, template, k, embedding_function):
    messages[last_user_message_idx] = new_user_message

    return messages
+
+
+def get_embedding_model_path(
+    embedding_model: str, update_embedding_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_embedding_model
+
+    snapshot_kwargs = {
+        "cache_dir": cache_dir,
+        "local_files_only": local_files_only,
+    }
+
+    log.debug(f"embedding_model: {embedding_model}")
+    log.debug(f"snapshot_kwargs: {snapshot_kwargs}")
+
+    # Inspiration from upstream sentence_transformers
+    if (
+        os.path.exists(embedding_model)
+        or ("\\" in embedding_model or embedding_model.count("/") > 1)
+        and local_files_only
+    ):
+        # If fully qualified path exists, return input, else set repo_id
+        return embedding_model
+    elif "/" not in embedding_model:
+        # Set valid repo_id for model short-name
+        embedding_model = "sentence-transformers" + "/" + embedding_model
+
+    snapshot_kwargs["repo_id"] = embedding_model
+
+    # Attempt to query the huggingface_hub library to determine the local path and/or to update
+    try:
+        embedding_model_repo_path = snapshot_download(**snapshot_kwargs)
+        log.debug(f"embedding_model_repo_path: {embedding_model_repo_path}")
+        return embedding_model_repo_path
+    except Exception as e:
+        log.exception(f"Cannot determine embedding model snapshot path: {e}")
+        return embedding_model
--- a/backend/apps/web/models/auths.py
+++ b/backend/apps/web/models/auths.py
@ -86,6 +86,7 @@ class SignupForm(BaseModel):
    name: str
    email: str
    password: str
+    profile_image_url: Optional[str] = "/user.png"


 class AuthsTable:
@ -94,7 +95,12 @@ class AuthsTable:
        self.db.create_tables([Auth])

    def insert_new_auth(
-        self, email: str, password: str, name: str, role: str = "pending"
+        self,
+        email: str,
+        password: str,
+        name: str,
+        profile_image_url: str = "/user.png",
+        role: str = "pending",
    ) -> Optional[UserModel]:
        log.info("insert_new_auth")

@ -105,7 +111,7 @@ class AuthsTable:
        )
        result = Auth.create(**auth.model_dump())

-        user = Users.insert_new_user(id, name, email, role)
+        user = Users.insert_new_user(id, name, email, profile_image_url, role)

        if result and user:
            return user
--- a/backend/apps/web/models/chats.py
+++ b/backend/apps/web/models/chats.py
@ -206,6 +206,18 @@ class ChatTable:
        except:
            return None

+    def get_chat_by_share_id(self, id: str) -> Optional[ChatModel]:
+        try:
+            chat = Chat.get(Chat.share_id == id)
+
+            if chat:
+                chat = Chat.get(Chat.id == id)
+                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:
            chat = Chat.get(Chat.id == id, Chat.user_id == user_id)
--- a/backend/apps/web/models/users.py
+++ b/backend/apps/web/models/users.py
@ -31,7 +31,7 @@ class UserModel(BaseModel):
    name: str
    email: str
    role: str = "pending"
-    profile_image_url: str = "/user.png"
+    profile_image_url: str
    timestamp: int  # timestamp in epoch
    api_key: Optional[str] = None

@ -59,7 +59,12 @@ class UsersTable:
        self.db.create_tables([User])

    def insert_new_user(
-        self, id: str, name: str, email: str, role: str = "pending"
+        self,
+        id: str,
+        name: str,
+        email: str,
+        profile_image_url: str = "/user.png",
+        role: str = "pending",
    ) -> Optional[UserModel]:
        user = UserModel(
            **{
@ -67,7 +72,7 @@ class UsersTable:
                "name": name,
                "email": email,
                "role": role,
-                "profile_image_url": "/user.png",
+                "profile_image_url": profile_image_url,
                "timestamp": int(time.time()),
            }
        )
--- a/backend/apps/web/routers/auths.py
+++ b/backend/apps/web/routers/auths.py
@ -163,7 +163,11 @@ async def signup(request: Request, form_data: SignupForm):
        )
        hashed = get_password_hash(form_data.password)
        user = Auths.insert_new_auth(
-            form_data.email.lower(), hashed, form_data.name, role
+            form_data.email.lower(),
+            hashed,
+            form_data.name,
+            form_data.profile_image_url,
+            role,
        )

        if user:
--- a/backend/apps/web/routers/chats.py
+++ b/backend/apps/web/routers/chats.py
@ -251,6 +251,14 @@ async def delete_shared_chat_by_id(id: str, user=Depends(get_current_user)):

@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:
--- a/backend/config.py
+++ b/backend/config.py
@ -28,8 +28,6 @@ except ImportError:
 WEBUI_NAME = os.environ.get("WEBUI_NAME", "Open WebUI")
 WEBUI_FAVICON_URL = "https://openwebui.com/favicon.png"

-shutil.copyfile("../build/favicon.png", "./static/favicon.png")
-
 ####################################
 # ENV (dev,test,prod)
 ####################################
@ -103,6 +101,26 @@ for version in soup.find_all("h2"):

 CHANGELOG = changelog_json

+####################################
+# DATA/FRONTEND BUILD DIR
+####################################
+
+DATA_DIR = str(Path(os.getenv("DATA_DIR", "./data")).resolve())
+FRONTEND_BUILD_DIR = str(Path(os.getenv("FRONTEND_BUILD_DIR", "../build")))
+
+try:
+    with open(f"{DATA_DIR}/config.json", "r") as f:
+        CONFIG_DATA = json.load(f)
+except:
+    CONFIG_DATA = {}
+
+####################################
+# Static DIR
+####################################
+
+STATIC_DIR = str(Path(os.getenv("STATIC_DIR", "./static")).resolve())
+
+shutil.copyfile(f"{FRONTEND_BUILD_DIR}/favicon.png", f"{STATIC_DIR}/favicon.png")

 ####################################
 # LOGGING
@ -165,7 +183,7 @@ if CUSTOM_NAME:

                r = requests.get(url, stream=True)
                if r.status_code == 200:
-                    with open("./static/favicon.png", "wb") as f:
+                    with open(f"{STATIC_DIR}/favicon.png", "wb") as f:
                        r.raw.decode_content = True
                        shutil.copyfileobj(r.raw, f)

@ -177,18 +195,6 @@ else:
    if WEBUI_NAME != "Open WebUI":
        WEBUI_NAME += " (Open WebUI)"

-####################################
-# DATA/FRONTEND BUILD DIR
-####################################
-
-DATA_DIR = str(Path(os.getenv("DATA_DIR", "./data")).resolve())
-FRONTEND_BUILD_DIR = str(Path(os.getenv("FRONTEND_BUILD_DIR", "../build")))
-
-try:
-    with open(f"{DATA_DIR}/config.json", "r") as f:
-        CONFIG_DATA = json.load(f)
-except:
-    CONFIG_DATA = {}

 ####################################
 # File Upload DIR
@ -257,6 +263,7 @@ 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 OLLAMA_BASE_URL == "" and OLLAMA_API_BASE_URL != "":
    OLLAMA_BASE_URL = (
@ -266,9 +273,13 @@ if OLLAMA_BASE_URL == "" and OLLAMA_API_BASE_URL != "":
    )

 if ENV == "prod":
-    if OLLAMA_BASE_URL == "/ollama":
+    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"

@ -391,10 +402,22 @@ if WEBUI_AUTH and WEBUI_SECRET_KEY == "":
 CHROMA_DATA_PATH = f"{DATA_DIR}/vector_db"
 # 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)
 RAG_EMBEDDING_MODEL = os.environ.get("RAG_EMBEDDING_MODEL", "all-MiniLM-L6-v2")
-# device type ebbeding models - "cpu" (default), "cuda" (nvidia gpu required) or "mps" (apple silicon) - choosing this right can lead to better performance
-RAG_EMBEDDING_MODEL_DEVICE_TYPE = os.environ.get(
-    "RAG_EMBEDDING_MODEL_DEVICE_TYPE", "cpu"
+log.info(f"Embedding model set: {RAG_EMBEDDING_MODEL}"),
+
+RAG_EMBEDDING_MODEL_AUTO_UPDATE = (
+    os.environ.get("RAG_EMBEDDING_MODEL_AUTO_UPDATE", "").lower() == "true"
 )
+
+
+# device type ebbeding 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"
+
+
 CHROMA_CLIENT = chromadb.PersistentClient(
    path=CHROMA_DATA_PATH,
    settings=Settings(allow_reset=True, anonymized_telemetry=False),
--- a/backend/main.py
+++ b/backend/main.py
@ -5,6 +5,7 @@ import time
 import os
 import sys
 import logging
+import aiohttp
 import requests

 from fastapi import FastAPI, Request, Depends, status
@ -18,6 +19,7 @@ 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.audio.main import app as audio_app
 from apps.images.main import app as images_app
@ -38,6 +40,8 @@ from config import (
    VERSION,
    CHANGELOG,
    FRONTEND_BUILD_DIR,
+    CACHE_DIR,
+    STATIC_DIR,
    MODEL_FILTER_ENABLED,
    MODEL_FILTER_LIST,
    GLOBAL_LOG_LEVEL,
@ -269,14 +273,16 @@ async def get_app_changelog():
@app.get("/api/version/updates")
 async def get_app_latest_release_version():
    try:
-        response = requests.get(
-            f"https://api.github.com/repos/open-webui/open-webui/releases/latest"
-        )
+        async with aiohttp.ClientSession() as session:
+            async with session.get(
+                "https://api.github.com/repos/open-webui/open-webui/releases/latest"
+            ) as response:
                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:]}
-    except Exception as e:
+    except aiohttp.ClientError as e:
        raise HTTPException(
            status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
            detail=ERROR_MESSAGES.RATE_LIMIT_EXCEEDED,
@ -297,9 +303,8 @@ async def get_manifest_json():
    }


