tdpeuter/open-webui
tdpeuter/open-webui
1
Fork 0
forked from open-webui/open-webui
Code Issues Pull requests 1 Releases 2 Packages Activity Actions

Merge pull request #897 from open-webui/main

Browse source 
dev
This commit is contained in:
Timothy Jaeryang Baek 2024-02-24 18:59:16 -05:00 committed by GitHub
commit 437d7ff6f5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
155 changed files with 13322 additions and 5133 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
.dockerignore
View file

@ -1,4 +1,7 @@
.github
.DS_Store
docs
kubernetes
node_modules
/.svelte-kit
/package

8
example.env → .env.example
View file

@ -3,4 +3,10 @@
OLLAMA_API_BASE_URL='http://localhost:11434/api'
OPENAI_API_BASE_URL=''
OPENAI_API_KEY=''
OPENAI_API_KEY=''
# AUTOMATIC1111_BASE_URL="http://localhost:7860"
# DO NOT TRACK
SCARF_NO_ANALYTICS=true
DO_NOT_TRACK=true

1
.gitattributes vendored Normal file
View file

@ -0,0 +1 @@
*.sh text eol=lf

32
.github/pull_request_template.md vendored Normal file
View file

@ -0,0 +1,32 @@
## Pull Request Checklist
- [ ] **Description:** Briefly describe the changes in this pull request.
- [ ] **Changelog:** Ensure a changelog entry following the format of [Keep a Changelog](https://keepachangelog.com/) is added at the bottom of the PR description.
- [ ] **Documentation:** Have you updated relevant documentation?
- [ ] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation?
---
## Description
[Insert a brief description of the changes made in this pull request]
---
### Changelog Entry
### Added
- [List any new features or additions]
### Fixed
- [List any fixes or corrections]
### Changed
- [List any changes or updates]
### Removed
- [List any removed features or files]

49
.github/workflows/build-release.yml vendored Normal file
View file

@ -0,0 +1,49 @@
name: Release
on:
push:
branches:
- main # or whatever branch you want to use
jobs:
release:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v2
- name: Check for changes in package.json
run: |
git diff --cached --diff-filter=d package.json || {
echo "No changes to package.json"
exit 1
}
- name: Get version number from package.json
id: get_version
run: |
VERSION=$(jq -r '.version' package.json)
echo "::set-output name=version::$VERSION"
- name: Create GitHub release
uses: actions/github-script@v5
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
script: |
const release = await github.rest.repos.createRelease({
owner: context.repo.owner,
repo: context.repo.repo,
tag_name: `v${{ steps.get_version.outputs.version }}`,
name: `v${{ steps.get_version.outputs.version }}`,
body: 'Automatically created new release',
})
console.log(`Created release ${release.data.html_url}`)
- name: Upload package to GitHub release
uses: actions/upload-artifact@v3
with:
name: package
path: .
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

16
.github/workflows/docker-build.yaml vendored
View file

@ -40,15 +40,21 @@ jobs:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
# This step uses [docker/metadata-action](https://github.com/docker/metadata-action#about) to extract tags and labels that will be applied to the specified image. The `id` "meta" allows the output of this step to be referenced in a subsequent step. The `images` value provides the base name for the tags and labels.
- name: Extract metadata (tags, labels) for Docker
- name: Extract metadata for Docker images
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
# This step uses the `docker/build-push-action` action to build the image, based on your repository's `Dockerfile`. If the build succeeds, it pushes the image to GitHub Packages.
# It uses the `context` parameter to define the build's context as the set of files located in the specified path. For more information, see "[Usage](https://github.com/docker/build-push-action#usage)" in the README of the `docker/build-push-action` repository.
# It uses the `tags` and `labels` parameters to tag and label the image with the output from the "meta" step.
# This configuration dynamically generates tags based on the branch, tag, commit, and custom suffix for lite version.
tags: |
type=ref,event=branch
type=ref,event=tag
type=sha,prefix=git-
type=semver,pattern={{version}}
flavor: |
latest=${{ github.ref == 'refs/heads/main' }}
- name: Build and push Docker image
uses: docker/build-push-action@v5
with:

25
CHANGELOG.md Normal file
View file

@ -0,0 +1,25 @@
# Changelog
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).
## [0.1.102] - 2024-02-22
### Added
- **🖼️ Image Generation**: Generate Images using the AUTOMATIC1111/stable-diffusion-webui API. You can set this up in Settings > Images.
- **📝 Change title generation prompt**: Change the prompt used to generate titles for your chats. You can set this up in the Settings > Interface.
- **🤖 Change embedding model**: Change the embedding model used to generate embeddings for your chats in the Dockerfile. Use any sentence transformer model from huggingface.co.
- **📢 CHANGELOG.md/Popup**: This popup will show you the latest changes.
## [0.1.101] - 2024-02-22
### Fixed
- LaTex output formatting issue (#828)
### Changed
- Instead of having the previous 1.0.0-alpha.101, we switched to semantic versioning as a way to respect global conventions.

61
Dockerfile
View file

@ -5,9 +5,10 @@ FROM node:alpine 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"
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 ./
COPY package.json package-lock.json ./
RUN npm ci
COPY . .
@ -17,35 +18,65 @@ RUN npm run build
FROM python:3.11-slim-bookworm as base
ENV ENV=prod
ENV PORT ""
ENV OLLAMA_API_BASE_URL "/ollama/api"
ENV OPENAI_API_BASE_URL ""
ENV OPENAI_API_KEY ""
ENV WEBUI_JWT_SECRET_KEY "SECRET_KEY"
ENV WEBUI_SECRET_KEY ""
WORKDIR /app
ENV SCARF_NO_ANALYTICS true
ENV DO_NOT_TRACK true
# copy embedding weight from build
RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
COPY --from=build /app/onnx.tar.gz /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
######## Preloaded models ########
# whisper TTS Settings
ENV WHISPER_MODEL="base"
ENV WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models"
RUN cd /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2 &&\
tar -xzf onnx.tar.gz
# 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 ebbeding 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
# copy built frontend files
COPY --from=build /app/build /app/build
######## Preloaded models ########
WORKDIR /app/backend
# install python dependencies
COPY ./backend/requirements.txt ./requirements.txt
RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
RUN pip3 install -r requirements.txt
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
# RUN python -c "from sentence_transformers import SentenceTransformer; model = SentenceTransformer('all-MiniLM-L6-v2')"
# 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
# copy built frontend files
COPY --from=build /app/build /app/build
COPY --from=build /app/CHANGELOG.md /app/CHANGELOG.md
COPY --from=build /app/package.json /app/package.json
# copy backend files
COPY ./backend .
CMD [ "sh", "start.sh"]
CMD [ "bash", "start.sh"]

4
INSTALLATION.md
View file

@ -1,4 +1,4 @@
### Installing Both Ollama and Ollama Web UI Using Kustomize
### Installing Both Ollama and Open WebUI Using Kustomize
For cpu-only pod
@ -12,7 +12,7 @@ For gpu-enabled pod
kubectl apply -k ./kubernetes/manifest
```
### Installing Both Ollama and Ollama Web UI Using Helm
### Installing Both Ollama and Open WebUI Using Helm
Package Helm file first

243
README.md
View file

@ -1,23 +1,19 @@
# Ollama Web UI: A User-Friendly Web Interface for Chat Interactions 👋
# Open WebUI (Formerly Ollama WebUI) 👋
![GitHub stars](https://img.shields.io/github/stars/ollama-webui/ollama-webui?style=social)
![GitHub forks](https://img.shields.io/github/forks/ollama-webui/ollama-webui?style=social)
![GitHub watchers](https://img.shields.io/github/watchers/ollama-webui/ollama-webui?style=social)
![GitHub repo size](https://img.shields.io/github/repo-size/ollama-webui/ollama-webui)
![GitHub language count](https://img.shields.io/github/languages/count/ollama-webui/ollama-webui)
![GitHub top language](https://img.shields.io/github/languages/top/ollama-webui/ollama-webui)
![GitHub last commit](https://img.shields.io/github/last-commit/ollama-webui/ollama-webui?color=red)
![GitHub stars](https://img.shields.io/github/stars/open-webui/open-webui?style=social)
![GitHub forks](https://img.shields.io/github/forks/open-webui/open-webui?style=social)
![GitHub watchers](https://img.shields.io/github/watchers/open-webui/open-webui?style=social)
![GitHub repo size](https://img.shields.io/github/repo-size/open-webui/open-webui)
![GitHub language count](https://img.shields.io/github/languages/count/open-webui/open-webui)
![GitHub top language](https://img.shields.io/github/languages/top/open-webui/open-webui)
![GitHub last commit](https://img.shields.io/github/last-commit/open-webui/open-webui?color=red)
![Hits](https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2Follama-webui%2Follama-wbui&count_bg=%2379C83D&title_bg=%23555555&icon=&icon_color=%23E7E7E7&title=hits&edge_flat=false)
[![Discord](https://img.shields.io/badge/Discord-Ollama_Web_UI-blue?logo=discord&logoColor=white)](https://discord.gg/5rJgQTnV4s)
[![Discord](https://img.shields.io/badge/Discord-Open_WebUI-blue?logo=discord&logoColor=white)](https://discord.gg/5rJgQTnV4s)
[![](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=%23fe8e86)](https://github.com/sponsors/tjbck)
ChatGPT-Style Web Interface for Ollama 🦙
User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs. For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
**Disclaimer:** _ollama-webui is a community-driven project and is not affiliated with the Ollama team in any way. This initiative is independent, and any inquiries or feedback should be directed to [our community on Discord](https://discord.gg/5rJgQTnV4s). We kindly request users to refrain from contacting or harassing the Ollama team regarding this project._
![Ollama Web UI Demo](./demo.gif)
Also check our sibling project, [OllamaHub](https://ollamahub.com/), where you can discover, download, and explore customized Modelfiles for Ollama! 🦙🔍
![Open WebUI Demo](./demo.gif)
## Features ⭐
@ -33,12 +29,16 @@ Also check our sibling project, [OllamaHub](https://ollamahub.com/), where you c
- ✒️🔢 **Full Markdown and LaTeX Support**: Elevate your LLM experience with comprehensive Markdown and LaTeX capabilities for enriched interaction.
- 📚 **Local RAG Integration (Alpha)**: Immerse yourself in cutting-edge Retrieval Augmented Generation support, revolutionizing your chat experience by seamlessly incorporating document interactions. In its alpha phase, expect occasional issues as we actively refine and enhance this feature to ensure optimal performance and reliability.
- 📚 **Local RAG Integration**: Dive into the future of chat interactions with the groundbreaking Retrieval Augmented Generation (RAG) support. This feature seamlessly integrates document interactions into your chat experience. You can load documents directly into the chat or add files to your document library, effortlessly accessing them using `#` command in the prompt. In its alpha phase, occasional issues may arise as we actively refine and enhance this feature to ensure optimal performance and reliability.
- 📜 **Prompt Preset Support**: Instantly access preset prompts using the '/' command in the chat input. Load predefined conversation starters effortlessly and expedite your interactions. Effortlessly import prompts through [OllamaHub](https://ollamahub.com/) integration.
- 🌐 **Web Browsing Capability**: Seamlessly integrate websites into your chat experience using the `#` command followed by the URL. This feature allows you to incorporate web content directly into your conversations, enhancing the richness and depth of your interactions.
- 📜 **Prompt Preset Support**: Instantly access preset prompts using the `/` command in the chat input. Load predefined conversation starters effortlessly and expedite your interactions. Effortlessly import prompts through [Open WebUI Community](https://openwebui.com/) integration.
- 👍👎 **RLHF Annotation**: Empower your messages by rating them with thumbs up and thumbs down, facilitating the creation of datasets for Reinforcement Learning from Human Feedback (RLHF). Utilize your messages to train or fine-tune models, all while ensuring the confidentiality of locally saved data.
- 🏷️ **Conversation Tagging**: Effortlessly categorize and locate specific chats for quick reference and streamlined data collection.
- 📥🗑️ **Download/Delete Models**: Easily download or remove models directly from the web UI.
- ⬆️ **GGUF File Model Creation**: Effortlessly create Ollama models by uploading GGUF files directly from the web UI. Streamlined process with options to upload from your machine or download GGUF files from Hugging Face.
@ -47,10 +47,12 @@ Also check our sibling project, [OllamaHub](https://ollamahub.com/), where you c
- 🔄 **Multi-Modal Support**: Seamlessly engage with models that support multimodal interactions, including images (e.g., LLava).
- 🧩 **Modelfile Builder**: Easily create Ollama modelfiles via the web UI. Create and add characters/agents, customize chat elements, and import modelfiles effortlessly through [OllamaHub](https://ollamahub.com/) integration.
- 🧩 **Modelfile Builder**: Easily create Ollama modelfiles via the web UI. Create and add characters/agents, customize chat elements, and import modelfiles effortlessly through [Open WebUI Community](https://openwebui.com/) integration.
- ⚙️ **Many Models Conversations**: Effortlessly engage with various models simultaneously, harnessing their unique strengths for optimal responses. Enhance your experience by leveraging a diverse set of models in parallel.
- 💬 **Collaborative Chat**: Harness the collective intelligence of multiple models by seamlessly orchestrating group conversations. Use the `@` command to specify the model, enabling dynamic and diverse dialogues within your chat interface. Immerse yourself in the collective intelligence woven into your chat environment.
- 🤝 **OpenAI API Integration**: Effortlessly integrate OpenAI-compatible API for versatile conversations alongside Ollama models. Customize the API Base URL to link with **LMStudio, Mistral, OpenRouter, and more**.
- 🔄 **Regeneration History Access**: Easily revisit and explore your entire regeneration history.
@ -67,193 +69,65 @@ Also check our sibling project, [OllamaHub](https://ollamahub.com/), where you c
- 🔐 **Role-Based Access Control (RBAC)**: Ensure secure access with restricted permissions; only authorized individuals can access your Ollama, and exclusive model creation/pulling rights are reserved for administrators.
- 🔒 **Backend Reverse Proxy Support**: Bolster security through direct communication between Ollama Web UI backend and Ollama. This key feature eliminates the need to expose Ollama over LAN. Requests made to the '/ollama/api' route from the web UI are seamlessly redirected to Ollama from the backend, enhancing overall system security.
- 🔒 **Backend Reverse Proxy Support**: Bolster security through direct communication between Open WebUI backend and Ollama. This key feature eliminates the need to expose Ollama over LAN. Requests made to the '/ollama/api' route from the web UI are seamlessly redirected to Ollama from the backend, enhancing overall system security.
- 🌟 **Continuous Updates**: We are committed to improving Ollama Web UI with regular updates and new features.
- 🌟 **Continuous Updates**: We are committed to improving Open WebUI with regular updates and new features.
## 🔗 Also Check Out OllamaHub!
## 🔗 Also Check Out Open WebUI Community!
Don't forget to explore our sibling project, [OllamaHub](https://ollamahub.com/), where you can discover, download, and explore customized Modelfiles. OllamaHub offers a wide range of exciting possibilities for enhancing your chat interactions with Ollama! 🚀
Don't forget to explore our sibling project, [Open WebUI Community](https://openwebui.com/), where you can discover, download, and explore customized Modelfiles. Open WebUI Community offers a wide range of exciting possibilities for enhancing your chat interactions with Open WebUI! 🚀
## How to Install 🚀
🌟 **Important Note on User Roles and Privacy:**
> [!NOTE]
> Please note that for certain Docker environments, additional configurations might be needed. If you encounter any connection issues, our detailed guide on [Open WebUI Documentation](https://docs.openwebui.com/) is ready to assist you.
- **Admin Creation:** The very first account to sign up on the Ollama Web UI will be granted **Administrator privileges**. This account will have comprehensive control over the platform, including user management and system settings.
- **User Registrations:** All subsequent users signing up will initially have their accounts set to **Pending** status by default. These accounts will require approval from the Administrator to gain access to the platform functionalities.
- **Privacy and Data Security:** We prioritize your privacy and data security above all. Please be reassured that all data entered into the Ollama Web UI is stored locally on your device. Our system is designed to be privacy-first, ensuring that no external requests are made, and your data does not leave your local environment. We are committed to maintaining the highest standards of data privacy and security, ensuring that your information remains confidential and under your control.
### Installing Ollama Web UI Only
#### Prerequisites
Make sure you have the latest version of Ollama installed before proceeding with the installation. You can find the latest version of Ollama at [https://ollama.ai/](https://ollama.ai/).
##### Checking Ollama
After installing Ollama, verify that Ollama is running by accessing the following link in your web browser: [http://127.0.0.1:11434/](http://127.0.0.1:11434/). Note that the port number may differ based on your system configuration.
#### Using Docker 🐳
**Important:** When using Docker to install Ollama Web UI, make sure to include the `-v ollama-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 hosted on your local machine and accessible at [http://127.0.0.1:11434/](http://127.0.0.1:11434/), run the following command:
```bash
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v ollama-webui:/app/backend/data --name ollama-webui --restart always ghcr.io/ollama-webui/ollama-webui:main
```
Alternatively, if you prefer to build the container yourself, use the following command:
```bash
docker build -t ollama-webui .
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v ollama-webui:/app/backend/data --name ollama-webui --restart always ollama-webui
```
Your Ollama Web UI should now be hosted at [http://localhost:3000](http://localhost:3000) and accessible over LAN (or Network). Enjoy! 😄
#### Accessing External Ollama on a Different Server
Change `OLLAMA_API_BASE_URL` environment variable to match the external Ollama Server url:
```bash
docker run -d -p 3000:8080 -e OLLAMA_API_BASE_URL=https://example.com/api -v ollama-webui:/app/backend/data --name ollama-webui --restart always ghcr.io/ollama-webui/ollama-webui:main
```
Alternatively, if you prefer to build the container yourself, use the following command:
```bash
docker build -t ollama-webui .
docker run -d -p 3000:8080 -e OLLAMA_API_BASE_URL=https://example.com/api -v ollama-webui:/app/backend/data --name ollama-webui --restart always ollama-webui
```
### Installing Both Ollama and Ollama Web UI
#### Using Docker Compose
If you don't have Ollama installed yet, you can use the provided Docker Compose file for a hassle-free installation. Simply run the following command:
```bash
docker compose up -d --build
```
This command will install both Ollama and Ollama Web UI on your system.
##### Enable GPU
Use the additional Docker Compose file designed to enable GPU support by running the following command:
```bash
docker compose -f docker-compose.yaml -f docker-compose.gpu.yaml up -d --build
```
##### Expose Ollama API outside the container stack
Deploy the service with an additional Docker Compose file designed for API exposure:
```bash
docker compose -f docker-compose.yaml -f docker-compose.api.yaml up -d --build
```
#### Using Provided `run-compose.sh` Script (Linux)
Also available on Windows under any docker-enabled WSL2 linux distro (you have to enable it from Docker Desktop)
Simply run the following command to grant execute permission to script:
```bash
chmod +x run-compose.sh
```
##### For CPU only container
```bash
./run-compose.sh
```
##### Enable GPU
For GPU enabled container (to enable this you must have your gpu driver for docker, it mostly works with nvidia so this is the official install guide: [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html))
Warning! A GPU-enabled installation has only been tested using linux and nvidia GPU, full functionalities are not guaranteed under Windows or Macos or using a different GPU
```bash
./run-compose.sh --enable-gpu
```
Note that both the above commands will use the latest production docker image in repository, to be able to build the latest local version you'll need to append the `--build` parameter, for example:
```bash
./run-compose.sh --enable-gpu --build
```
#### Using Alternative Methods (Kustomize or Helm)
See [INSTALLATION.md](/INSTALLATION.md) for information on how to install and/or join our [Ollama Web UI Discord community](https://discord.gg/5rJgQTnV4s).
## How to Install Without Docker
While we strongly recommend using our convenient Docker container installation for optimal support, we understand that some situations may require a non-Docker setup, especially for development purposes. Please note that non-Docker installations are not officially supported, and you might need to troubleshoot on your own.
### Project Components
The Ollama Web UI consists of two primary components: the frontend and the backend (which serves as a reverse proxy, handling static frontend files, and additional features). Both need to be running concurrently for the development environment.
### Quick Start with Docker 🐳
> [!IMPORTANT]
> The backend is required for proper functionality
> 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.
### Requirements 📦
- **If Ollama is on your computer**, use this command:
- 🐰 [Bun](https://bun.sh) >= 1.0.21 or 🐢 [Node.js](https://nodejs.org/en) >= 20.10
- 🐍 [Python](https://python.org) >= 3.11
```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
```
### Build and Install 🛠️
- **If Ollama is on a Different Server**, use this command:
Run the following commands to install:
- To connect to Ollama on another server, change the `OLLAMA_API_BASE_URL` to the server's URL:
```sh
git clone https://github.com/ollama-webui/ollama-webui.git
cd ollama-webui/
```bash
docker run -d -p 3000:8080 -e OLLAMA_API_BASE_URL=https://example.com/api -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
```
# Copying required .env file
cp -RPp example.env .env
- After installation, you can access Open WebUI at [http://localhost:3000](http://localhost:3000). Enjoy! 😄
# Building Frontend Using Node
npm i
npm run build
#### Troubleshooting
# or Building Frontend Using Bun
# bun install
# bun run build
Encountering connection issues? Our [Open WebUI Documentation](https://docs.openwebui.com/getting-started/troubleshooting/) has got you covered. For further assistance and to join our vibrant community, visit the [Open WebUI Discord](https://discord.gg/5rJgQTnV4s).
# Serving Frontend with the Backend
cd ./backend
pip install -r requirements.txt -U
sh start.sh
### Other Installation Methods
We offer various installation alternatives, including non-Docker methods, Docker Compose, Kustomize, and Helm. Visit our [Open WebUI Documentation](https://docs.openwebui.com/getting-started/) or join our [Discord community](https://discord.gg/5rJgQTnV4s) for comprehensive guidance.
### Keeping Your Docker Installation Up-to-Date
In case you want to update your local Docker installation to the latest version, you can do it with [Watchtower](https://containrrr.dev/watchtower/):
```bash
docker run --rm --volume /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower --run-once open-webui
```
You should have the Ollama Web UI up and running at http://localhost:8080/. Enjoy! 😄
In the last part of the command, replace `open-webui` with your container name if it is different.
## Troubleshooting
### Moving from Ollama WebUI to Open WebUI
See [TROUBLESHOOTING.md](/TROUBLESHOOTING.md) for information on how to troubleshoot and/or join our [Ollama Web UI Discord community](https://discord.gg/5rJgQTnV4s).
Check our Migration Guide available in our [Open WebUI Documentation](https://docs.openwebui.com/migration/).
## What's Next? 🚀
## What's Next? 🌟
### Roadmap 📝
Here are some exciting tasks on our roadmap:
- 🌐 **Web Browsing Capability**: Experience the convenience of seamlessly integrating web content directly into your chat. Easily browse and share information without leaving the conversation.
- 🔄 **Function Calling**: Empower your interactions by running code directly within the chat. Execute functions and commands effortlessly, enhancing the functionality of your conversations.
- ⚙️ **Custom Python Backend Actions**: Empower your Ollama Web UI by creating or downloading custom Python backend actions. Unleash the full potential of your web interface with tailored actions that suit your specific needs, enhancing functionality and versatility.
- 🧠 **Long-Term Memory**: Witness the power of persistent memory in our agents. Enjoy conversations that feel continuous as agents remember and reference past interactions, creating a more cohesive and personalized user experience.
- 🧪 **Research-Centric Features**: Empower researchers in the fields of LLM and HCI with a comprehensive web UI for conducting user studies. Stay tuned for ongoing feature enhancements (e.g., surveys, analytics, and participant tracking) to facilitate their research.
- 📈 **User Study Tools**: Providing specialized tools, like heat maps and behavior tracking modules, to empower researchers in capturing and analyzing user behavior patterns with precision and accuracy.
- 📚 **Enhanced Documentation**: Elevate your setup and customization experience with improved, comprehensive documentation.
Feel free to contribute and help us make Ollama Web UI even better! 🙌
Discover upcoming features on our roadmap in the [Open WebUI Documentation](https://docs.openwebui.com/roadmap/).
## Supporters ✨
@ -265,7 +139,7 @@ A big shoutout to our amazing supporters who's helping to make this project poss
### Acknowledgments
Special thanks to [Prof. Lawrence Kim @ SFU](https://www.lhkim.com/) and [Prof. Nick Vincent @ SFU](https://www.nickmvincent.com/) for their invaluable support and guidance in shaping this project into a research endeavor. Grateful for your mentorship throughout the journey! 🙌
Special thanks to [Prof. Lawrence Kim](https://www.lhkim.com/) and [Prof. Nick Vincent](https://www.nickmvincent.com/) for their invaluable support and guidance in shaping this project into a research endeavor. Grateful for your mentorship throughout the journey! 🙌
## License 📜
@ -274,9 +148,8 @@ This project is licensed under the [MIT License](LICENSE) - see the [LICENSE](LI
## Support 💬
If you have any questions, suggestions, or need assistance, please open an issue or join our
[Ollama Web UI Discord community](https://discord.gg/5rJgQTnV4s) or
[Ollama Discord community](https://discord.gg/ollama) to connect with us! 🤝
[Open WebUI Discord community](https://discord.gg/5rJgQTnV4s) to connect with us! 🤝
---
Created by [Timothy J. Baek](https://github.com/tjbck) - Let's make Ollama Web UI even more amazing together! 💪
Created by [Timothy J. Baek](https://github.com/tjbck) - Let's make Open Web UI even more amazing together! 💪