-app.mount("/static", StaticFiles(directory="static"), name="static")
-app.mount("/cache", StaticFiles(directory="data/cache"), name="cache")
-
+app.mount("/static", StaticFiles(directory=STATIC_DIR), name="static")
+app.mount("/cache", StaticFiles(directory=CACHE_DIR), name="cache")

 app.mount(
    "/",
--- a/backend/start.sh
+++ b/backend/start.sh
@ -7,16 +7,26 @@ KEY_FILE=.webui_secret_key

 PORT="${PORT:-8080}"
 if test "$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
-  WEBUI_SECRET_KEY=`cat $KEY_FILE`
+  echo "Loading WEBUI_SECRET_KEY from $KEY_FILE"
+  WEBUI_SECRET_KEY=$(cat "$KEY_FILE")
+fi
+
+if [ "$USE_OLLAMA_DOCKER" = "true" ]; then
+    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="$WEBUI_SECRET_KEY" exec uvicorn main:app --host 0.0.0.0 --port "$PORT" --forwarded-allow-ips '*'
--- a/docker-compose.amdgpu.yaml
+++ b/docker-compose.amdgpu.yaml
@ -0,0 +1,8 @@
+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}'
--- a/docker-compose.yaml
+++ b/docker-compose.yaml
@ -8,7 +8,7 @@ services:
    pull_policy: always
    tty: true
    restart: unless-stopped
-    image: ollama/ollama:latest
+    image: ollama/ollama:${OLLAMA_DOCKER_TAG-latest}

  open-webui:
    build:
@ -16,7 +16,7 @@ services:
      args:
        OLLAMA_BASE_URL: '/ollama'
      dockerfile: Dockerfile
-    image: ghcr.io/open-webui/open-webui:main
+    image: ghcr.io/open-webui/open-webui:${WEBUI_DOCKER_TAG-main}
    container_name: open-webui
    volumes:
      - open-webui:/app/backend/data
--- a/kubernetes/helm/templates/_helpers.tpl
+++ b/kubernetes/helm/templates/_helpers.tpl
@ -7,8 +7,12 @@ ollama
 {{- end -}}

 {{- define "ollama.url" -}}
+{{- if .Values.ollama.externalHost }}
+{{- 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" -}}
 {{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
--- a/kubernetes/helm/templates/ollama-service.yaml
+++ b/kubernetes/helm/templates/ollama-service.yaml
@ -1,3 +1,4 @@
+{{- if not .Values.ollama.externalHost }}
 apiVersion: v1
 kind: Service
 metadata:
@ -19,3 +20,4 @@ spec:
    port: {{ .port }}
    targetPort: http
 {{- end }}
+{{- end }}
--- a/kubernetes/helm/templates/ollama-statefulset.yaml
+++ b/kubernetes/helm/templates/ollama-statefulset.yaml
@ -1,3 +1,4 @@
+{{- if not .Values.ollama.externalHost }}
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
@ -94,3 +95,4 @@ spec:
        {{- toYaml . | nindent 8 }}
      {{- end }}
      {{- end }}
+{{- end }}
--- a/kubernetes/helm/templates/webui-pvc.yaml
+++ b/kubernetes/helm/templates/webui-pvc.yaml
@ -17,7 +17,9 @@ spec:
  resources:
    requests:
      storage: {{ .Values.webui.persistence.size }}
+  {{- if .Values.webui.persistence.storageClass }}
  storageClassName: {{ .Values.webui.persistence.storageClass }}
+  {{- end }}
  {{- with .Values.webui.persistence.selector }}
  selector:
    {{- toYaml . | nindent 4 }}
--- a/kubernetes/helm/values.yaml
+++ b/kubernetes/helm/values.yaml
@ -1,6 +1,7 @@
 nameOverride: ""

 ollama:
+  externalHost: ""
  annotations: {}
  podAnnotations: {}
  replicaCount: 1
--- a/package-lock.json
+++ b/package-lock.json
@ -1,12 +1,12 @@
 {
 	"name": "open-webui",
-	"version": "0.1.117",
+	"version": "0.1.118",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "open-webui",
-			"version": "0.1.117",
+			"version": "0.1.118",
 			"dependencies": {
 				"@sveltejs/adapter-node": "^1.3.1",
 				"async": "^3.2.5",
@ -5688,9 +5688,9 @@
 			}
 		},
 		"node_modules/undici": {
-			"version": "5.28.3",
-			"resolved": "https://registry.npmjs.org/undici/-/undici-5.28.3.tgz",
-			"integrity": "sha512-3ItfzbrhDlINjaP0duwnNsKpDQk3acHI3gVJ1z4fmwMK31k5G9OVIAMLSIaP6w4FaGkaAkN6zaQO9LUvZ1t7VA==",
+			"version": "5.28.4",
+			"resolved": "https://registry.npmjs.org/undici/-/undici-5.28.4.tgz",
+			"integrity": "sha512-72RFADWFqKmUb2hmmvNODKL3p9hcB6Gt2DOQMis1SEBaV6a4MH8soBvzg+95CYhCKPFedut2JY9bMfrDl9D23g==",
 			"dependencies": {
 				"@fastify/busboy": "^2.0.0"
 			},
--- a/package.json
+++ b/package.json
@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.1.117",
+	"version": "0.1.118",
 	"private": true,
 	"scripts": {
 		"dev": "vite dev --host",
--- a/src/lib/apis/auths/index.ts
+++ b/src/lib/apis/auths/index.ts
@ -58,7 +58,12 @@ export const userSignIn = async (email: string, password: string) => {
 	return res;
 };

-export const userSignUp = async (name: string, email: string, password: string) => {
+export const userSignUp = async (
+	name: string,
+	email: string,
+	password: string,
+	profile_image_url: string
+) => {
 	let error = null;

 	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/signup`, {
@ -69,7 +74,8 @@ export const userSignUp = async (name: string, email: string, password: string)
 		body: JSON.stringify({
 			name: name,
 			email: email,
-			password: password
+			password: password,
+			profile_image_url: profile_image_url
 		})
 	})
 		.then(async (res) => {
--- a/src/lib/apis/rag/index.ts
+++ b/src/lib/apis/rag/index.ts
@ -345,3 +345,64 @@ export const resetVectorDB = async (token: string) => {

 	return res;
 };
+
+export const getEmbeddingModel = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${RAG_API_BASE_URL}/embedding/model`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+type EmbeddingModelUpdateForm = {
+	embedding_model: string;
+};
+
+export const updateEmbeddingModel = async (token: string, payload: EmbeddingModelUpdateForm) => {
+	let error = null;
+
+	const res = await fetch(`${RAG_API_BASE_URL}/embedding/model/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;
+};
--- a/src/lib/components/chat/MessageInput.svelte
+++ b/src/lib/components/chat/MessageInput.svelte
@ -295,6 +295,13 @@

 		const dropZone = document.querySelector('body');

+		const handleKeyDown = (event: KeyboardEvent) => {
+			if (event.key === 'Escape') {
+				console.log('Escape');
+				dragged = false;
+			}
+		};
+
 		const onDragOver = (e) => {
 			e.preventDefault();
 			dragged = true;
@ -350,11 +357,15 @@
 			dragged = false;
 		};

+		window.addEventListener('keydown', handleKeyDown);
+
 		dropZone?.addEventListener('dragover', onDragOver);
 		dropZone?.addEventListener('drop', onDrop);
 		dropZone?.addEventListener('dragleave', onDragLeave);

 		return () => {
+			window.removeEventListener('keydown', handleKeyDown);
+
 			dropZone?.removeEventListener('dragover', onDragOver);
 			dropZone?.removeEventListener('drop', onDrop);
 			dropZone?.removeEventListener('dragleave', onDragLeave);
--- a/src/lib/components/chat/Messages.svelte
+++ b/src/lib/components/chat/Messages.svelte
@ -107,12 +107,8 @@
 		await sendPrompt(userPrompt, userMessageId, chatId);
 	};

-	const confirmEditResponseMessage = async (messageId, content) => {
-		history.messages[messageId].originalContent = history.messages[messageId].content;
-		history.messages[messageId].content = content;
-
+	const updateChatMessages = async () => {
 		await tick();
-
 		await updateChatById(localStorage.token, chatId, {
 			messages: messages,
 			history: history
@ -121,15 +117,20 @@
 		await chats.set(await getChatList(localStorage.token));
 	};

-	const rateMessage = async (messageId, rating) => {
-		history.messages[messageId].rating = rating;
-		await tick();
-		await updateChatById(localStorage.token, chatId, {
-			messages: messages,
-			history: history
-		});
+	const confirmEditResponseMessage = async (messageId, content) => {
+		history.messages[messageId].originalContent = history.messages[messageId].content;
+		history.messages[messageId].content = content;

-		await chats.set(await getChatList(localStorage.token));
+		await updateChatMessages();
+	};
+
+	const rateMessage = async (messageId, rating) => {
+		history.messages[messageId].annotation = {
+			...history.messages[messageId].annotation,
+			rating: rating
+		};
+
+		await updateChatMessages();
 	};

 	const showPreviousMessage = async (message) => {
@ -338,6 +339,7 @@
 								siblings={history.messages[message.parentId]?.childrenIds ?? []}
 								isLastMessage={messageIdx + 1 === messages.length}
 								{readOnly}
+								{updateChatMessages}
 								{confirmEditResponseMessage}
 								{showPreviousMessage}
 								{showNextMessage}
--- a/src/lib/components/chat/Messages/RateComment.svelte
+++ b/src/lib/components/chat/Messages/RateComment.svelte
@ -0,0 +1,117 @@
+<script lang="ts">
+	import { toast } from 'svelte-sonner';
+
+	import { createEventDispatcher, onMount } from 'svelte';
+
+	const dispatch = createEventDispatcher();
+
+	export let show = false;
+	export let message;
+
+	const LIKE_REASONS = [
+		`Accurate information`,
+		`Followed instructions perfectly`,
+		`Showcased creativity`,
+		`Positive attitude`,
+		`Attention to detail`,
+		`Thorough explanation`,
+		`Other`
+	];
+
+	const DISLIKE_REASONS = [
+		`Don't like the style`,
+		`Not factually correct`,
+		`Didn't fully follow instructions`,
+		`Refused when it shouldn't have`,
+		`Being Lazy`,
+		`Other`
+	];
+
+	let reasons = [];
+	let selectedReason = null;
+	let comment = '';
+
+	$: if (message.annotation.rating === 1) {
+		reasons = LIKE_REASONS;
+	} else if (message.annotation.rating === -1) {
+		reasons = DISLIKE_REASONS;
+	}
+
+	onMount(() => {
+		selectedReason = message.annotation.reason;
+		comment = message.annotation.comment;
+	});
+
+	const submitHandler = () => {
+		console.log('submitHandler');
+
+		message.annotation.reason = selectedReason;
+		message.annotation.comment = comment;
+
+		dispatch('submit');
+
+		toast.success('Thanks for your feedback!');
+		show = false;
+	};
+</script>
+
+<div class=" my-2.5 rounded-xl px-4 py-3 border dark:border-gray-850">
+	<div class="flex justify-between items-center">
+		<div class=" text-sm">Tell us more:</div>
+
+		<button
+			on:click={() => {
+				show = false;
+			}}
+		>
+			<svg
+				xmlns="http://www.w3.org/2000/svg"
+				fill="none"
+				viewBox="0 0 24 24"
+				stroke-width="1.5"
+				stroke="currentColor"
+				class="size-4"
+			>
+				<path stroke-linecap="round" stroke-linejoin="round" d="M6 18 18 6M6 6l12 12" />
+			</svg>
+		</button>
+	</div>
+
+	{#if reasons.length > 0}
+		<div class="flex flex-wrap gap-2 text-sm mt-2.5">
+			{#each reasons as reason}
+				<button
+					class="px-3.5 py-1 border dark:border-gray-850 dark:hover:bg-gray-850 {selectedReason ===
+					reason
+						? 'dark:bg-gray-800'
+						: ''} transition rounded-lg"
+					on:click={() => {
+						selectedReason = reason;
+					}}
+				>
+					{reason}
+				</button>
+			{/each}
+		</div>
+	{/if}
+
+	<div class="mt-2">
+		<textarea
+			bind:value={comment}
+			class="w-full text-sm px-1 py-2 bg-transparent outline-none resize-none rounded-xl"
+			placeholder="Feel free to add specific details"
+			rows="2"
+		/>
+	</div>
+
+	<div class="mt-2 flex justify-end">
+		<button
+			class=" bg-emerald-700 text-white text-sm font-medium rounded-lg px-3.5 py-1.5"
+			on:click={() => {
+				submitHandler();
+			}}
+		>
+			Submit
+		</button>
+	</div>
+</div>
--- a/src/lib/components/chat/Messages/ResponseMessage.svelte
+++ b/src/lib/components/chat/Messages/ResponseMessage.svelte
@ -30,6 +30,7 @@
 	import Image from '$lib/components/common/Image.svelte';
 	import { WEBUI_BASE_URL } from '$lib/constants';
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import RateComment from './RateComment.svelte';

 	export let modelfiles = [];
 	export let message;
@ -39,6 +40,7 @@

 	export let readOnly = false;

+	export let updateChatMessages: Function;
 	export let confirmEditResponseMessage: Function;
 	export let showPreviousMessage: Function;
 	export let showNextMessage: Function;
@ -60,6 +62,8 @@
 	let loadingSpeech = false;
 	let generatingImage = false;

+	let showRateComment = false;
+
 	$: tokens = marked.lexer(sanitizeResponseContent(message.content));

 	const renderer = new marked.Renderer();
@ -536,11 +540,13 @@
 												<button
 													class="{isLastMessage
 														? 'visible'
-														: 'invisible group-hover:visible'} p-1 rounded {message.rating === 1
+														: 'invisible group-hover:visible'} p-1 rounded {message?.annotation
+														?.rating === 1
 														? 'bg-gray-100 dark:bg-gray-800'
 														: ''} dark:hover:text-white hover:text-black transition"
 													on:click={() => {
 														rateMessage(message.id, 1);
+														showRateComment = true;
 													}}
 												>
 													<svg
@ -563,11 +569,13 @@
 												<button
 													class="{isLastMessage
 														? 'visible'
-														: 'invisible group-hover:visible'} p-1 rounded {message.rating === -1
+														: 'invisible group-hover:visible'} p-1 rounded {message?.annotation
+														?.rating === -1
 														? 'bg-gray-100 dark:bg-gray-800'
 														: ''} dark:hover:text-white hover:text-black transition"
 													on:click={() => {
 														rateMessage(message.id, -1);
+														showRateComment = true;
 													}}
 												>
 													<svg
@ -824,6 +832,16 @@
 										{/if}
 									</div>
 								{/if}
+
+								{#if showRateComment}
+									<RateComment
+										bind:show={showRateComment}
+										bind:message
+										on:submit={() => {
+											updateChatMessages();
+										}}
+									/>
+								{/if}
 							</div>
 						{/if}
 					</div>
--- a/src/lib/components/chat/Settings/Account.svelte
+++ b/src/lib/components/chat/Settings/Account.svelte
@ -7,6 +7,7 @@

 	import UpdatePassword from './Account/UpdatePassword.svelte';
 	import { getGravatarUrl } from '$lib/apis/utils';
+	import { generateInitialsImage, canvasPixelTest } from '$lib/utils';
 	import { copyToClipboard } from '$lib/utils';
 	import Plus from '$lib/components/icons/Plus.svelte';
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
@ -18,6 +19,8 @@
 	let profileImageUrl = '';
 	let name = '';

+	let showAPIKeys = false;
+
 	let showJWTToken = false;
 	let JWTTokenCopied = false;

@ -28,6 +31,12 @@
 	let profileImageInputElement: HTMLInputElement;

 	const submitHandler = async () => {
+		if (name !== $user.name) {
+			if (profileImageUrl === generateInitialsImage($user.name) || profileImageUrl === '') {
+				profileImageUrl = generateInitialsImage(name);
+			}
+		}
+
 		const updatedUser = await updateUserProfile(localStorage.token, name, profileImageUrl).catch(
 			(error) => {
 				toast.error(error);
@ -125,11 +134,12 @@
 			}}
 		/>

-		<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Profile')}</div>
+		<div class="space-y-1">
+			<!-- <div class=" text-sm font-medium">{$i18n.t('Account')}</div> -->

 			<div class="flex space-x-5">
 				<div class="flex flex-col">
-				<div class="self-center">
+					<div class="self-center mt-2">
 						<button
 							class="relative rounded-full dark:bg-gray-700"
 							type="button"
@ -138,9 +148,9 @@
 							}}
 						>
 							<img
-							src={profileImageUrl !== '' ? profileImageUrl : '/user.png'}
+								src={profileImageUrl !== '' ? profileImageUrl : generateInitialsImage(name)}
 								alt="profile"
-							class=" rounded-full w-16 h-16 object-cover"
+								class=" rounded-full size-16 object-cover"
 							/>