16
TROUBLESHOOTING.md
View file

@ -1,32 +1,32 @@
# Ollama Web UI Troubleshooting Guide
# Open WebUI Troubleshooting Guide
## Understanding the Ollama WebUI Architecture
## Understanding the Open WebUI Architecture
The Ollama WebUI system is designed to streamline interactions between the client (your browser) and the Ollama API. At the heart of this design is a backend reverse proxy, enhancing security and resolving CORS issues.
The Open WebUI system is designed to streamline interactions between the client (your browser) and the Ollama API. At the heart of this design is a backend reverse proxy, enhancing security and resolving CORS issues.
- **How it Works**: The Ollama WebUI is designed to interact with the Ollama API through a specific route. When a request is made from the WebUI to Ollama, it is not directly sent to the Ollama API. Initially, the request is sent to the Ollama WebUI backend via `/ollama/api` route. From there, the backend is responsible for forwarding the request to the Ollama API. This forwarding is accomplished by using the route specified in the `OLLAMA_API_BASE_URL` environment variable. Therefore, a request made to `/ollama/api` in the WebUI is effectively the same as making a request to `OLLAMA_API_BASE_URL` in the backend. For instance, a request to `/ollama/api/tags` in the WebUI is equivalent to `OLLAMA_API_BASE_URL/tags` in the backend.
- **How it Works**: The Open WebUI is designed to interact with the Ollama API through a specific route. When a request is made from the WebUI to Ollama, it is not directly sent to the Ollama API. Initially, the request is sent to the Open WebUI backend via `/ollama/api` route. From there, the backend is responsible for forwarding the request to the Ollama API. This forwarding is accomplished by using the route specified in the `OLLAMA_API_BASE_URL` environment variable. Therefore, a request made to `/ollama/api` in the WebUI is effectively the same as making a request to `OLLAMA_API_BASE_URL` in the backend. For instance, a request to `/ollama/api/tags` in the WebUI is equivalent to `OLLAMA_API_BASE_URL/tags` in the backend.
- **Security Benefits**: This design prevents direct exposure of the Ollama API to the frontend, safeguarding against potential CORS (Cross-Origin Resource Sharing) issues and unauthorized access. Requiring authentication to access the Ollama API further enhances this security layer.
## Ollama WebUI: Server Connection Error
## Open WebUI: Server Connection Error
If you're experiencing connection issues, it’s often due to the WebUI docker container not being able to reach the Ollama server at 127.0.0.1:11434 (host.docker.internal:11434) inside the container . Use the `--network=host` flag in your docker command to resolve this. Note that the port changes from 3000 to 8080, resulting in the link: `http://localhost:8080`.
**Example Docker Command**:
```bash
docker run -d --network=host -v ollama-webui:/app/backend/data -e OLLAMA_API_BASE_URL=http://127.0.0.1:11434/api --name ollama-webui --restart always ghcr.io/ollama-webui/ollama-webui:main
docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_API_BASE_URL=http://127.0.0.1:11434/api --name open-webui --restart always ghcr.io/open-webui/open-webui:main
```
### General Connection Errors
**Ensure Ollama Version is Up-to-Date**: Always start by checking that you have the latest version of Ollama. Visit [Ollama's official site](https://ollama.ai/) for the latest updates.
**Ensure Ollama Version is Up-to-Date**: Always start by checking that you have the latest version of Ollama. Visit [Ollama's official site](https://ollama.com/) for the latest updates.
**Troubleshooting Steps**:
1. **Verify Ollama URL Format**:
- When running the Web UI container, ensure the `OLLAMA_API_BASE_URL` is correctly set, including the `/api` suffix. (e.g., `http://192.168.1.1:11434/api` for different host setups).
- In the Ollama WebUI, navigate to "Settings" > "General".
- In the Open WebUI, navigate to "Settings" > "General".
- Confirm that the Ollama Server URL is correctly set to `[OLLAMA URL]/api` (e.g., `http://localhost:11434/api`), including the `/api` suffix.
By following these enhanced troubleshooting steps, connection issues should be effectively resolved. For further assistance or queries, feel free to reach out to us on our community Discord.

4
backend/.gitignore vendored
View file

@ -6,4 +6,6 @@ uploads
*.db
_test
Pipfile
data/*
data/*
!data/config.json
.webui_secret_key

80
backend/apps/audio/main.py Normal file
View file

@ -0,0 +1,80 @@
import os
from fastapi import (
FastAPI,
Request,
Depends,
HTTPException,
status,
UploadFile,
File,
Form,
)
from fastapi.middleware.cors import CORSMiddleware
from faster_whisper import WhisperModel
from constants import ERROR_MESSAGES
from utils.utils import (
decode_token,
get_current_user,
get_verified_user,
get_admin_user,
)
from utils.misc import calculate_sha256
from config import CACHE_DIR, UPLOAD_DIR, WHISPER_MODEL, WHISPER_MODEL_DIR
app = FastAPI()
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
@app.post("/transcribe")
def transcribe(
file: UploadFile = File(...),
user=Depends(get_current_user),
):
print(file.content_type)
if file.content_type not in ["audio/mpeg", "audio/wav"]:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.FILE_NOT_SUPPORTED,
)
try:
filename = file.filename
file_path = f"{UPLOAD_DIR}/{filename}"
contents = file.file.read()
with open(file_path, "wb") as f:
f.write(contents)
f.close()
model = WhisperModel(
WHISPER_MODEL,
device="auto",
compute_type="int8",
download_root=WHISPER_MODEL_DIR,
)
segments, info = model.transcribe(file_path, beam_size=5)
print(
"Detected language '%s' with probability %f"
% (info.language, info.language_probability)
)
transcript = "".join([segment.text for segment in list(segments)])
return {"text": transcript.strip()}
except Exception as e:
print(e)
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.DEFAULT(e),
)

193
backend/apps/images/main.py Normal file
View file

@ -0,0 +1,193 @@
import re
import requests
from fastapi import (
FastAPI,
Request,
Depends,
HTTPException,
status,
UploadFile,
File,
Form,
)
from fastapi.middleware.cors import CORSMiddleware
from faster_whisper import WhisperModel
from constants import ERROR_MESSAGES
from utils.utils import (
get_current_user,
get_admin_user,
)
from utils.misc import calculate_sha256
from typing import Optional
from pydantic import BaseModel
from config import AUTOMATIC1111_BASE_URL
app = FastAPI()
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
app.state.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL
app.state.ENABLED = app.state.AUTOMATIC1111_BASE_URL != ""
app.state.IMAGE_SIZE = "512x512"
@app.get("/enabled", response_model=bool)
async def get_enable_status(request: Request, user=Depends(get_admin_user)):
return app.state.ENABLED
@app.get("/enabled/toggle", response_model=bool)
async def toggle_enabled(request: Request, user=Depends(get_admin_user)):
try:
r = requests.head(app.state.AUTOMATIC1111_BASE_URL)
app.state.ENABLED = not app.state.ENABLED
return app.state.ENABLED
except Exception as e:
raise HTTPException(status_code=r.status_code, detail=ERROR_MESSAGES.DEFAULT(e))
class UrlUpdateForm(BaseModel):
url: str
@app.get("/url")
async def get_openai_url(user=Depends(get_admin_user)):
return {"AUTOMATIC1111_BASE_URL": app.state.AUTOMATIC1111_BASE_URL}
@app.post("/url/update")
async def update_openai_url(form_data: UrlUpdateForm, user=Depends(get_admin_user)):
if form_data.url == "":
app.state.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL
else:
app.state.AUTOMATIC1111_BASE_URL = form_data.url.strip("/")
return {
"AUTOMATIC1111_BASE_URL": app.state.AUTOMATIC1111_BASE_URL,
"status": True,
}
class ImageSizeUpdateForm(BaseModel):
size: str
@app.get("/size")
async def get_image_size(user=Depends(get_admin_user)):
return {"IMAGE_SIZE": app.state.IMAGE_SIZE}
@app.post("/size/update")
async def update_image_size(
form_data: ImageSizeUpdateForm, user=Depends(get_admin_user)
):
pattern = r"^\d+x\d+$" # Regular expression pattern
if re.match(pattern, form_data.size):
app.state.IMAGE_SIZE = form_data.size
return {
"IMAGE_SIZE": app.state.IMAGE_SIZE,
"status": True,
}
else:
raise HTTPException(
status_code=400,
detail=ERROR_MESSAGES.INCORRECT_FORMAT(" (e.g., 512x512)."),
)
@app.get("/models")
def get_models(user=Depends(get_current_user)):
try:
r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/sd-models")
models = r.json()
return models
except Exception as e:
raise HTTPException(status_code=r.status_code, detail=ERROR_MESSAGES.DEFAULT(e))
@app.get("/models/default")
async def get_default_model(user=Depends(get_admin_user)):
try:
r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options")
options = r.json()
return {"model": options["sd_model_checkpoint"]}
except Exception as e:
raise HTTPException(status_code=r.status_code, detail=ERROR_MESSAGES.DEFAULT(e))
class UpdateModelForm(BaseModel):
model: str
def set_model_handler(model: str):
r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options")
options = r.json()
if model != options["sd_model_checkpoint"]:
options["sd_model_checkpoint"] = model
r = requests.post(
url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options", json=options
)
return options
@app.post("/models/default/update")
def update_default_model(
form_data: UpdateModelForm,
user=Depends(get_current_user),
):
return set_model_handler(form_data.model)
class GenerateImageForm(BaseModel):
model: Optional[str] = None
prompt: str
n: int = 1
size: str = "512x512"
negative_prompt: Optional[str] = None
@app.post("/generations")
def generate_image(
form_data: GenerateImageForm,
user=Depends(get_current_user),
):
print(form_data)
try:
if form_data.model:
set_model_handler(form_data.model)
width, height = tuple(map(int, app.state.IMAGE_SIZE.split("x")))
data = {
"prompt": form_data.prompt,
"batch_size": form_data.n,
"width": width,
"height": height,
}
if form_data.negative_prompt != None:
data["negative_prompt"] = form_data.negative_prompt
print(data)
r = requests.post(
url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/txt2img",
json=data,
)
return r.json()
except Exception as e:
print(e)
raise HTTPException(status_code=r.status_code, detail=ERROR_MESSAGES.DEFAULT(e))

74
backend/apps/ollama/main.py
View file

@ -1,15 +1,16 @@
from fastapi import FastAPI, Request, Response, HTTPException, Depends
from fastapi import FastAPI, Request, Response, HTTPException, Depends, status
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import StreamingResponse
from fastapi.concurrency import run_in_threadpool
import requests
import json
import uuid
from pydantic import BaseModel
from apps.web.models.users import Users
from constants import ERROR_MESSAGES
from utils.utils import decode_token, get_current_user
from utils.utils import decode_token, get_current_user, get_admin_user
from config import OLLAMA_API_BASE_URL, WEBUI_AUTH
app = FastAPI()
@ -26,12 +27,12 @@ app.state.OLLAMA_API_BASE_URL = OLLAMA_API_BASE_URL
# TARGET_SERVER_URL = OLLAMA_API_BASE_URL
REQUEST_POOL = []
@app.get("/url")
async def get_ollama_api_url(user=Depends(get_current_user)):
if user and user.role == "admin":
return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
else:
raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
async def get_ollama_api_url(user=Depends(get_admin_user)):
return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
class UrlUpdateForm(BaseModel):
@ -39,12 +40,17 @@ class UrlUpdateForm(BaseModel):
@app.post("/url/update")
async def update_ollama_api_url(
form_data: UrlUpdateForm, user=Depends(get_current_user)
):
if user and user.role == "admin":
app.state.OLLAMA_API_BASE_URL = form_data.url
return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
async def update_ollama_api_url(form_data: UrlUpdateForm, user=Depends(get_admin_user)):
app.state.OLLAMA_API_BASE_URL = form_data.url
return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
@app.get("/cancel/{request_id}")
async def cancel_ollama_request(request_id: str, user=Depends(get_current_user)):
if user:
if request_id in REQUEST_POOL:
REQUEST_POOL.remove(request_id)
return True
else:
raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
@ -60,21 +66,45 @@ async def proxy(path: str, request: Request, user=Depends(get_current_user)):
if path in ["pull", "delete", "push", "copy", "create"]:
if user.role != "admin":
raise HTTPException(
status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
else:
raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
headers.pop("Host", None)
headers.pop("Authorization", None)
headers.pop("Origin", None)
headers.pop("Referer", None)
headers.pop("host", None)
headers.pop("authorization", None)
headers.pop("origin", None)
headers.pop("referer", None)
r = None
def get_request():
nonlocal r
request_id = str(uuid.uuid4())
try:
REQUEST_POOL.append(request_id)
def stream_content():
try:
if path in ["chat"]:
yield json.dumps({"id": request_id, "done": False}) + "\n"
for chunk in r.iter_content(chunk_size=8192):
if request_id in REQUEST_POOL:
yield chunk
else:
print("User: canceled request")
break
finally:
if hasattr(r, "close"):
r.close()
REQUEST_POOL.remove(request_id)
r = requests.request(
method=request.method,
url=target_url,
@ -85,8 +115,10 @@ async def proxy(path: str, request: Request, user=Depends(get_current_user)):
r.raise_for_status()
# r.close()
return StreamingResponse(
r.iter_content(chunk_size=8192),
stream_content(),
status_code=r.status_code,
headers=dict(r.headers),
)
@ -96,7 +128,7 @@ async def proxy(path: str, request: Request, user=Depends(get_current_user)):
try:
return await run_in_threadpool(get_request)
except Exception as e:
error_detail = "Ollama WebUI: Server Connection Error"
error_detail = "Open WebUI: Server Connection Error"
if r is not None:
try:
res = r.json()