 							<div
@ -161,23 +171,56 @@
 							</div>
 						</button>
 					</div>
+				</div>
+
+				<div class="flex-1 flex flex-col self-center gap-0.5">
+					<div class=" mb-0.5 text-sm font-medium">{$i18n.t('Profile Image')}</div>
+
+					<div>
 						<button
-					class=" text-xs text-gray-600"
+							class=" text-xs text-center text-gray-800 dark:text-gray-400 rounded-full px-4 py-0.5 bg-gray-100 dark:bg-gray-850"
+							on:click={async () => {
+								if (canvasPixelTest()) {
+									profileImageUrl = generateInitialsImage(name);
+								} else {
+									toast.info(
+										$i18n.t(
+											'Fingerprint spoofing detected: Unable to use initials as avatar. Defaulting to default profile image.'
+										),
+										{
+											duration: 1000 * 10
+										}
+									);
+								}
+							}}>{$i18n.t('Use Initials')}</button
+						>
+
+						<button
+							class=" text-xs text-center text-gray-800 dark:text-gray-400 rounded-full px-4 py-0.5 bg-gray-100 dark:bg-gray-850"
 							on:click={async () => {
 								const url = await getGravatarUrl($user.email);

 								profileImageUrl = url;
 							}}>{$i18n.t('Use Gravatar')}</button
 						>
+
+						<button
+							class=" text-xs text-center text-gray-800 dark:text-gray-400 rounded-lg px-2 py-1"
+							on:click={async () => {
+								profileImageUrl = '/user.png';
+							}}>{$i18n.t('Remove')}</button
+						>
+					</div>
+				</div>
 			</div>

-			<div class="flex-1">
+			<div class="pt-0.5">
 				<div class="flex flex-col w-full">
-					<div class=" mb-1 text-xs text-gray-500">{$i18n.t('Name')}</div>
+					<div class=" mb-1 text-xs font-medium">{$i18n.t('Name')}</div>

 					<div class="flex-1">
 						<input
-							class="w-full rounded py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none"
+							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
 							type="text"
 							bind:value={name}
 							required
@ -187,11 +230,24 @@
 			</div>
 		</div>

-		<hr class=" dark:border-gray-700 my-4" />
+		<div class="py-0.5">
 			<UpdatePassword />
+		</div>

 		<hr class=" dark:border-gray-700 my-4" />

+		<div class="flex justify-between items-center text-sm">
+			<div class="  font-medium">{$i18n.t('API keys')}</div>
+			<button
+				class=" text-xs font-medium text-gray-500"
+				type="button"
+				on:click={() => {
+					showAPIKeys = !showAPIKeys;
+				}}>{showAPIKeys ? $i18n.t('Hide') : $i18n.t('Show')}</button
+			>
+		</div>
+
+		{#if showAPIKeys}
 			<div class="flex flex-col gap-4">
 				<div class="justify-between w-full">
 					<div class="flex justify-between w-full">
@ -201,14 +257,14 @@
 					<div class="flex mt-2">
 						<div class="flex w-full">
 							<input
-							class="w-full rounded-l-lg py-1.5 pl-4 text-sm bg-white dark:text-gray-300 dark:bg-gray-800 outline-none"
+								class="w-full rounded-l-lg py-1.5 pl-4 text-sm bg-white dark:text-gray-300 dark:bg-gray-850 outline-none"
 								type={showJWTToken ? 'text' : 'password'}
 								value={localStorage.token}
 								disabled
 							/>

 							<button
-							class="px-2 transition rounded-r-lg bg-white dark:bg-gray-800"
+								class="px-2 transition rounded-r-lg bg-white dark:bg-gray-850"
 								on:click={() => {
 									showJWTToken = !showJWTToken;
 								}}
@ -248,7 +304,7 @@
 						</div>

 						<button
-						class="ml-1.5 px-1.5 py-1 dark:hover:bg-gray-800 transition rounded-lg"
+							class="ml-1.5 px-1.5 py-1 dark:hover:bg-gray-850 transition rounded-lg"
 							on:click={() => {
 								copyToClipboard(localStorage.token);
 								JWTTokenCopied = true;
@ -301,14 +357,14 @@
 						{#if APIKey}
 							<div class="flex w-full">
 								<input
-								class="w-full rounded-l-lg py-1.5 pl-4 text-sm bg-white dark:text-gray-300 dark:bg-gray-800 outline-none"
+									class="w-full rounded-l-lg py-1.5 pl-4 text-sm bg-white dark:text-gray-300 dark:bg-gray-850 outline-none"
 									type={showAPIKey ? 'text' : 'password'}
 									value={APIKey}
 									disabled
 								/>

 								<button
-								class="px-2 transition rounded-r-lg bg-white dark:bg-gray-800"
+									class="px-2 transition rounded-r-lg bg-white dark:bg-gray-850"
 									on:click={() => {
 										showAPIKey = !showAPIKey;
 									}}
@ -348,7 +404,7 @@
 							</div>

 							<button
-							class="ml-1.5 px-1.5 py-1 dark:hover:bg-gray-800 transition rounded-lg"
+								class="ml-1.5 px-1.5 py-1 dark:hover:bg-gray-850 transition rounded-lg"
 								on:click={() => {
 									copyToClipboard(APIKey);
 									APIKeyCopied = true;
@ -393,7 +449,7 @@

 							<Tooltip content="Create new key">
 								<button
-								class=" px-1.5 py-1 dark:hover:bg-gray-800transition rounded-lg"
+									class=" px-1.5 py-1 dark:hover:bg-gray-850transition rounded-lg"
 									on:click={() => {
 										createAPIKeyHandler();
 									}}
@ -416,7 +472,7 @@
 							</Tooltip>
 						{:else}
 							<button
-							class="flex gap-1.5 items-center font-medium px-3.5 py-1.5 rounded-lg bg-gray-100/70 hover:bg-gray-100 dark:bg-gray-850 dark:hover:bg-gray-800 transition"
+								class="flex gap-1.5 items-center font-medium px-3.5 py-1.5 rounded-lg bg-gray-100/70 hover:bg-gray-100 dark:bg-gray-850 dark:hover:bg-gray-850 transition"
 								on:click={() => {
 									createAPIKeyHandler();
 								}}
@ -429,6 +485,7 @@
 					</div>
 				</div>
 			</div>
+		{/if}
 	</div>

 	<div class="flex justify-end pt-3 text-sm font-medium">
--- a/src/lib/components/chat/Settings/General.svelte
+++ b/src/lib/components/chat/Settings/General.svelte
@ -185,7 +185,7 @@

 			<div>
 				<div class=" py-0.5 flex w-full justify-between">
-					<div class=" self-center text-xs font-medium">{$i18n.t('Desktop Notifications')}</div>
+					<div class=" self-center text-xs font-medium">{$i18n.t('Notifications')}</div>

 					<button
 						class="p-1 px-3 text-xs flex rounded transition"
--- a/src/lib/components/common/Modal.svelte
+++ b/src/lib/components/common/Modal.svelte
@ -7,6 +7,7 @@
 	export let show = true;
 	export let size = 'md';

+	let modalElement = null;
 	let mounted = false;

 	const sizeToWidth = (size) => {
@ -19,14 +20,23 @@
 		}
 	};

+	const handleKeyDown = (event: KeyboardEvent) => {
+		if (event.key === 'Escape') {
+			console.log('Escape');
+			show = false;
+		}
+	};
+
 	onMount(() => {
 		mounted = true;
 	});

 	$: if (mounted) {
 		if (show) {
+			window.addEventListener('keydown', handleKeyDown);
 			document.body.style.overflow = 'hidden';
 		} else {
+			window.removeEventListener('keydown', handleKeyDown);
 			document.body.style.overflow = 'unset';
 		}
 	}
@ -36,6 +46,7 @@
 	<!-- svelte-ignore a11y-click-events-have-key-events -->
 	<!-- svelte-ignore a11y-no-static-element-interactions -->
 	<div
+		bind:this={modalElement}
 		class=" fixed top-0 right-0 left-0 bottom-0 bg-black/60 w-full min-h-screen h-screen flex justify-center z-50 overflow-hidden overscroll-contain"
 		in:fade={{ duration: 10 }}
 		on:click={() => {
--- a/src/lib/components/documents/Settings/General.svelte
+++ b/src/lib/components/documents/Settings/General.svelte
@ -6,18 +6,23 @@
 		getQuerySettings,
 		scanDocs,
 		updateQuerySettings,
-		resetVectorDB
+		resetVectorDB,
+		getEmbeddingModel,
+		updateEmbeddingModel
 	} from '$lib/apis/rag';

 	import { documents } from '$lib/stores';
 	import { onMount, getContext } from 'svelte';
 	import { toast } from 'svelte-sonner';

+	import Tooltip from '$lib/components/common/Tooltip.svelte';
+
 	const i18n = getContext('i18n');

 	export let saveHandler: Function;

-	let loading = false;
+	let scanDirLoading = false;
+	let updateEmbeddingModelLoading = false;

 	let showResetConfirm = false;

@ -30,10 +35,12 @@
 		k: 4
 	};

+	let embeddingModel = '';
+
 	const scanHandler = async () => {
-		loading = true;
+		scanDirLoading = true;
 		const res = await scanDocs(localStorage.token);
-		loading = false;
+		scanDirLoading = false;

 		if (res) {
 			await documents.set(await getDocs(localStorage.token));
@ -41,6 +48,38 @@
 		}
 	};

+	const embeddingModelUpdateHandler = async () => {
+		if (embeddingModel.split('/').length - 1 > 1) {
+			toast.error(
+				$i18n.t(
+					'Model filesystem path detected. Model shortname is required for update, cannot continue.'
+				)
+			);
+			return;
+		}
+
+		console.log('Update embedding model attempt:', embeddingModel);
+
+		updateEmbeddingModelLoading = true;
+		const res = await updateEmbeddingModel(localStorage.token, {
+			embedding_model: embeddingModel
+		}).catch(async (error) => {
+			toast.error(error);
+			embeddingModel = (await getEmbeddingModel(localStorage.token)).embedding_model;
+			return null;
+		});
+		updateEmbeddingModelLoading = false;
+
+		if (res) {
+			console.log('embeddingModelUpdateHandler:', res);
+			if (res.status === true) {
+				toast.success($i18n.t('Model {{embedding_model}} update complete!', res), {
+					duration: 1000 * 10
+				});
+			}
+		}
+	};
+
 	const submitHandler = async () => {
 		const res = await updateRAGConfig(localStorage.token, {
 			pdf_extract_images: pdfExtractImages,
@ -62,6 +101,8 @@
 			chunkOverlap = res.chunk.chunk_overlap;
 		}

+		embeddingModel = (await getEmbeddingModel(localStorage.token)).embedding_model;
+
 		querySettings = await getQuerySettings(localStorage.token);
 	});
 </script>
@ -73,7 +114,7 @@
 		saveHandler();
 	}}
 >
-	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
+	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-[22rem]">
 		<div>
 			<div class=" mb-2 text-sm font-medium">{$i18n.t('General Settings')}</div>

@ -83,7 +124,7 @@
 				</div>

 				<button
-					class=" self-center text-xs p-1 px-3 bg-gray-100 dark:bg-gray-800 dark:hover:bg-gray-700 rounded flex flex-row space-x-1 items-center {loading
+					class=" self-center text-xs p-1 px-3 bg-gray-100 dark:bg-gray-800 dark:hover:bg-gray-700 rounded-lg flex flex-row space-x-1 items-center {scanDirLoading
 						? ' cursor-not-allowed'
 						: ''}"
 					on:click={() => {
@ -91,24 +132,11 @@
 						console.log('check');
 					}}
 					type="button"
-					disabled={loading}
+					disabled={scanDirLoading}
 				>
 					<div class="self-center font-medium">{$i18n.t('Scan')}</div>

-					<!-- <svg
-						xmlns="http://www.w3.org/2000/svg"
-						viewBox="0 0 16 16"
-						fill="currentColor"
-						class="w-3 h-3"
-					>
-						<path
-							fill-rule="evenodd"
-							d="M13.836 2.477a.75.75 0 0 1 .75.75v3.182a.75.75 0 0 1-.75.75h-3.182a.75.75 0 0 1 0-1.5h1.37l-.84-.841a4.5 4.5 0 0 0-7.08.932.75.75 0 0 1-1.3-.75 6 6 0 0 1 9.44-1.242l.842.84V3.227a.75.75 0 0 1 .75-.75Zm-.911 7.5A.75.75 0 0 1 13.199 11a6 6 0 0 1-9.44 1.241l-.84-.84v1.371a.75.75 0 0 1-1.5 0V9.591a.75.75 0 0 1 .75-.75H5.35a.75.75 0 0 1 0 1.5H3.98l.841.841a4.5 4.5 0 0 0 7.08-.932.75.75 0 0 1 1.025-.273Z"
-							clip-rule="evenodd"
-						/>
-					</svg> -->
-
-					{#if loading}
+					{#if scanDirLoading}
 						<div class="ml-3 self-center">
 							<svg
 								class=" w-3 h-3"
@ -141,6 +169,78 @@

 		<hr class=" dark:border-gray-700" />

+		<div class="space-y-2">
+			<div>
+				<div class=" mb-2 text-sm font-medium">{$i18n.t('Update Embedding Model')}</div>
+				<div class="flex w-full">
+					<div class="flex-1 mr-2">
+						<input
+							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+							placeholder={$i18n.t('Update embedding model (e.g. {{model}})', {
+								model: embeddingModel.slice(-40)
+							})}
+							bind:value={embeddingModel}
+						/>
+					</div>
+					<button
+						class="px-2.5 bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-850 dark:hover:bg-gray-800 dark:text-gray-100 rounded-lg transition"
+						on:click={() => {
+							embeddingModelUpdateHandler();
+						}}
+						disabled={updateEmbeddingModelLoading}
+					>
+						{#if updateEmbeddingModelLoading}
+							<div class="self-center">
+								<svg
+									class=" w-4 h-4"
+									viewBox="0 0 24 24"
+									fill="currentColor"
+									xmlns="http://www.w3.org/2000/svg"
+									><style>
+										.spinner_ajPY {
+											transform-origin: center;
+											animation: spinner_AtaB 0.75s infinite linear;
+										}
+										@keyframes spinner_AtaB {
+											100% {
+												transform: rotate(360deg);
+											}
+										}
+									</style><path
+										d="M12,1A11,11,0,1,0,23,12,11,11,0,0,0,12,1Zm0,19a8,8,0,1,1,8-8A8,8,0,0,1,12,20Z"
+										opacity=".25"
+									/><path
+										d="M10.14,1.16a11,11,0,0,0-9,8.92A1.59,1.59,0,0,0,2.46,12,1.52,1.52,0,0,0,4.11,10.7a8,8,0,0,1,6.66-6.61A1.42,1.42,0,0,0,12,2.69h0A1.57,1.57,0,0,0,10.14,1.16Z"
+										class="spinner_ajPY"
+									/></svg
+								>
+							</div>
+						{:else}
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 16 16"
+								fill="currentColor"
+								class="w-4 h-4"
+							>
+								<path
+									d="M8.75 2.75a.75.75 0 0 0-1.5 0v5.69L5.03 6.22a.75.75 0 0 0-1.06 1.06l3.5 3.5a.75.75 0 0 0 1.06 0l3.5-3.5a.75.75 0 0 0-1.06-1.06L8.75 8.44V2.75Z"
+								/>
+								<path
+									d="M3.5 9.75a.75.75 0 0 0-1.5 0v1.5A2.75 2.75 0 0 0 4.75 14h6.5A2.75 2.75 0 0 0 14 11.25v-1.5a.75.75 0 0 0-1.5 0v1.5c0 .69-.56 1.25-1.25 1.25h-6.5c-.69 0-1.25-.56-1.25-1.25v-1.5Z"
+								/>
+							</svg>
+						{/if}
+					</button>
+				</div>
+
+				<div class="mt-2 mb-1 text-xs text-gray-400 dark:text-gray-500">
+					{$i18n.t(
+						'Warning: If you update or change your embedding model, you will need to re-import all documents.'
+					)}
+				</div>
+
+				<hr class=" dark:border-gray-700 my-3" />
+
 				<div class=" ">
 					<div class=" text-sm font-medium">{$i18n.t('Chunk Params')}</div>

@ -150,7 +250,7 @@

 							<div class="self-center p-3">
 								<input
-							class=" w-full rounded py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none border border-gray-100 dark:border-gray-600"
+									class=" w-full rounded-lg py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
 									type="number"
 									placeholder={$i18n.t('Enter Chunk Size')}
 									bind:value={chunkSize}
@ -161,11 +261,13 @@
 						</div>

 						<div class="flex w-full">
-					<div class=" self-center text-xs font-medium min-w-fit">{$i18n.t('Chunk Overlap')}</div>
+							<div class=" self-center text-xs font-medium min-w-fit">
+								{$i18n.t('Chunk Overlap')}
+							</div>

 							<div class="self-center p-3">
 								<input
-							class="w-full rounded py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none border border-gray-100 dark:border-gray-600"
+									class="w-full rounded-lg py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
 									type="number"
 									placeholder={$i18n.t('Enter Chunk Overlap')}
 									bind:value={chunkOverlap}
@ -176,7 +278,7 @@
 						</div>
 					</div>

-			<div>
+					<div class="pr-2">
 						<div class="flex justify-between items-center text-xs">
 							<div class=" text-xs font-medium">{$i18n.t('PDF Extract Images (OCR)')}</div>