4
backend/apps/ollama/old_main.py
View file

@ -61,7 +61,7 @@ async def update_ollama_api_url(
# yield line
# except Exception as e:
# print(e)
# error_detail = "Ollama WebUI: Server Connection Error"
# error_detail = "Open WebUI: Server Connection Error"
# yield json.dumps({"error": error_detail, "message": str(e)}).encode()
@ -110,7 +110,7 @@ async def proxy(path: str, request: Request, user=Depends(get_current_user)):
except Exception as e:
print(e)
error_detail = "Ollama WebUI: Server Connection Error"
error_detail = "Open WebUI: Server Connection Error"
if response is not None:
try:

149
backend/apps/openai/main.py
View file

@ -1,15 +1,24 @@
from fastapi import FastAPI, Request, Response, HTTPException, Depends
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import StreamingResponse, JSONResponse
from fastapi.responses import StreamingResponse, JSONResponse, FileResponse
import requests
import json
from pydantic import BaseModel
from apps.web.models.users import Users
from constants import ERROR_MESSAGES
from utils.utils import decode_token, get_current_user
from config import OPENAI_API_BASE_URL, OPENAI_API_KEY
from utils.utils import (
decode_token,
get_current_user,
get_verified_user,
get_admin_user,
)
from config import OPENAI_API_BASE_URL, OPENAI_API_KEY, CACHE_DIR
import hashlib
from pathlib import Path
app = FastAPI()
app.add_middleware(
@ -33,60 +42,114 @@ class KeyUpdateForm(BaseModel):
@app.get("/url")
async def get_openai_url(user=Depends(get_current_user)):
if user and user.role == "admin":
return {"OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL}
else:
raise HTTPException(status_code=401,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
async def get_openai_url(user=Depends(get_admin_user)):
return {"OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL}
@app.post("/url/update")
async def update_openai_url(form_data: UrlUpdateForm,
user=Depends(get_current_user)):
if user and user.role == "admin":
app.state.OPENAI_API_BASE_URL = form_data.url
return {"OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL}
else:
raise HTTPException(status_code=401,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
async def update_openai_url(form_data: UrlUpdateForm, user=Depends(get_admin_user)):
app.state.OPENAI_API_BASE_URL = form_data.url
return {"OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL}
@app.get("/key")
async def get_openai_key(user=Depends(get_current_user)):
if user and user.role == "admin":
return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY}
else:
raise HTTPException(status_code=401,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
async def get_openai_key(user=Depends(get_admin_user)):
return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY}
@app.post("/key/update")
async def update_openai_key(form_data: KeyUpdateForm,
user=Depends(get_current_user)):
if user and user.role == "admin":
app.state.OPENAI_API_KEY = form_data.key
return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY}
else:
raise HTTPException(status_code=401,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
async def update_openai_key(form_data: KeyUpdateForm, user=Depends(get_admin_user)):
app.state.OPENAI_API_KEY = form_data.key
return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY}
@app.post("/audio/speech")
async def speech(request: Request, user=Depends(get_verified_user)):
target_url = f"{app.state.OPENAI_API_BASE_URL}/audio/speech"
if app.state.OPENAI_API_KEY == "":
raise HTTPException(status_code=401, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
body = await request.body()
name = hashlib.sha256(body).hexdigest()
SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
file_path = SPEECH_CACHE_DIR.joinpath(f"{name}.mp3")
file_body_path = SPEECH_CACHE_DIR.joinpath(f"{name}.json")
# Check if the file already exists in the cache
if file_path.is_file():
return FileResponse(file_path)
headers = {}
headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEY}"
headers["Content-Type"] = "application/json"
try:
print("openai")
r = requests.post(
url=target_url,
data=body,
headers=headers,
stream=True,
)
r.raise_for_status()
# Save the streaming content to a file
with open(file_path, "wb") as f:
for chunk in r.iter_content(chunk_size=8192):
f.write(chunk)
with open(file_body_path, "w") as f:
json.dump(json.loads(body.decode("utf-8")), f)
# Return the saved file
return FileResponse(file_path)
except Exception as e:
print(e)
error_detail = "Open WebUI: Server Connection Error"
if r is not None:
try:
res = r.json()
if "error" in res:
error_detail = f"External: {res['error']}"
except:
error_detail = f"External: {e}"
raise HTTPException(status_code=r.status_code, detail=error_detail)
@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
async def proxy(path: str, request: Request, user=Depends(get_current_user)):
async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
target_url = f"{app.state.OPENAI_API_BASE_URL}/{path}"
print(target_url, app.state.OPENAI_API_KEY)
if user.role not in ["user", "admin"]:
raise HTTPException(status_code=401,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
if app.state.OPENAI_API_KEY == "":
raise HTTPException(status_code=401,
detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
raise HTTPException(status_code=401, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
body = await request.body()
# headers = dict(request.headers)
# print(headers)
# TODO: Remove below after gpt-4-vision fix from Open AI
# Try to decode the body of the request from bytes to a UTF-8 string (Require add max_token to fix gpt-4-vision)
try:
body = body.decode("utf-8")
body = json.loads(body)
# Check if the model is "gpt-4-vision-preview" and set "max_tokens" to 4000
# This is a workaround until OpenAI fixes the issue with this model
if body.get("model") == "gpt-4-vision-preview":
if "max_tokens" not in body:
body["max_tokens"] = 4000
print("Modified body_dict:", body)
# Convert the modified body back to JSON
body = json.dumps(body)
except json.JSONDecodeError as e:
print("Error loading request body into a dictionary:", e)
headers = {}
headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEY}"
@ -121,17 +184,15 @@ async def proxy(path: str, request: Request, user=Depends(get_current_user)):
response_data = r.json()
print(type(response_data))
if "openai" in app.state.OPENAI_API_BASE_URL and path == "models":
response_data["data"] = list(
filter(lambda model: "gpt" in model["id"],
response_data["data"]))
filter(lambda model: "gpt" in model["id"], response_data["data"])
)
return response_data
except Exception as e:
print(e)
error_detail = "Ollama WebUI: Server Connection Error"
error_detail = "Open WebUI: Server Connection Error"
if r is not None:
try:
res = r.json()