@ -191,6 +293,8 @@
 					</div>
 				</div>

+				<hr class=" dark:border-gray-700 my-3" />
+
 				<div>
 					<div class=" text-sm font-medium">{$i18n.t('Query Params')}</div>

@ -200,7 +304,7 @@

 							<div class="self-center p-3">
 								<input
-							class=" w-full rounded py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none border border-gray-100 dark:border-gray-600"
+									class=" w-full rounded-lg py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
 									type="number"
 									placeholder={$i18n.t('Enter Top K')}
 									bind:value={querySettings.k}
@ -209,34 +313,19 @@
 								/>
 							</div>
 						</div>
-
-				<!-- <div class="flex w-full">
-						<div class=" self-center text-xs font-medium min-w-fit">Chunk Overlap</div>
-	
-						<div class="self-center p-3">
-							<input
-								class="w-full rounded py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none border border-gray-100 dark:border-gray-600"
-								type="number"
-								placeholder="Enter Chunk Overlap"
-								bind:value={chunkOverlap}
-								autocomplete="off"
-								min="0"
-							/>
-						</div>
-					</div> -->
 					</div>

 					<div>
 						<div class=" mb-2.5 text-sm font-medium">{$i18n.t('RAG Template')}</div>
 						<textarea
 							bind:value={querySettings.template}
-					class="w-full rounded p-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none resize-none"
+							class="w-full rounded-lg px-4 py-3 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none resize-none"
 							rows="4"
 						/>
 					</div>
 				</div>

-		<hr class=" dark:border-gray-700" />
+				<hr class=" dark:border-gray-700 my-3" />