511
backend/apps/rag/main.py
View file

@ -1,6 +1,5 @@
from fastapi import (
FastAPI,
Request,
Depends,
HTTPException,
status,
@ -11,7 +10,11 @@ from fastapi import (
from fastapi.middleware.cors import CORSMiddleware
import os, shutil
# from chromadb.utils import embedding_functions
from pathlib import Path
from typing import List
from sentence_transformers import SentenceTransformer
from chromadb.utils import embedding_functions
from langchain_community.document_loaders import (
WebBaseLoader,
@ -19,29 +22,71 @@ from langchain_community.document_loaders import (
PyPDFLoader,
CSVLoader,
Docx2txtLoader,
UnstructuredEPubLoader,
UnstructuredWordDocumentLoader,
UnstructuredMarkdownLoader,
UnstructuredXMLLoader,
UnstructuredRSTLoader,
UnstructuredExcelLoader,
)
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import Chroma
from langchain.chains import RetrievalQA
from pydantic import BaseModel
from typing import Optional
import mimetypes
import uuid
import time
import json
from apps.web.models.documents import (
Documents,
DocumentForm,
DocumentResponse,
)
from utils.misc import (
calculate_sha256,
calculate_sha256_string,
sanitize_filename,
extract_folders_after_data_docs,
)
from utils.utils import get_current_user, get_admin_user
from config import (
UPLOAD_DIR,
DOCS_DIR,
RAG_EMBEDDING_MODEL,
RAG_EMBEDDING_MODEL_DEVICE_TYPE,
CHROMA_CLIENT,
CHUNK_SIZE,
CHUNK_OVERLAP,
RAG_TEMPLATE,
)
from utils.misc import calculate_sha256
from utils.utils import get_current_user
from config import UPLOAD_DIR, EMBED_MODEL, CHROMA_CLIENT, CHUNK_SIZE, CHUNK_OVERLAP
from constants import ERROR_MESSAGES
# EMBEDDING_FUNC = embedding_functions.SentenceTransformerEmbeddingFunction(
# model_name=EMBED_MODEL
# )
#
# 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.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.sentence_transformer_ef = (
embedding_functions.SentenceTransformerEmbeddingFunction(
model_name=app.state.RAG_EMBEDDING_MODEL,
device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
)
)
origins = ["*"]
app.add_middleware(
@ -63,7 +108,7 @@ class StoreWebForm(CollectionNameForm):
def store_data_in_vector_db(data, collection_name) -> bool:
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=CHUNK_SIZE, chunk_overlap=CHUNK_OVERLAP
chunk_size=app.state.CHUNK_SIZE, chunk_overlap=app.state.CHUNK_OVERLAP
)
docs = text_splitter.split_documents(data)
@ -71,7 +116,10 @@ def store_data_in_vector_db(data, collection_name) -> bool:
metadatas = [doc.metadata for doc in docs]
try:
collection = CHROMA_CLIENT.create_collection(name=collection_name)
collection = CHROMA_CLIENT.create_collection(
name=collection_name,
embedding_function=app.state.sentence_transformer_ef,
)
collection.add(
documents=texts, metadatas=metadatas, ids=[str(uuid.uuid1()) for _ in texts]
@ -87,22 +135,112 @@ def store_data_in_vector_db(data, collection_name) -> bool:
@app.get("/")
async def get_status():
return {"status": True}
return {
"status": True,
"chunk_size": app.state.CHUNK_SIZE,
"chunk_overlap": app.state.CHUNK_OVERLAP,
"template": app.state.RAG_TEMPLATE,
"embedding_model": app.state.RAG_EMBEDDING_MODEL,
}
@app.get("/query/{collection_name}")
def query_collection(
collection_name: str,
query: str,
k: Optional[int] = 4,
@app.get("/embedding/model")
async def get_embedding_model(user=Depends(get_admin_user)):
return {
"status": True,
"embedding_model": app.state.RAG_EMBEDDING_MODEL,
}
class EmbeddingModelUpdateForm(BaseModel):
embedding_model: str
@app.post("/embedding/model/update")
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 = (
embedding_functions.SentenceTransformerEmbeddingFunction(
model_name=app.state.RAG_EMBEDDING_MODEL,
device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
)
)
return {
"status": True,
"embedding_model": app.state.RAG_EMBEDDING_MODEL,
}
@app.get("/chunk")
async def get_chunk_params(user=Depends(get_admin_user)):
return {
"status": True,
"chunk_size": app.state.CHUNK_SIZE,
"chunk_overlap": app.state.CHUNK_OVERLAP,
}
class ChunkParamUpdateForm(BaseModel):
chunk_size: int
chunk_overlap: int
@app.post("/chunk/update")
async def update_chunk_params(
form_data: ChunkParamUpdateForm, user=Depends(get_admin_user)
):
app.state.CHUNK_SIZE = form_data.chunk_size
app.state.CHUNK_OVERLAP = form_data.chunk_overlap
return {
"status": True,
"chunk_size": app.state.CHUNK_SIZE,
"chunk_overlap": app.state.CHUNK_OVERLAP,
}
@app.get("/template")
async def get_rag_template(user=Depends(get_current_user)):
return {
"status": True,
"template": app.state.RAG_TEMPLATE,
}
class RAGTemplateForm(BaseModel):
template: str
@app.post("/template/update")
async def update_rag_template(form_data: RAGTemplateForm, user=Depends(get_admin_user)):
# TODO: check template requirements
app.state.RAG_TEMPLATE = (
form_data.template if form_data.template != "" else RAG_TEMPLATE
)
return {"status": True, "template": app.state.RAG_TEMPLATE}
class QueryDocForm(BaseModel):
collection_name: str
query: str
k: Optional[int] = 4
@app.post("/query/doc")
def query_doc(
form_data: QueryDocForm,
user=Depends(get_current_user),
):
try:
# if you use docker use the model from the environment variable
collection = CHROMA_CLIENT.get_collection(
name=collection_name,
name=form_data.collection_name,
embedding_function=app.state.sentence_transformer_ef,
)
result = collection.query(query_texts=[query], n_results=k)
result = collection.query(query_texts=[form_data.query], n_results=form_data.k)
return result
except Exception as e:
print(e)
@ -112,14 +250,99 @@ def query_collection(
)
class QueryCollectionsForm(BaseModel):
collection_names: List[str]
query: str
k: Optional[int] = 4
def merge_and_sort_query_results(query_results, k):
# Initialize lists to store combined data
combined_ids = []
combined_distances = []
combined_metadatas = []
combined_documents = []
# Combine data from each dictionary
for data in query_results:
combined_ids.extend(data["ids"][0])
combined_distances.extend(data["distances"][0])
combined_metadatas.extend(data["metadatas"][0])
combined_documents.extend(data["documents"][0])
# Create a list of tuples (distance, id, metadata, document)
combined = list(
zip(combined_distances, combined_ids, combined_metadatas, combined_documents)
)
# Sort the list based on distances
combined.sort(key=lambda x: x[0])
# Unzip the sorted list
sorted_distances, sorted_ids, sorted_metadatas, sorted_documents = zip(*combined)
# Slicing the lists to include only k elements
sorted_distances = list(sorted_distances)[:k]
sorted_ids = list(sorted_ids)[:k]
sorted_metadatas = list(sorted_metadatas)[:k]
sorted_documents = list(sorted_documents)[:k]
# Create the output dictionary
merged_query_results = {
"ids": [sorted_ids],
"distances": [sorted_distances],
"metadatas": [sorted_metadatas],
"documents": [sorted_documents],
"embeddings": None,
"uris": None,
"data": None,
}
return merged_query_results
@app.post("/query/collection")
def query_collection(
form_data: QueryCollectionsForm,
user=Depends(get_current_user),
):
results = []
for collection_name in form_data.collection_names:
try:
# if you use docker use the model from the environment variable
collection = CHROMA_CLIENT.get_collection(
name=collection_name,
embedding_function=app.state.sentence_transformer_ef,
)
result = collection.query(
query_texts=[form_data.query], n_results=form_data.k
)
results.append(result)
except:
pass
return merge_and_sort_query_results(results, form_data.k)
@app.post("/web")
def store_web(form_data: StoreWebForm, user=Depends(get_current_user)):
# "https://www.gutenberg.org/files/1727/1727-h/1727-h.htm"
try:
loader = WebBaseLoader(form_data.url)
data = loader.load()
store_data_in_vector_db(data, form_data.collection_name)
return {"status": True, "collection_name": form_data.collection_name}
collection_name = form_data.collection_name
if collection_name == "":
collection_name = calculate_sha256_string(form_data.url)[:63]
store_data_in_vector_db(data, collection_name)
return {
"status": True,
"collection_name": collection_name,
"filename": form_data.url,
}
except Exception as e:
print(e)
raise HTTPException(
@ -128,6 +351,87 @@ def store_web(form_data: StoreWebForm, user=Depends(get_current_user)):
)
def get_loader(filename: str, file_content_type: str, file_path: str):
file_ext = filename.split(".")[-1].lower()
known_type = True
known_source_ext = [
"go",
"py",
"java",
"sh",
"bat",
"ps1",
"cmd",
"js",
"ts",
"css",
"cpp",
"hpp",
"h",
"c",
"cs",
"sql",
"log",
"ini",
"pl",
"pm",
"r",
"dart",
"dockerfile",
"env",
"php",
"hs",
"hsc",
"lua",
"nginxconf",
"conf",
"m",
"mm",
"plsql",
"perl",
"rb",
"rs",
"db2",
"scala",
"bash",
"swift",
"vue",
"svelte",
]
if file_ext == "pdf":
loader = PyPDFLoader(file_path)
elif file_ext == "csv":
loader = CSVLoader(file_path)
elif file_ext == "rst":
loader = UnstructuredRSTLoader(file_path, mode="elements")
elif file_ext == "xml":
loader = UnstructuredXMLLoader(file_path)
elif file_ext == "md":
loader = UnstructuredMarkdownLoader(file_path)
elif file_content_type == "application/epub+zip":
loader = UnstructuredEPubLoader(file_path)
elif (
file_content_type
== "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
or file_ext in ["doc", "docx"]
):
loader = Docx2txtLoader(file_path)
elif file_content_type in [
"application/vnd.ms-excel",
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
] or file_ext in ["xls", "xlsx"]:
loader = UnstructuredExcelLoader(file_path)
elif file_ext in known_source_ext or (file_content_type and file_content_type.find("text/") >= 0):
loader = TextLoader(file_path)
else:
loader = TextLoader(file_path)
known_type = False
return loader, known_type
@app.post("/doc")
def store_doc(
collection_name: Optional[str] = Form(None),
@ -136,17 +440,7 @@ def store_doc(
):
# "https://www.gutenberg.org/files/1727/1727-h/1727-h.htm"
if file.content_type not in [
"application/pdf",
"text/plain",
"text/csv",
"application/vnd.openxmlformats-officedocument.wordprocessingml.document",
]:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.FILE_NOT_SUPPORTED,
)
print(file.content_type)
try:
filename = file.filename
file_path = f"{UPLOAD_DIR}/{filename}"
@ -160,23 +454,17 @@ def store_doc(
collection_name = calculate_sha256(f)[:63]
f.close()
if file.content_type == "application/pdf":
loader = PyPDFLoader(file_path)
elif (
file.content_type
== "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
):
loader = Docx2txtLoader(file_path)
elif file.content_type == "text/plain":
loader = TextLoader(file_path)
elif file.content_type == "text/csv":
loader = CSVLoader(file_path)
loader, known_type = get_loader(file.filename, file.content_type, file_path)
data = loader.load()
result = store_data_in_vector_db(data, collection_name)
if result:
return {"status": True, "collection_name": collection_name}
return {
"status": True,
"collection_name": collection_name,
"filename": filename,
"known_type": known_type,
}
else:
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
@ -184,45 +472,96 @@ def store_doc(
)
except Exception as e:
print(e)
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.DEFAULT(e),
)
if "No pandoc was found" in str(e):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.PANDOC_NOT_INSTALLED,
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.DEFAULT(e),
)
@app.get("/reset/db")
def reset_vector_db(user=Depends(get_current_user)):
if user.role == "admin":
CHROMA_CLIENT.reset()
else:
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
@app.get("/reset")
def reset(user=Depends(get_current_user)) -> bool:
if user.role == "admin":
folder = f"{UPLOAD_DIR}"
for filename in os.listdir(folder):
file_path = os.path.join(folder, filename)
try:
if os.path.isfile(file_path) or os.path.islink(file_path):
os.unlink(file_path)
elif os.path.isdir(file_path):
shutil.rmtree(file_path)
except Exception as e:
print("Failed to delete %s. Reason: %s" % (file_path, e))
@app.get("/scan")
def scan_docs_dir(user=Depends(get_admin_user)):
for path in Path(DOCS_DIR).rglob("./**/*"):
try:
CHROMA_CLIENT.reset()
if path.is_file() and not path.name.startswith("."):
tags = extract_folders_after_data_docs(path)
filename = path.name
file_content_type = mimetypes.guess_type(path)
f = open(path, "rb")
collection_name = calculate_sha256(f)[:63]
f.close()
loader, known_type = get_loader(
filename, file_content_type[0], str(path)
)
data = loader.load()
result = store_data_in_vector_db(data, collection_name)
if result:
sanitized_filename = sanitize_filename(filename)
doc = Documents.get_doc_by_name(sanitized_filename)
if doc == None:
doc = Documents.insert_new_doc(
user.id,
DocumentForm(
**{
"name": sanitized_filename,
"title": filename,
"collection_name": collection_name,
"filename": filename,
"content": (
json.dumps(
{
"tags": list(
map(
lambda name: {"name": name},
tags,
)
)
}
)
if len(tags)
else "{}"
),
}
),
)
except Exception as e:
print(e)
return True
else:
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
return True
@app.get("/reset/db")
def reset_vector_db(user=Depends(get_admin_user)):
CHROMA_CLIENT.reset()
@app.get("/reset")
def reset(user=Depends(get_admin_user)) -> bool:
folder = f"{UPLOAD_DIR}"
for filename in os.listdir(folder):
file_path = os.path.join(folder, filename)
try:
if os.path.isfile(file_path) or os.path.islink(file_path):
os.unlink(file_path)
elif os.path.isdir(file_path):
shutil.rmtree(file_path)
except Exception as e:
print("Failed to delete %s. Reason: %s" % (file_path, e))
try:
CHROMA_CLIENT.reset()
except Exception as e:
print(e)
return True

4
backend/apps/web/internal/db.py
View file

@ -1,4 +1,6 @@
from peewee import *
from config import DATA_DIR
DB = SqliteDatabase("./data/ollama.db")
DB = SqliteDatabase(f"{DATA_DIR}/ollama.db")
DB.connect()

38
backend/apps/web/main.py
View file

@ -1,15 +1,38 @@
from fastapi import FastAPI, Depends
from fastapi.routing import APIRoute
from fastapi.middleware.cors import CORSMiddleware
from apps.web.routers import auths, users, chats, modelfiles, prompts, configs, utils
from config import WEBUI_VERSION, WEBUI_AUTH
from apps.web.routers import (
auths,
users,
chats,
documents,
modelfiles,
prompts,
configs,
utils,
)
from config import (
WEBUI_VERSION,
WEBUI_AUTH,
DEFAULT_MODELS,
DEFAULT_PROMPT_SUGGESTIONS,
DEFAULT_USER_ROLE,
ENABLE_SIGNUP,
USER_PERMISSIONS,
)
app = FastAPI()
origins = ["*"]
app.state.ENABLE_SIGNUP = True
app.state.DEFAULT_MODELS = None
app.state.ENABLE_SIGNUP = ENABLE_SIGNUP
app.state.JWT_EXPIRES_IN = "-1"
app.state.DEFAULT_MODELS = DEFAULT_MODELS
app.state.DEFAULT_PROMPT_SUGGESTIONS = DEFAULT_PROMPT_SUGGESTIONS
app.state.DEFAULT_USER_ROLE = DEFAULT_USER_ROLE
app.state.USER_PERMISSIONS = USER_PERMISSIONS
app.add_middleware(
CORSMiddleware,
@ -22,9 +45,8 @@ app.add_middleware(
app.include_router(auths.router, prefix="/auths", tags=["auths"])
app.include_router(users.router, prefix="/users", tags=["users"])
app.include_router(chats.router, prefix="/chats", tags=["chats"])
app.include_router(modelfiles.router,
prefix="/modelfiles",
tags=["modelfiles"])
app.include_router(documents.router, prefix="/documents", tags=["documents"])
app.include_router(modelfiles.router, prefix="/modelfiles", tags=["modelfiles"])
app.include_router(prompts.router, prefix="/prompts", tags=["prompts"])
app.include_router(configs.router, prefix="/configs", tags=["configs"])
@ -35,7 +57,7 @@ app.include_router(utils.router, prefix="/utils", tags=["utils"])
async def get_status():
return {
"status": True,
"version": WEBUI_VERSION,
"auth": WEBUI_AUTH,
"default_models": app.state.DEFAULT_MODELS,
"default_prompt_suggestions": app.state.DEFAULT_PROMPT_SUGGESTIONS,
}

16
backend/apps/web/models/auths.py
View file

@ -5,12 +5,7 @@ import uuid
from peewee import *
from apps.web.models.users import UserModel, Users
from utils.utils import (
verify_password,
get_password_hash,
bearer_scheme,
create_token,
)
from utils.utils import verify_password
from apps.web.internal.db import DB
@ -63,6 +58,15 @@ class SigninForm(BaseModel):
password: str
class ProfileImageUrlForm(BaseModel):
profile_image_url: str
class UpdateProfileForm(BaseModel):
profile_image_url: str
name: str
class UpdatePasswordForm(BaseModel):
password: str
new_password: str

55
backend/apps/web/models/chats.py
View file

@ -60,23 +60,23 @@ class ChatTitleIdResponse(BaseModel):
class ChatTable:
def __init__(self, db):
self.db = db
db.create_tables([Chat])
def insert_new_chat(self, user_id: str,
form_data: ChatForm) -> Optional[ChatModel]:
def insert_new_chat(self, user_id: str, form_data: ChatForm) -> Optional[ChatModel]:
id = str(uuid.uuid4())
chat = ChatModel(
**{
"id": id,
"user_id": user_id,
"title": form_data.chat["title"] if "title" in
form_data.chat else "New Chat",
"title": (
form_data.chat["title"] if "title" in form_data.chat else "New Chat"
),
"chat": json.dumps(form_data.chat),
"timestamp": int(time.time()),
})
}
)
result = Chat.create(**chat.model_dump())
return chat if result else None
@ -109,25 +109,43 @@ class ChatTable:
except:
return None
def get_chat_lists_by_user_id(self,
user_id: str,
skip: int = 0,
limit: int = 50) -> List[ChatModel]:
def get_chat_lists_by_user_id(
self, user_id: str, skip: int = 0, limit: int = 50
) -> List[ChatModel]:
return [
ChatModel(**model_to_dict(chat)) for chat in Chat.select().where(
Chat.user_id == user_id).order_by(Chat.timestamp.desc())
ChatModel(**model_to_dict(chat))
for chat in Chat.select()
.where(Chat.user_id == user_id)
.order_by(Chat.timestamp.desc())
# .limit(limit)
# .offset(skip)
]
def get_all_chats_by_user_id(self, user_id: str) -> List[ChatModel]:
def get_chat_lists_by_chat_ids(
self, chat_ids: List[str], skip: int = 0, limit: int = 50
) -> List[ChatModel]:
return [
ChatModel(**model_to_dict(chat)) for chat in Chat.select().where(
Chat.user_id == user_id).order_by(Chat.timestamp.desc())
ChatModel(**model_to_dict(chat))
for chat in Chat.select()
.where(Chat.id.in_(chat_ids))
.order_by(Chat.timestamp.desc())
]
def get_chat_by_id_and_user_id(self, id: str,
user_id: str) -> Optional[ChatModel]:
def get_all_chats(self) -> List[ChatModel]:
return [
ChatModel(**model_to_dict(chat))
for chat in Chat.select().order_by(Chat.timestamp.desc())
]
def get_all_chats_by_user_id(self, user_id: str) -> List[ChatModel]:
return [
ChatModel(**model_to_dict(chat))
for chat in Chat.select()
.where(Chat.user_id == user_id)
.order_by(Chat.timestamp.desc())
]
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)
return ChatModel(**model_to_dict(chat))
@ -142,8 +160,7 @@ class ChatTable:
def delete_chat_by_id_and_user_id(self, id: str, user_id: str) -> bool:
try:
query = Chat.delete().where((Chat.id == id)
& (Chat.user_id == user_id))
query = Chat.delete().where((Chat.id == id) & (Chat.user_id == user_id))
query.execute() # Remove the rows, return number of rows removed.
return True

154
backend/apps/web/models/documents.py Normal file
View file

@ -0,0 +1,154 @@
from pydantic import BaseModel
from peewee import *
from playhouse.shortcuts import model_to_dict
from typing import List, Union, Optional
import time
from utils.utils import decode_token
from utils.misc import get_gravatar_url
from apps.web.internal.db import DB
import json
####################
# Documents DB Schema
####################
class Document(Model):
collection_name = CharField(unique=True)
name = CharField(unique=True)
title = CharField()
filename = CharField()
content = TextField(null=True)
user_id = CharField()
timestamp = DateField()
class Meta:
database = DB
class DocumentModel(BaseModel):
collection_name: str
name: str
title: str
filename: str
content: Optional[str] = None
user_id: str
timestamp: int # timestamp in epoch
####################
# Forms
####################
class DocumentResponse(BaseModel):
collection_name: str
name: str
title: str
filename: str
content: Optional[dict] = None
user_id: str
timestamp: int # timestamp in epoch
class DocumentUpdateForm(BaseModel):
name: str
title: str
class DocumentForm(DocumentUpdateForm):
collection_name: str
filename: str
content: Optional[str] = None
class DocumentsTable:
def __init__(self, db):
self.db = db
self.db.create_tables([Document])
def insert_new_doc(
self, user_id: str, form_data: DocumentForm
) -> Optional[DocumentModel]:
document = DocumentModel(
**{
**form_data.model_dump(),
"user_id": user_id,
"timestamp": int(time.time()),
}
)
try:
result = Document.create(**document.model_dump())
if result:
return document
else:
return None
except:
return None
def get_doc_by_name(self, name: str) -> Optional[DocumentModel]:
try:
document = Document.get(Document.name == name)
return DocumentModel(**model_to_dict(document))
except:
return None
def get_docs(self) -> List[DocumentModel]:
return [
DocumentModel(**model_to_dict(doc))
for doc in Document.select()
# .limit(limit).offset(skip)
]
def update_doc_by_name(
self, name: str, form_data: DocumentUpdateForm
) -> Optional[DocumentModel]:
try:
query = Document.update(
title=form_data.title,
name=form_data.name,
timestamp=int(time.time()),
).where(Document.name == name)
query.execute()
doc = Document.get(Document.name == form_data.name)
return DocumentModel(**model_to_dict(doc))
except Exception as e:
print(e)
return None
def update_doc_content_by_name(
self, name: str, updated: dict
) -> Optional[DocumentModel]:
try:
doc = self.get_doc_by_name(name)
doc_content = json.loads(doc.content if doc.content else "{}")
doc_content = {**doc_content, **updated}
query = Document.update(
content=json.dumps(doc_content),
timestamp=int(time.time()),
).where(Document.name == name)
query.execute()
doc = Document.get(Document.name == name)
return DocumentModel(**model_to_dict(doc))
except Exception as e:
print(e)
return None
def delete_doc_by_name(self, name: str) -> bool:
try:
query = Document.delete().where((Document.name == name))
query.execute() # Remove the rows, return number of rows removed.
return True
except:
return False
Documents = DocumentsTable(DB)

206
backend/apps/web/models/tags.py Normal file
View file

@ -0,0 +1,206 @@
from pydantic import BaseModel
from typing import List, Union, Optional
from peewee import *
from playhouse.shortcuts import model_to_dict
import json
import uuid
import time
from apps.web.internal.db import DB
####################
# Tag DB Schema
####################
class Tag(Model):
id = CharField(unique=True)
name = CharField()
user_id = CharField()
data = TextField(null=True)
class Meta:
database = DB
class ChatIdTag(Model):
id = CharField(unique=True)
tag_name = CharField()
chat_id = CharField()
user_id = CharField()
timestamp = DateField()
class Meta:
database = DB
class TagModel(BaseModel):
id: str
name: str
user_id: str
data: Optional[str] = None
class ChatIdTagModel(BaseModel):
id: str
tag_name: str
chat_id: str
user_id: str
timestamp: int
####################
# Forms
####################
class ChatIdTagForm(BaseModel):
tag_name: str
chat_id: str
class TagChatIdsResponse(BaseModel):
chat_ids: List[str]
class ChatTagsResponse(BaseModel):
tags: List[str]
class TagTable:
def __init__(self, db):
self.db = db
db.create_tables([Tag, ChatIdTag])
def insert_new_tag(self, name: str, user_id: str) -> Optional[TagModel]:
id = str(uuid.uuid4())
tag = TagModel(**{"id": id, "user_id": user_id, "name": name})
try:
result = Tag.create(**tag.model_dump())
if result:
return tag
else:
return None
except Exception as e:
return None
def get_tag_by_name_and_user_id(
self, name: str, user_id: str
) -> Optional[TagModel]:
try:
tag = Tag.get(Tag.name == name, Tag.user_id == user_id)
return TagModel(**model_to_dict(tag))
except Exception as e:
return None
def add_tag_to_chat(
self, user_id: str, form_data: ChatIdTagForm
) -> Optional[ChatIdTagModel]:
tag = self.get_tag_by_name_and_user_id(form_data.tag_name, user_id)
if tag == None:
tag = self.insert_new_tag(form_data.tag_name, user_id)
id = str(uuid.uuid4())
chatIdTag = ChatIdTagModel(
**{
"id": id,
"user_id": user_id,
"chat_id": form_data.chat_id,
"tag_name": tag.name,
"timestamp": int(time.time()),
}
)
try:
result = ChatIdTag.create(**chatIdTag.model_dump())
if result:
return chatIdTag
else:
return None
except:
return None
def get_tags_by_user_id(self, user_id: str) -> List[TagModel]:
tag_names = [
ChatIdTagModel(**model_to_dict(chat_id_tag)).tag_name
for chat_id_tag in ChatIdTag.select()
.where(ChatIdTag.user_id == user_id)
.order_by(ChatIdTag.timestamp.desc())
]
return [
TagModel(**model_to_dict(tag))
for tag in Tag.select().where(Tag.name.in_(tag_names))
]
def get_tags_by_chat_id_and_user_id(
self, chat_id: str, user_id: str
) -> List[TagModel]:
tag_names = [
ChatIdTagModel(**model_to_dict(chat_id_tag)).tag_name
for chat_id_tag in ChatIdTag.select()
.where((ChatIdTag.user_id == user_id) & (ChatIdTag.chat_id == chat_id))
.order_by(ChatIdTag.timestamp.desc())
]
return [
TagModel(**model_to_dict(tag))
for tag in Tag.select().where(Tag.name.in_(tag_names))
]
def get_chat_ids_by_tag_name_and_user_id(
self, tag_name: str, user_id: str
) -> Optional[ChatIdTagModel]:
return [
ChatIdTagModel(**model_to_dict(chat_id_tag))
for chat_id_tag in ChatIdTag.select()
.where((ChatIdTag.user_id == user_id) & (ChatIdTag.tag_name == tag_name))
.order_by(ChatIdTag.timestamp.desc())
]
def count_chat_ids_by_tag_name_and_user_id(
self, tag_name: str, user_id: str
) -> int:
return (
ChatIdTag.select()
.where((ChatIdTag.tag_name == tag_name) & (ChatIdTag.user_id == user_id))
.count()
)
def delete_tag_by_tag_name_and_chat_id_and_user_id(
self, tag_name: str, chat_id: str, user_id: str
) -> bool:
try:
query = ChatIdTag.delete().where(
(ChatIdTag.tag_name == tag_name)
& (ChatIdTag.chat_id == chat_id)
& (ChatIdTag.user_id == user_id)
)
res = query.execute() # Remove the rows, return number of rows removed.
print(res)
tag_count = self.count_chat_ids_by_tag_name_and_user_id(tag_name, user_id)
if tag_count == 0:
# Remove tag item from Tag col as well
query = Tag.delete().where(
(Tag.name == tag_name) & (Tag.user_id == user_id)
)
query.execute() # Remove the rows, return number of rows removed.
return True
except Exception as e:
print("delete_tag", e)
return False
def delete_tags_by_chat_id_and_user_id(self, chat_id: str, user_id: str) -> bool:
tags = self.get_tags_by_chat_id_and_user_id(chat_id, user_id)
for tag in tags:
self.delete_tag_by_tag_name_and_chat_id_and_user_id(
tag.tag_name, chat_id, user_id
)
return True
Tags = TagTable(DB)

19
backend/apps/web/models/users.py
View file

@ -65,7 +65,7 @@ class UsersTable:
"name": name,
"email": email,
"role": role,
"profile_image_url": get_gravatar_url(email),
"profile_image_url": "/user.png",
"timestamp": int(time.time()),
}
)
@ -92,7 +92,8 @@ class UsersTable:
def get_users(self, skip: int = 0, limit: int = 50) -> List[UserModel]:
return [
UserModel(**model_to_dict(user))
for user in User.select().limit(limit).offset(skip)
for user in User.select()
# .limit(limit).offset(skip)
]
def get_num_users(self) -> Optional[int]:
@ -108,6 +109,20 @@ class UsersTable:
except:
return None
def update_user_profile_image_url_by_id(
self, id: str, profile_image_url: str
) -> Optional[UserModel]:
try:
query = User.update(profile_image_url=profile_image_url).where(
User.id == id
)
query.execute()
user = User.get(User.id == id)
return UserModel(**model_to_dict(user))
except:
return None
def update_user_by_id(self, id: str, updated: dict) -> Optional[UserModel]:
try:
query = User.update(**updated).where(User.id == id)