 				{#if showResetConfirm}
 					<div class="flex justify-between rounded-md items-center py-2 px-3.5 w-full transition">
@ -330,7 +419,8 @@
 					</button>
 				{/if}
 			</div>
-
+		</div>
+	</div>
 	<div class="flex justify-end pt-3 text-sm font-medium">
 		<button
 			class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
--- a/src/lib/i18n/locales/bg-BG/translation.json
+++ b/src/lib/i18n/locales/bg-BG/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "Изтрито {{deleteModelTag}}",
 	"Deleted {tagName}": "Изтрито {tagName}",
 	"Description": "Описание",
-	"Desktop Notifications": "Десктоп Известия",
+	"Notifications": "Десктоп Известия",
 	"Disabled": "Деактивиран",
 	"Discover a modelfile": "Откриване на модфайл",
 	"Discover a prompt": "Откриване на промпт",
--- a/src/lib/i18n/locales/ca-ES/translation.json
+++ b/src/lib/i18n/locales/ca-ES/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "Esborrat {{deleteModelTag}}",
 	"Deleted {tagName}": "Esborrat {tagName}",
 	"Description": "Descripció",
-	"Desktop Notifications": "Notificacions d'Escriptori",
+	"Notifications": "Notificacions d'Escriptori",
 	"Disabled": "Desactivat",
 	"Discover a modelfile": "Descobreix un fitxer de model",
 	"Discover a prompt": "Descobreix un prompt",
--- a/src/lib/i18n/locales/de-DE/translation.json
+++ b/src/lib/i18n/locales/de-DE/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} gelöscht",
 	"Deleted {tagName}": "{tagName} gelöscht",
 	"Description": "Beschreibung",
-	"Desktop Notifications": "Desktop-Benachrichtigungen",
+	"Notifications": "Desktop-Benachrichtigungen",
 	"Disabled": "Deaktiviert",
 	"Discover a modelfile": "Eine Modelfiles entdecken",
 	"Discover a prompt": "Einen Prompt entdecken",
--- a/src/lib/i18n/locales/en-GB/translation.json
+++ b/src/lib/i18n/locales/en-GB/translation.json
@ -0,0 +1,64 @@
+{
+	"analyze": "analyse",
+	"analyzed": "analysed",
+	"analyzes": "analyses",
+	"apologize": "apologise",
+	"apologized": "apologised",
+	"apologizes": "apologises",
+	"apologizing": "apologising",
+	"canceled": "cancelled",
+	"canceling": "cancelling",
+	"capitalize": "capitalise",
+	"capitalized": "capitalised",
+	"capitalizes": "capitalises",
+	"center": "centre",
+	"centered": "centred",
+	"color": "colour",
+	"colorize": "colourise",
+	"customize": "customise",
+	"customizes": "customises",
+	"defense": "defence",
+	"dialog": "dialogue",
+	"emphasize": "emphasise",
+	"emphasized": "emphasised",
+	"emphasizes": "emphasises",
+	"favor": "favour",
+	"favorable": "favourable",
+	"favorite": "favourite",
+	"favoritism": "favouritism",
+	"labor": "labour",
+	"labored": "laboured",
+	"laboring": "labouring",
+	"maximize": "maximise",
+	"maximizes": "maximises",
+	"minimize": "minimise",
+	"minimizes": "minimises",
+	"neighbor": "neighbour",
+	"neighborhood": "neighbourhood",
+	"offense": "offence",
+	"organize": "organise",
+	"organizes": "organises",
+	"personalize": "personalise",
+	"personalizes": "personalises",
+	"program": "programme",
+	"programmed": "programmed",
+	"programs": "programmes",
+	"quantization": "quantisation",
+	"quantize": "quantise",
+	"randomize": "randomise",
+	"randomizes": "randomises",
+	"realize": "realise",
+	"realizes": "realises",
+	"recognize": "recognise",
+	"recognizes": "recognises",
+	"summarize": "summarise",
+	"summarizes": "summarises",
+	"theater": "theatre",
+	"theaters": "theatres",
+	"toward": "towards",
+	"traveled": "travelled",
+	"traveler": "traveller",
+	"traveling": "travelling",
+	"utilize": "utilise",
+	"utilizes": "utilises"
+}
--- a/src/lib/i18n/locales/en-US/translation.json
+++ b/src/lib/i18n/locales/en-US/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "",
 	"Deleted {tagName}": "",
 	"Description": "",
-	"Desktop Notifications": "",
+	"Notifications": "",
 	"Disabled": "",
 	"Discover a modelfile": "",
 	"Discover a prompt": "",
@ -120,6 +120,7 @@
 	"Edit Doc": "",
 	"Edit User": "",
 	"Email": "",
+	"Embedding model: {{embedding_model}}": "",
 	"Enable Chat History": "",
 	"Enable New Sign Ups": "",
 	"Enabled": "",
@ -150,6 +151,7 @@
 	"Failed to read clipboard contents": "",
 	"File Mode": "",
 	"File not found.": "",
+	"Fingerprint spoofing detected: Unable to use initials as avatar. Defaulting to default profile image.": "",
 	"Focus chat input": "",
 	"Format your variables using square brackets like this:": "",
 	"From (Base Model)": "",
@ -193,8 +195,11 @@
 	"MMMM DD, YYYY": "",
 	"Model '{{modelName}}' has been successfully downloaded.": "",
 	"Model '{{modelTag}}' is already in queue for downloading.": "",
+	"Model {{embedding_model}} update complete!": "",
+	"Model {{embedding_model}} update failed or not required!": "",
 	"Model {{modelId}} not found": "",
 	"Model {{modelName}} already exists.": "",
+	"Model filesystem path detected. Model shortname is required for update, cannot continue.": "",
 	"Model Name": "",
 	"Model not selected": "",
 	"Model Tag Name": "",
@ -332,7 +337,10 @@
 	"TTS Settings": "",
 	"Type Hugging Face Resolve (Download) URL": "",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "",
+	"Understand that updating or changing your embedding model requires reset of the vector database and re-import of all documents. You have been warned!": "",
 	"Unknown File Type '{{file_type}}', but accepting and treating as plain text": "",
+	"Update": "",
+	"Update embedding model {{embedding_model}}": "",
 	"Update password": "",
 	"Upload a GGUF model": "",
 	"Upload files": "",
@ -340,6 +348,7 @@
 	"URL Mode": "",
 	"Use '#' in the prompt input to load and select your documents.": "",
 	"Use Gravatar": "",
+	"Use Initials": "",
 	"user": "",
 	"User Permissions": "",
 	"Users": "",
--- a/src/lib/i18n/locales/es-ES/translation.json
+++ b/src/lib/i18n/locales/es-ES/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "Se borró {{deleteModelTag}}",
 	"Deleted {tagName}": "Se borró {tagName}",
 	"Description": "Descripción",
-	"Desktop Notifications": "Notificaciones",
+	"Notifications": "Notificaciones",
 	"Disabled": "Desactivado",
 	"Discover a modelfile": "Descubre un modelfile",
 	"Discover a prompt": "Descubre un Prompt",
--- a/src/lib/i18n/locales/fa-IR/translation.json
+++ b/src/lib/i18n/locales/fa-IR/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} پاک شد",
 	"Deleted {tagName}": "{tagName} حذف شد",
 	"Description": "توضیحات",
-	"Desktop Notifications": "اعلان",
+	"Notifications": "اعلان",
 	"Disabled": "غیرفعال",
 	"Discover a modelfile": "فایل مدل را کشف کنید",
 	"Discover a prompt": "یک اعلان را کشف کنید",
--- a/src/lib/i18n/locales/fr-CA/translation.json
+++ b/src/lib/i18n/locales/fr-CA/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} supprimé",
 	"Deleted {tagName}": "{tagName} supprimé",
 	"Description": "Description",
-	"Desktop Notifications": "Notifications de bureau",
+	"Notifications": "Notifications de bureau",
 	"Disabled": "Désactivé",
 	"Discover a modelfile": "Découvrir un fichier de modèle",
 	"Discover a prompt": "Découvrir un prompt",
--- a/src/lib/i18n/locales/fr-FR/translation.json
+++ b/src/lib/i18n/locales/fr-FR/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} supprimé",
 	"Deleted {tagName}": "{tagName} supprimé",
 	"Description": "Description",
-	"Desktop Notifications": "Notifications de bureau",
+	"Notifications": "Notifications de bureau",
 	"Disabled": "Désactivé",
 	"Discover a modelfile": "Découvrir un fichier de modèle",
 	"Discover a prompt": "Découvrir un prompt",
--- a/src/lib/i18n/locales/it-IT/translation.json
+++ b/src/lib/i18n/locales/it-IT/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "Eliminato {{deleteModelTag}}",
 	"Deleted {tagName}": "Eliminato {tagName}",
 	"Description": "Descrizione",
-	"Desktop Notifications": "Notifiche desktop",
+	"Notifications": "Notifiche desktop",
 	"Disabled": "Disabilitato",
 	"Discover a modelfile": "Scopri un file modello",
 	"Discover a prompt": "Scopri un prompt",
--- a/src/lib/i18n/locales/ja-JP/translation.json
+++ b/src/lib/i18n/locales/ja-JP/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} を削除しました",
 	"Deleted {tagName}": "{tagName} を削除しました",
 	"Description": "説明",
-	"Desktop Notifications": "デスクトップ通知",
+	"Notifications": "デスクトップ通知",
 	"Disabled": "無効",
 	"Discover a modelfile": "モデルファイルを見つける",
 	"Discover a prompt": "プロンプトを見つける",
--- a/src/lib/i18n/locales/ko-KR/translation.json
+++ b/src/lib/i18n/locales/ko-KR/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} 삭제됨",
 	"Deleted {tagName}": "{tagName} 삭제됨",
 	"Description": "설명",
-	"Desktop Notifications": "알림",
+	"Notifications": "알림",
 	"Disabled": "비활성화",
 	"Discover a modelfile": "모델파일 검색",
 	"Discover a prompt": "프롬프트 검색",
--- a/src/lib/i18n/locales/languages.json
+++ b/src/lib/i18n/locales/languages.json
@ -15,6 +15,10 @@
 		"code": "de-DE",
 		"title": "Deutsch"
 	},
+	{
+		"code": "en-GB",
+		"title": "English (GB)"
+	},
 	{
 		"code": "es-ES",
 		"title": "Spanish"
--- a/src/lib/i18n/locales/nl-NL/translation.json
+++ b/src/lib/i18n/locales/nl-NL/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} is verwijderd",
 	"Deleted {tagName}": "{tagName} is verwijderd",
 	"Description": "Beschrijving",
-	"Desktop Notifications": "Desktop Notificaties",
+	"Notifications": "Desktop Notificaties",
 	"Disabled": "Uitgeschakeld",
 	"Discover a modelfile": "Ontdek een modelfile",
 	"Discover a prompt": "Ontdek een prompt",
--- a/src/lib/i18n/locales/pt-BR/translation.json
+++ b/src/lib/i18n/locales/pt-BR/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} excluído",
 	"Deleted {tagName}": "{tagName} excluído",
 	"Description": "Descrição",
-	"Desktop Notifications": "Notificações da Área de Trabalho",
+	"Notifications": "Notificações da Área de Trabalho",
 	"Disabled": "Desativado",
 	"Discover a modelfile": "Descobrir um arquivo de modelo",
 	"Discover a prompt": "Descobrir um prompt",
--- a/src/lib/i18n/locales/pt-PT/translation.json
+++ b/src/lib/i18n/locales/pt-PT/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} excluído",
 	"Deleted {tagName}": "{tagName} excluído",
 	"Description": "Descrição",
-	"Desktop Notifications": "Notificações da Área de Trabalho",
+	"Notifications": "Notificações da Área de Trabalho",
 	"Disabled": "Desativado",
 	"Discover a modelfile": "Descobrir um arquivo de modelo",
 	"Discover a prompt": "Descobrir um prompt",
--- a/src/lib/i18n/locales/ru-RU/translation.json
+++ b/src/lib/i18n/locales/ru-RU/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "Удалено {{deleteModelTag}}",
 	"Deleted {tagName}": "Удалено {tagName}",
 	"Description": "Описание",
-	"Desktop Notifications": "Уведомления на рабочем столе",
+	"Notifications": "Уведомления на рабочем столе",
 	"Disabled": "Отключено",
 	"Discover a modelfile": "Найти файл модели",
 	"Discover a prompt": "Найти промт",
--- a/src/lib/i18n/locales/tr-TR/translation.json
+++ b/src/lib/i18n/locales/tr-TR/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} silindi",
 	"Deleted {tagName}": "{tagName} silindi",
 	"Description": "Açıklama",
-	"Desktop Notifications": "Masaüstü Bildirimleri",
+	"Notifications": "Bildirimler",
 	"Disabled": "Devre Dışı",
 	"Discover a modelfile": "Bir model dosyası keşfedin",
 	"Discover a prompt": "Bir prompt keşfedin",
--- a/src/lib/i18n/locales/uk-UA/translation.json
+++ b/src/lib/i18n/locales/uk-UA/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "Видалено {{deleteModelTag}}",
 	"Deleted {tagName}": "Видалено {tagName}",
 	"Description": "Опис",
-	"Desktop Notifications": "Сповіщення",
+	"Notifications": "Сповіщення",
 	"Disabled": "Вимкнено",
 	"Discover a modelfile": "Знайти файл моделі",
 	"Discover a prompt": "Знайти промт",
--- a/src/lib/i18n/locales/vi-VN/translation.json
+++ b/src/lib/i18n/locales/vi-VN/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "Đã xóa {{deleteModelTag}}",
 	"Deleted {tagName}": "Đã xóa {tagName}",
 	"Description": "Mô tả",
-	"Desktop Notifications": "Thông báo trên máy tính (Notification)",
+	"Notifications": "Thông báo trên máy tính (Notification)",
 	"Disabled": "Đã vô hiệu hóa",
 	"Discover a modelfile": "Khám phá thêm các mô hình mới",
 	"Discover a prompt": "Khám phá thêm prompt mới",
--- a/src/lib/i18n/locales/zh-CN/translation.json
+++ b/src/lib/i18n/locales/zh-CN/translation.json
@ -100,7 +100,7 @@
 	"Deleted {{deleteModelTag}}": "已删除{{deleteModelTag}}",
 	"Deleted {tagName}": "已删除{tagName}",
 	"Description": "描述",
-	"Desktop Notifications": "桌面通知",
+	"Notifications": "桌面通知",
 	"Disabled": "禁用",
 	"Discover a modelfile": "探索模型文件",
 	"Discover a prompt": "探索提示词",
--- a/src/lib/i18n/locales/zh-TW/translation.json
+++ b/src/lib/i18n/locales/zh-TW/translation.json
@ -101,7 +101,7 @@
 	"Deleted {{deleteModelTag}}": "已刪除 {{deleteModelTag}}",
 	"Deleted {tagName}": "已刪除 {tagName}",
 	"Description": "描述",
-	"Desktop Notifications": "桌面通知",
+	"Notifications": "桌面通知",
 	"Disabled": "已停用",
 	"Discover a modelfile": "發現新 Modelfile",
 	"Discover a prompt": "發現新提示詞",
--- a/src/lib/utils/index.ts
+++ b/src/lib/utils/index.ts
@ -111,6 +111,82 @@ export const getGravatarURL = (email) => {
 	return `https://www.gravatar.com/avatar/${hash}`;
 };