193
backend/apps/web/routers/auths.py
View file

@ -3,14 +3,16 @@ from fastapi import Depends, FastAPI, HTTPException, status
from datetime import datetime, timedelta
from typing import List, Union
from fastapi import APIRouter
from fastapi import APIRouter, status
from pydantic import BaseModel
import time
import uuid
import re
from apps.web.models.auths import (
SigninForm,
SignupForm,
UpdateProfileForm,
UpdatePasswordForm,
UserResponse,
SigninResponse,
@ -18,8 +20,13 @@ from apps.web.models.auths import (
)
from apps.web.models.users import Users
from utils.utils import get_password_hash, get_current_user, create_token
from utils.misc import get_gravatar_url, validate_email_format
from utils.utils import (
get_password_hash,
get_current_user,
get_admin_user,
create_token,
)
from utils.misc import parse_duration, validate_email_format
from constants import ERROR_MESSAGES
router = APIRouter()
@ -40,14 +47,37 @@ async def get_session_user(user=Depends(get_current_user)):
}
############################
# Update Profile
############################
@router.post("/update/profile", response_model=UserResponse)
async def update_profile(
form_data: UpdateProfileForm, session_user=Depends(get_current_user)
):
if session_user:
user = Users.update_user_by_id(
session_user.id,
{"profile_image_url": form_data.profile_image_url, "name": form_data.name},
)
if user:
return user
else:
raise HTTPException(400, detail=ERROR_MESSAGES.DEFAULT())
else:
raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
############################
# Update Password
############################
@router.post("/update/password", response_model=bool)
async def update_password(form_data: UpdatePasswordForm,
session_user=Depends(get_current_user)):
async def update_password(
form_data: UpdatePasswordForm, session_user=Depends(get_current_user)
):
if session_user:
user = Auths.authenticate_user(session_user.email, form_data.password)
@ -66,10 +96,13 @@ async def update_password(form_data: UpdatePasswordForm,
@router.post("/signin", response_model=SigninResponse)
async def signin(form_data: SigninForm):
async def signin(request: Request, form_data: SigninForm):
user = Auths.authenticate_user(form_data.email.lower(), form_data.password)
if user:
token = create_token(data={"email": user.email})
token = create_token(
data={"id": user.id},
expires_delta=parse_duration(request.app.state.JWT_EXPIRES_IN),
)
return {
"token": token,
@ -91,41 +124,50 @@ async def signin(form_data: SigninForm):
@router.post("/signup", response_model=SigninResponse)
async def signup(request: Request, form_data: SignupForm):
if request.app.state.ENABLE_SIGNUP:
if validate_email_format(form_data.email.lower()):
if not Users.get_user_by_email(form_data.email.lower()):
try:
role = "admin" if Users.get_num_users() == 0 else "pending"
hashed = get_password_hash(form_data.password)
user = Auths.insert_new_auth(form_data.email.lower(),
hashed, form_data.name, role)
if not request.app.state.ENABLE_SIGNUP:
raise HTTPException(
status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.ACCESS_PROHIBITED
)
if user:
token = create_token(data={"email": user.email})
# response.set_cookie(key='token', value=token, httponly=True)
if not validate_email_format(form_data.email.lower()):
raise HTTPException(
status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.INVALID_EMAIL_FORMAT
)
return {
"token": token,
"token_type": "Bearer",
"id": user.id,
"email": user.email,
"name": user.name,
"role": user.role,
"profile_image_url": user.profile_image_url,
}
else:
raise HTTPException(
500, detail=ERROR_MESSAGES.CREATE_USER_ERROR)
except Exception as err:
raise HTTPException(500,
detail=ERROR_MESSAGES.DEFAULT(err))
else:
raise HTTPException(400, detail=ERROR_MESSAGES.EMAIL_TAKEN)
if Users.get_user_by_email(form_data.email.lower()):
raise HTTPException(400, detail=ERROR_MESSAGES.EMAIL_TAKEN)
try:
role = (
"admin"
if Users.get_num_users() == 0
else request.app.state.DEFAULT_USER_ROLE
)
hashed = get_password_hash(form_data.password)
user = Auths.insert_new_auth(
form_data.email.lower(), hashed, form_data.name, role
)
if user:
token = create_token(
data={"id": user.id},
expires_delta=parse_duration(request.app.state.JWT_EXPIRES_IN),
)
# response.set_cookie(key='token', value=token, httponly=True)
return {
"token": token,
"token_type": "Bearer",
"id": user.id,
"email": user.email,
"name": user.name,
"role": user.role,
"profile_image_url": user.profile_image_url,
}
else:
raise HTTPException(400,
detail=ERROR_MESSAGES.INVALID_EMAIL_FORMAT)
else:
raise HTTPException(400, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
raise HTTPException(500, detail=ERROR_MESSAGES.CREATE_USER_ERROR)
except Exception as err:
raise HTTPException(500, detail=ERROR_MESSAGES.DEFAULT(err))
############################
@ -134,23 +176,64 @@ async def signup(request: Request, form_data: SignupForm):
@router.get("/signup/enabled", response_model=bool)
async def get_sign_up_status(request: Request, user=Depends(get_current_user)):
if user.role == "admin":
return request.app.state.ENABLE_SIGNUP
else:
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
async def get_sign_up_status(request: Request, user=Depends(get_admin_user)):
return request.app.state.ENABLE_SIGNUP
@router.get("/signup/enabled/toggle", response_model=bool)
async def toggle_sign_up(request: Request, user=Depends(get_current_user)):
if user.role == "admin":
request.app.state.ENABLE_SIGNUP = not request.app.state.ENABLE_SIGNUP
return request.app.state.ENABLE_SIGNUP
async def toggle_sign_up(request: Request, user=Depends(get_admin_user)):
request.app.state.ENABLE_SIGNUP = not request.app.state.ENABLE_SIGNUP
return request.app.state.ENABLE_SIGNUP
############################
# Default User Role
############################
@router.get("/signup/user/role")
async def get_default_user_role(request: Request, user=Depends(get_admin_user)):
return request.app.state.DEFAULT_USER_ROLE
class UpdateRoleForm(BaseModel):
role: str
@router.post("/signup/user/role")
async def update_default_user_role(
request: Request, form_data: UpdateRoleForm, user=Depends(get_admin_user)
):
if form_data.role in ["pending", "user", "admin"]:
request.app.state.DEFAULT_USER_ROLE = form_data.role
return request.app.state.DEFAULT_USER_ROLE
############################
# JWT Expiration
############################
@router.get("/token/expires")
async def get_token_expires_duration(request: Request, user=Depends(get_admin_user)):
return request.app.state.JWT_EXPIRES_IN
class UpdateJWTExpiresDurationForm(BaseModel):
duration: str
@router.post("/token/expires/update")
async def update_token_expires_duration(
request: Request,
form_data: UpdateJWTExpiresDurationForm,
user=Depends(get_admin_user),
):
pattern = r"^(-1|0|(-?\d+(\.\d+)?)(ms|s|m|h|d|w))$"
# Check if the input string matches the pattern
if re.match(pattern, form_data.duration):
request.app.state.JWT_EXPIRES_IN = form_data.duration
return request.app.state.JWT_EXPIRES_IN
else:
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
return request.app.state.JWT_EXPIRES_IN

193
backend/apps/web/routers/chats.py
View file

@ -1,7 +1,7 @@
from fastapi import Depends, Request, HTTPException, status
from datetime import datetime, timedelta
from typing import List, Union, Optional
from utils.utils import get_current_user
from utils.utils import get_current_user, get_admin_user
from fastapi import APIRouter
from pydantic import BaseModel
import json
@ -16,8 +16,15 @@ from apps.web.models.chats import (
Chats,
)
from utils.utils import (
bearer_scheme, )
from apps.web.models.tags import (
TagModel,
ChatIdTagModel,
ChatIdTagForm,
ChatTagsResponse,
Tags,
)
from constants import ERROR_MESSAGES
router = APIRouter()
@ -29,7 +36,8 @@ router = APIRouter()
@router.get("/", response_model=List[ChatTitleIdResponse])
async def get_user_chats(
user=Depends(get_current_user), skip: int = 0, limit: int = 50):
user=Depends(get_current_user), skip: int = 0, limit: int = 50
):
return Chats.get_chat_lists_by_user_id(user.id, skip, limit)
@ -41,9 +49,21 @@ async def get_user_chats(
@router.get("/all", response_model=List[ChatResponse])
async def get_all_user_chats(user=Depends(get_current_user)):
return [
ChatResponse(**{
**chat.model_dump(), "chat": json.loads(chat.chat)
}) for chat in Chats.get_all_chats_by_user_id(user.id)
ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
for chat in Chats.get_all_chats_by_user_id(user.id)
]
############################
# GetAllChatsInDB
############################
@router.get("/all/db", response_model=List[ChatResponse])
async def get_all_user_chats_in_db(user=Depends(get_admin_user)):
return [
ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
for chat in Chats.get_all_chats()
]
@ -54,8 +74,50 @@ async def get_all_user_chats(user=Depends(get_current_user)):
@router.post("/new", response_model=Optional[ChatResponse])
async def create_new_chat(form_data: ChatForm, user=Depends(get_current_user)):
chat = Chats.insert_new_chat(user.id, form_data)
return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
try:
chat = Chats.insert_new_chat(user.id, form_data)
return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
except Exception as e:
print(e)
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
)
############################
# GetAllTags
############################
@router.get("/tags/all", response_model=List[TagModel])
async def get_all_tags(user=Depends(get_current_user)):
try:
tags = Tags.get_tags_by_user_id(user.id)
return tags
except Exception as e:
print(e)
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
)
############################
# GetChatsByTags
############################
@router.get("/tags/tag/{tag_name}", response_model=List[ChatTitleIdResponse])
async def get_user_chats_by_tag_name(
tag_name: str, user=Depends(get_current_user), skip: int = 0, limit: int = 50
):
chat_ids = [
chat_id_tag.chat_id
for chat_id_tag in Tags.get_chat_ids_by_tag_name_and_user_id(tag_name, user.id)
]
print(chat_ids)
return Chats.get_chat_lists_by_chat_ids(chat_ids, skip, limit)
############################
@ -68,12 +130,11 @@ async def get_chat_by_id(id: str, user=Depends(get_current_user)):
chat = Chats.get_chat_by_id_and_user_id(id, user.id)
if chat:
return ChatResponse(**{
**chat.model_dump(), "chat": json.loads(chat.chat)
})
return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
else:
raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.NOT_FOUND)
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
)
############################
@ -82,17 +143,15 @@ async def get_chat_by_id(id: str, user=Depends(get_current_user)):
@router.post("/{id}", response_model=Optional[ChatResponse])
async def update_chat_by_id(id: str,
form_data: ChatForm,
user=Depends(get_current_user)):
async def update_chat_by_id(
id: str, form_data: ChatForm, user=Depends(get_current_user)
):
chat = Chats.get_chat_by_id_and_user_id(id, user.id)
if chat:
updated_chat = {**json.loads(chat.chat), **form_data.chat}
chat = Chats.update_chat_by_id(id, updated_chat)
return ChatResponse(**{
**chat.model_dump(), "chat": json.loads(chat.chat)
})
return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
@ -106,11 +165,103 @@ async def update_chat_by_id(id: str,
@router.delete("/{id}", response_model=bool)
async def delete_chat_by_id(id: str, user=Depends(get_current_user)):
async def delete_chat_by_id(request: Request, id: str, user=Depends(get_current_user)):
if (
user.role == "user"
and not request.app.state.USER_PERMISSIONS["chat"]["deletion"]
):
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
result = Chats.delete_chat_by_id_and_user_id(id, user.id)
return result
############################
# GetChatTagsById
############################
@router.get("/{id}/tags", response_model=List[TagModel])
async def get_chat_tags_by_id(id: str, user=Depends(get_current_user)):
tags = Tags.get_tags_by_chat_id_and_user_id(id, user.id)
if tags != None:
return tags
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
)
############################
# AddChatTagById
############################
@router.post("/{id}/tags", response_model=Optional[ChatIdTagModel])
async def add_chat_tag_by_id(
id: str, form_data: ChatIdTagForm, user=Depends(get_current_user)
):
tags = Tags.get_tags_by_chat_id_and_user_id(id, user.id)
if form_data.tag_name not in tags:
tag = Tags.add_tag_to_chat(user.id, form_data)
if tag:
return tag
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.NOT_FOUND,
)
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.DEFAULT()
)
############################
# DeleteChatTagById
############################
@router.delete("/{id}/tags", response_model=Optional[bool])
async def delete_chat_tag_by_id(
id: str, form_data: ChatIdTagForm, user=Depends(get_current_user)
):
result = Tags.delete_tag_by_tag_name_and_chat_id_and_user_id(
form_data.tag_name, id, user.id
)
if result:
return result
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
)
############################
# DeleteAllChatTagsById
############################
@router.delete("/{id}/tags/all", response_model=Optional[bool])
async def delete_all_chat_tags_by_id(id: str, user=Depends(get_current_user)):
result = Tags.delete_tags_by_chat_id_and_user_id(id, user.id)
if result:
return result
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
)
############################
# DeleteAllChats
############################

39
backend/apps/web/routers/configs.py
View file

@ -10,7 +10,7 @@ import uuid
from apps.web.models.users import Users
from utils.utils import get_password_hash, get_current_user, create_token
from utils.utils import get_password_hash, get_current_user, get_admin_user, create_token
from utils.misc import get_gravatar_url, validate_email_format
from constants import ERROR_MESSAGES
@ -21,20 +21,35 @@ class SetDefaultModelsForm(BaseModel):
models: str
class PromptSuggestion(BaseModel):
title: List[str]
content: str
class SetDefaultSuggestionsForm(BaseModel):
suggestions: List[PromptSuggestion]
############################
# SetDefaultModels
############################
@router.post("/default/models", response_model=str)
async def set_global_default_models(request: Request,
form_data: SetDefaultModelsForm,
user=Depends(get_current_user)):
if user.role == "admin":
request.app.state.DEFAULT_MODELS = form_data.models
return request.app.state.DEFAULT_MODELS
else:
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
async def set_global_default_models(
request: Request, form_data: SetDefaultModelsForm, user=Depends(get_admin_user)
):
request.app.state.DEFAULT_MODELS = form_data.models
return request.app.state.DEFAULT_MODELS
@router.post("/default/suggestions", response_model=List[PromptSuggestion])
async def set_global_default_suggestions(
request: Request,
form_data: SetDefaultSuggestionsForm,
user=Depends(get_admin_user),
):
data = form_data.model_dump()
request.app.state.DEFAULT_PROMPT_SUGGESTIONS = data["suggestions"]
return request.app.state.DEFAULT_PROMPT_SUGGESTIONS