+export const canvasPixelTest = () => {
+	// Test a 1x1 pixel to potentially identify browser/plugin fingerprint blocking or spoofing
+	// Inspiration: https://github.com/kkapsner/CanvasBlocker/blob/master/test/detectionTest.js
+	const canvas = document.createElement('canvas');
+	const ctx = canvas.getContext('2d');
+	canvas.height = 1;
+	canvas.width = 1;
+	const imageData = new ImageData(canvas.width, canvas.height);
+	const pixelValues = imageData.data;
+
+	// Generate RGB test data
+	for (let i = 0; i < imageData.data.length; i += 1) {
+		if (i % 4 !== 3) {
+			pixelValues[i] = Math.floor(256 * Math.random());
+		} else {
+			pixelValues[i] = 255;
+		}
+	}
+
+	ctx.putImageData(imageData, 0, 0);
+	const p = ctx.getImageData(0, 0, canvas.width, canvas.height).data;
+
+	// Read RGB data and fail if unmatched
+	for (let i = 0; i < p.length; i += 1) {
+		if (p[i] !== pixelValues[i]) {
+			console.log(
+				'canvasPixelTest: Wrong canvas pixel RGB value detected:',
+				p[i],
+				'at:',
+				i,
+				'expected:',
+				pixelValues[i]
+			);
+			console.log('canvasPixelTest: Canvas blocking or spoofing is likely');
+			return false;
+		}
+	}
+
+	return true;
+};
+
+export const generateInitialsImage = (name) => {
+	const canvas = document.createElement('canvas');
+	const ctx = canvas.getContext('2d');
+	canvas.width = 100;
+	canvas.height = 100;
+
+	if (!canvasPixelTest()) {
+		console.log(
+			'generateInitialsImage: failed pixel test, fingerprint evasion is likely. Using default image.'
+		);
+		return '/user.png';
+	}
+
+	ctx.fillStyle = '#F39C12';
+	ctx.fillRect(0, 0, canvas.width, canvas.height);
+
+	ctx.fillStyle = '#FFFFFF';
+	ctx.font = '40px Helvetica';
+	ctx.textAlign = 'center';
+	ctx.textBaseline = 'middle';
+
+	const sanitizedName = name.trim();
+	const initials =
+		sanitizedName.length > 0
+			? sanitizedName[0] +
+			  (sanitizedName.split(' ').length > 1
+					? sanitizedName[sanitizedName.lastIndexOf(' ') + 1]
+					: '')
+			: '';
+
+	ctx.fillText(initials.toUpperCase(), canvas.width / 2, canvas.height / 2);
+
+	return canvas.toDataURL();
+};
+
 export const copyToClipboard = (text) => {
 	if (!navigator.clipboard) {
 		const textArea = document.createElement('textarea');
--- a/src/routes/(app)/admin/+page.svelte
+++ b/src/routes/(app)/admin/+page.svelte
@ -4,6 +4,8 @@
 	import { goto } from '$app/navigation';
 	import { onMount, getContext } from 'svelte';

+	import dayjs from 'dayjs';
+
 	import { toast } from 'svelte-sonner';

 	import { updateUserRole, getUsers, deleteUserById } from '$lib/apis/users';
@ -16,6 +18,7 @@
 	let loaded = false;
 	let users = [];

+	let search = '';
 	let selectedUser = null;

 	let showSettingsModal = false;
@ -80,20 +83,15 @@

 <SettingsModal bind:show={showSettingsModal} />

-<div class="min-h-screen max-h-[100dvh] w-full flex justify-center dark:text-white font-mona">
+<div class="min-h-screen max-h-[100dvh] w-full flex justify-center dark:text-white">
 	{#if loaded}
 		<div class=" flex flex-col justify-between w-full overflow-y-auto">
-			<div class="max-w-2xl mx-auto w-full px-3 md:px-0 my-10">
+			<div class=" mx-auto w-full">
 				<div class="w-full">
 					<div class=" flex flex-col justify-center">
+						<div class=" px-5 pt-3">
 							<div class=" flex justify-between items-center">
-							<div class="flex items-center text-2xl font-semibold">
-								{$i18n.t('All Users')}
-								<div class="flex self-center w-[1px] h-6 mx-2.5 bg-gray-200 dark:bg-gray-700" />
-								<span class="text-lg font-medium text-gray-500 dark:text-gray-300"
-									>{users.length}</span
-								>
-							</div>
+								<div class="flex items-center text-2xl font-semibold">Dashboard</div>
 								<div>
 									<button
 										class="flex items-center space-x-1 px-3 py-1.5 rounded-xl bg-gray-50 hover:bg-gray-100 dark:bg-gray-800 dark:hover:bg-gray-700 transition"
@ -119,32 +117,64 @@
 									</button>
 								</div>
 							</div>
-						<div class=" text-gray-500 text-xs mt-1">
-							ⓘ {$i18n.t("Click on the user role button to change a user's role.")}
 						</div>

-						<hr class=" my-3 dark:border-gray-600" />
+						<div class="px-5 flex text-sm gap-2.5">
+							<div class="py-3 border-b font-medium text-gray-100 cursor-pointer">Overview</div>
+							<!-- <div class="py-3 text-gray-300 cursor-pointer">Users</div> -->
+						</div>
+
+						<hr class=" mb-3 dark:border-gray-800" />
+
+						<div class="px-5">
+							<div class="mt-0.5 mb-3 flex justify-between">
+								<div class="flex text-lg font-medium px-0.5">
+									{$i18n.t('All Users')}
+									<div class="flex self-center w-[1px] h-6 mx-2.5 bg-gray-200 dark:bg-gray-700" />
+									<span class="text-lg font-medium text-gray-500 dark:text-gray-300"
+										>{users.length}</span
+									>
+								</div>
+
+								<div class="">
+									<input
+										class=" w-60 rounded-lg py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+										placeholder={$i18n.t('Search')}
+										bind:value={search}
+									/>
+								</div>
+							</div>

 							<div class="scrollbar-hidden relative overflow-x-auto whitespace-nowrap">
 								<table class="w-full text-sm text-left text-gray-500 dark:text-gray-400 table-auto">
 									<thead
-									class="text-xs text-gray-700 uppercase bg-gray-50 dark:bg-gray-700 dark:text-gray-400"
+										class="text-xs text-gray-700 uppercase bg-gray-50 dark:bg-gray-850 dark:text-gray-400"
 									>
 										<tr>
 											<th scope="col" class="px-3 py-2"> {$i18n.t('Role')} </th>
 											<th scope="col" class="px-3 py-2"> {$i18n.t('Name')} </th>
 											<th scope="col" class="px-3 py-2"> {$i18n.t('Email')} </th>
-										<th scope="col" class="px-3 py-2"> {$i18n.t('Action')} </th>
+											<th scope="col" class="px-3 py-2"> {$i18n.t('Created at')} </th>
+											<th scope="col" class="px-3 py-2 text-right" />
 										</tr>
 									</thead>
 									<tbody>
-									{#each users as user}
+										{#each users.filter((user) => {
+											if (search === '') {
+												return true;
+											} else {
+												let name = user.name.toLowerCase();
+												const query = search.toLowerCase();
+												return name.includes(query);
+											}
+										}) as user}
 											<tr class="bg-white border-b dark:bg-gray-900 dark:border-gray-700 text-xs">
 												<td class="px-3 py-2 min-w-[7rem] w-28">
 													<button
 														class=" flex items-center gap-2 text-xs px-3 py-0.5 rounded-lg {user.role ===
 															'admin' &&
-														'text-sky-600 dark:text-sky-200 bg-sky-200/30'} {user.role === 'user' &&
+															'text-sky-600 dark:text-sky-200 bg-sky-200/30'} {user.role ===
+															'user' &&
 															'text-green-600 dark:text-green-200 bg-green-200/30'} {user.role ===
 															'pending' && 'text-gray-600 dark:text-gray-200 bg-gray-200/30'}"
 														on:click={() => {
@ -180,7 +210,11 @@
 												<td class=" px-3 py-2"> {user.email} </td>

 												<td class=" px-3 py-2">
-												<div class="flex justify-start w-full">
+													{dayjs(user.timestamp * 1000).format($i18n.t('MMMM DD, YYYY'))}
+												</td>
+
+												<td class="px-3 py-2 text-right">
+													<div class="flex justify-end w-full">
 														<button
 															class="self-center w-fit text-sm px-2 py-2 hover:bg-black/5 dark:hover:bg-white/5 rounded-xl"
 															on:click={async () => {
@ -232,6 +266,11 @@
 									</tbody>
 								</table>
 							</div>
+
+							<div class=" text-gray-500 text-xs mt-2 text-right">
+								ⓘ {$i18n.t("Click on the user role button to change a user's role.")}
+							</div>
+						</div>
 					</div>
 				</div>
 			</div>
--- a/src/routes/auth/+page.svelte
+++ b/src/routes/auth/+page.svelte
@ -6,6 +6,7 @@
 	import { WEBUI_NAME, config, user } from '$lib/stores';
 	import { onMount, getContext } from 'svelte';
 	import { toast } from 'svelte-sonner';
+	import { generateInitialsImage, canvasPixelTest } from '$lib/utils';

 	const i18n = getContext('i18n');

@ -36,10 +37,12 @@
 	};

 	const signUpHandler = async () => {
-		const sessionUser = await userSignUp(name, email, password).catch((error) => {
+		const sessionUser = await userSignUp(name, email, password, generateInitialsImage(name)).catch(
+			(error) => {
 				toast.error(error);
 				return null;
-		});
+			}
+		);

 		await setSessionUser(sessionUser);
 	};