158
backend/apps/web/routers/documents.py Normal file
View file

@ -0,0 +1,158 @@
from fastapi import Depends, FastAPI, HTTPException, status
from datetime import datetime, timedelta
from typing import List, Union, Optional
from fastapi import APIRouter
from pydantic import BaseModel
import json
from apps.web.models.documents import (
Documents,
DocumentForm,
DocumentUpdateForm,
DocumentModel,
DocumentResponse,
)
from utils.utils import get_current_user, get_admin_user
from constants import ERROR_MESSAGES
router = APIRouter()
############################
# GetDocuments
############################
@router.get("/", response_model=List[DocumentResponse])
async def get_documents(user=Depends(get_current_user)):
docs = [
DocumentResponse(
**{
**doc.model_dump(),
"content": json.loads(doc.content if doc.content else "{}"),
}
)
for doc in Documents.get_docs()
]
return docs
############################
# CreateNewDoc
############################
@router.post("/create", response_model=Optional[DocumentResponse])
async def create_new_doc(form_data: DocumentForm, user=Depends(get_admin_user)):
doc = Documents.get_doc_by_name(form_data.name)
if doc == None:
doc = Documents.insert_new_doc(user.id, form_data)
if doc:
return DocumentResponse(
**{
**doc.model_dump(),
"content": json.loads(doc.content if doc.content else "{}"),
}
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.FILE_EXISTS,
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.NAME_TAG_TAKEN,
)
############################
# GetDocByName
############################
@router.get("/name/{name}", response_model=Optional[DocumentResponse])
async def get_doc_by_name(name: str, user=Depends(get_current_user)):
doc = Documents.get_doc_by_name(name)
if doc:
return DocumentResponse(
**{
**doc.model_dump(),
"content": json.loads(doc.content if doc.content else "{}"),
}
)
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.NOT_FOUND,
)
############################
# TagDocByName
############################
class TagItem(BaseModel):
name: str
class TagDocumentForm(BaseModel):
name: str
tags: List[dict]
@router.post("/name/{name}/tags", response_model=Optional[DocumentResponse])
async def tag_doc_by_name(form_data: TagDocumentForm, user=Depends(get_current_user)):
doc = Documents.update_doc_content_by_name(form_data.name, {"tags": form_data.tags})
if doc:
return DocumentResponse(
**{
**doc.model_dump(),
"content": json.loads(doc.content if doc.content else "{}"),
}
)
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.NOT_FOUND,
)
############################
# UpdateDocByName
############################
@router.post("/name/{name}/update", response_model=Optional[DocumentResponse])
async def update_doc_by_name(
name: str, form_data: DocumentUpdateForm, user=Depends(get_admin_user)
):
doc = Documents.update_doc_by_name(name, form_data)
if doc:
return DocumentResponse(
**{
**doc.model_dump(),
"content": json.loads(doc.content if doc.content else "{}"),
}
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.NAME_TAG_TAKEN,
)
############################
# DeleteDocByName
############################
@router.delete("/name/{name}/delete", response_model=bool)
async def delete_doc_by_name(name: str, user=Depends(get_admin_user)):
result = Documents.delete_doc_by_name(name)
return result

25
backend/apps/web/routers/modelfiles.py
View file

@ -13,7 +13,7 @@ from apps.web.models.modelfiles import (
ModelfileResponse,
)
from utils.utils import get_current_user
from utils.utils import get_current_user, get_admin_user
from constants import ERROR_MESSAGES
router = APIRouter()
@ -37,13 +37,7 @@ async def get_modelfiles(skip: int = 0,
@router.post("/create", response_model=Optional[ModelfileResponse])
async def create_new_modelfile(form_data: ModelfileForm,
user=Depends(get_current_user)):
if user.role != "admin":
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
user=Depends(get_admin_user)):
modelfile = Modelfiles.insert_new_modelfile(user.id, form_data)
if modelfile:
@ -91,12 +85,7 @@ async def get_modelfile_by_tag_name(form_data: ModelfileTagNameForm,
@router.post("/update", response_model=Optional[ModelfileResponse])
async def update_modelfile_by_tag_name(form_data: ModelfileUpdateForm,
user=Depends(get_current_user)):
if user.role != "admin":
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
user=Depends(get_admin_user)):
modelfile = Modelfiles.get_modelfile_by_tag_name(form_data.tag_name)
if modelfile:
updated_modelfile = {
@ -127,12 +116,6 @@ async def update_modelfile_by_tag_name(form_data: ModelfileUpdateForm,
@router.delete("/delete", response_model=bool)
async def delete_modelfile_by_tag_name(form_data: ModelfileTagNameForm,
user=Depends(get_current_user)):
if user.role != "admin":
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
user=Depends(get_admin_user)):
result = Modelfiles.delete_modelfile_by_tag_name(form_data.tag_name)
return result

38
backend/apps/web/routers/prompts.py
View file

@ -8,7 +8,7 @@ import json
from apps.web.models.prompts import Prompts, PromptForm, PromptModel
from utils.utils import get_current_user
from utils.utils import get_current_user, get_admin_user
from constants import ERROR_MESSAGES
router = APIRouter()
@ -29,29 +29,21 @@ async def get_prompts(user=Depends(get_current_user)):
@router.post("/create", response_model=Optional[PromptModel])
async def create_new_prompt(form_data: PromptForm, user=Depends(get_current_user)):
if user.role != "admin":
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
async def create_new_prompt(form_data: PromptForm, user=Depends(get_admin_user)):
prompt = Prompts.get_prompt_by_command(form_data.command)
if prompt == None:
prompt = Prompts.insert_new_prompt(user.id, form_data)
if prompt:
return prompt
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.DEFAULT(),
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.COMMAND_TAKEN,
detail=ERROR_MESSAGES.DEFAULT(),
)
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.COMMAND_TAKEN,
)
############################
@ -79,14 +71,8 @@ async def get_prompt_by_command(command: str, user=Depends(get_current_user)):
@router.post("/command/{command}/update", response_model=Optional[PromptModel])
async def update_prompt_by_command(
command: str, form_data: PromptForm, user=Depends(get_current_user)
command: str, form_data: PromptForm, user=Depends(get_admin_user)
):
if user.role != "admin":
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
prompt = Prompts.update_prompt_by_command(f"/{command}", form_data)
if prompt:
return prompt
@ -103,12 +89,6 @@ async def update_prompt_by_command(
@router.delete("/command/{command}/delete", response_model=bool)
async def delete_prompt_by_command(command: str, user=Depends(get_current_user)):
if user.role != "admin":
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
async def delete_prompt_by_command(command: str, user=Depends(get_admin_user)):
result = Prompts.delete_prompt_by_command(f"/{command}")
return result

101
backend/apps/web/routers/users.py
View file

@ -1,4 +1,4 @@
from fastapi import Response
from fastapi import Response, Request
from fastapi import Depends, FastAPI, HTTPException, status
from datetime import datetime, timedelta
from typing import List, Union, Optional
@ -11,7 +11,7 @@ import uuid
from apps.web.models.users import UserModel, UserUpdateForm, UserRoleUpdateForm, Users
from apps.web.models.auths import Auths
from utils.utils import get_current_user, get_password_hash
from utils.utils import get_current_user, get_password_hash, get_admin_user
from constants import ERROR_MESSAGES
router = APIRouter()
@ -22,37 +22,43 @@ router = APIRouter()
@router.get("/", response_model=List[UserModel])
async def get_users(skip: int = 0, limit: int = 50, user=Depends(get_current_user)):
if user.role != "admin":
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
async def get_users(skip: int = 0, limit: int = 50, user=Depends(get_admin_user)):
return Users.get_users(skip, limit)
############################
# User Permissions
############################
@router.get("/permissions/user")
async def get_user_permissions(request: Request, user=Depends(get_admin_user)):
return request.app.state.USER_PERMISSIONS
@router.post("/permissions/user")
async def update_user_permissions(
request: Request, form_data: dict, user=Depends(get_admin_user)
):
request.app.state.USER_PERMISSIONS = form_data
return request.app.state.USER_PERMISSIONS
############################
# UpdateUserRole
############################
@router.post("/update/role", response_model=Optional[UserModel])
async def update_user_role(
form_data: UserRoleUpdateForm, user=Depends(get_current_user)
):
if user.role != "admin":
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
async def update_user_role(form_data: UserRoleUpdateForm, user=Depends(get_admin_user)):
if user.id != form_data.id:
return Users.update_user_role_by_id(form_data.id, form_data.role)
else:
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACTION_PROHIBITED,
)
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACTION_PROHIBITED,
)
############################
@ -62,14 +68,8 @@ async def update_user_role(
@router.post("/{user_id}/update", response_model=Optional[UserModel])
async def update_user_by_id(
user_id: str, form_data: UserUpdateForm, session_user=Depends(get_current_user)
user_id: str, form_data: UserUpdateForm, session_user=Depends(get_admin_user)
):
if session_user.role != "admin":
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
user = Users.get_user_by_id(user_id)
if user:
@ -98,18 +98,17 @@ async def update_user_by_id(
if updated_user:
return updated_user
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.DEFAULT(),
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.USER_NOT_FOUND,
detail=ERROR_MESSAGES.DEFAULT(),
)
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.USER_NOT_FOUND,
)
############################
# DeleteUserById
@ -117,25 +116,19 @@ async def update_user_by_id(
@router.delete("/{user_id}", response_model=bool)
async def delete_user_by_id(user_id: str, user=Depends(get_current_user)):
if user.role == "admin":
if user.id != user_id:
result = Auths.delete_auth_by_id(user_id)
async def delete_user_by_id(user_id: str, user=Depends(get_admin_user)):
if user.id != user_id:
result = Auths.delete_auth_by_id(user_id)
if result:
return True
if result:
return True
else:
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail=ERROR_MESSAGES.DELETE_USER_ERROR,
)
else:
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACTION_PROHIBITED,
)
else:
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail=ERROR_MESSAGES.DELETE_USER_ERROR,
)
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail=ERROR_MESSAGES.ACTION_PROHIBITED,
)

69
backend/apps/web/routers/utils.py
View file

@ -9,9 +9,11 @@ import os
import aiohttp
import json
from utils.misc import calculate_sha256
from utils.misc import calculate_sha256, get_gravatar_url
from config import OLLAMA_API_BASE_URL, DATA_DIR, UPLOAD_DIR
from constants import ERROR_MESSAGES
from config import OLLAMA_API_BASE_URL
router = APIRouter()
@ -40,10 +42,7 @@ def parse_huggingface_url(hf_url):
return None
async def download_file_stream(url,
file_path,
file_name,
chunk_size=1024 * 1024):
async def download_file_stream(url, file_path, file_name, chunk_size=1024 * 1024):
done = False
if os.path.exists(file_path):
@ -57,8 +56,7 @@ async def download_file_stream(url,
async with aiohttp.ClientSession(timeout=timeout) as session:
async with session.get(url, headers=headers) as response:
total_size = int(response.headers.get("content-length",
0)) + current_size
total_size = int(response.headers.get("content-length", 0)) + current_size
with open(file_path, "ab+") as file:
async for data in response.content.iter_chunked(chunk_size):
@ -91,13 +89,14 @@ async def download_file_stream(url,
@router.get("/download")
async def download(url: str, ):
async def download(
url: str,
):
# url = "https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF/resolve/main/stablelm-zephyr-3b.Q2_K.gguf"
file_name = parse_huggingface_url(url)
if file_name:
os.makedirs("./uploads", exist_ok=True)
file_path = os.path.join("./uploads", f"{file_name}")
file_path = f"{UPLOAD_DIR}/{file_name}"
return StreamingResponse(
download_file_stream(url, file_path, file_name),
@ -108,25 +107,29 @@ async def download(url: str, ):
@router.post("/upload")
async def upload(file: UploadFile = File(...)):
os.makedirs("./uploads", exist_ok=True)
file_path = os.path.join("./uploads", file.filename)
def upload(file: UploadFile = File(...)):
file_path = f"{UPLOAD_DIR}/{file.filename}"
async def file_write_stream():
total = 0
total_size = file.size
# Save file in chunks
with open(file_path, "wb+") as f:
for chunk in file.file:
f.write(chunk)
def file_process_stream():
total_size = os.path.getsize(file_path)
chunk_size = 1024 * 1024
done = False
try:
with open(file_path, "wb+") as f:
while True:
chunk = file.file.read(chunk_size)
with open(file_path, "rb") as f:
total = 0
done = False
while not done:
chunk = f.read(chunk_size)
if not chunk:
break
f.write(chunk)
done = True
continue
total += len(chunk)
done = total_size == total
progress = round((total / total_size) * 100, 2)
res = {
@ -134,7 +137,6 @@ async def upload(file: UploadFile = File(...)):
"total": total_size,
"completed": total,
}
yield f"data: {json.dumps(res)}\n\n"
if done:
@ -152,14 +154,21 @@ async def upload(file: UploadFile = File(...)):
"name": file.filename,
}
os.remove(file_path)
yield f"data: {json.dumps(res)}\n\n"
else:
raise "Ollama: Could not create blob, Please try again."
raise Exception(
"Ollama: Could not create blob, Please try again."
)
except Exception as e:
res = {"error": str(e)}
yield f"data: {json.dumps(res)}\n\n"
return StreamingResponse(file_write_stream(),
media_type="text/event-stream")
return StreamingResponse(file_process_stream(), media_type="text/event-stream")
@router.get("/gravatar")
async def get_gravatar(
email: str,
):
return get_gravatar_url(email)

258
backend/config.py
View file

@ -1,30 +1,28 @@
from dotenv import load_dotenv, find_dotenv
import os
import chromadb
from chromadb import Settings
from base64 import b64encode
from bs4 import BeautifulSoup
from pathlib import Path
import json
import markdown
import requests
import shutil
from secrets import token_bytes
from base64 import b64encode
from constants import ERROR_MESSAGES
from pathlib import Path
try:
from dotenv import load_dotenv, find_dotenv
load_dotenv(find_dotenv("../.env"))
####################################
# File Upload
####################################
UPLOAD_DIR = "./data/uploads"
Path(UPLOAD_DIR).mkdir(parents=True, exist_ok=True)
load_dotenv(find_dotenv("../.env"))
except ImportError:
print("dotenv not installed, skipping...")
WEBUI_NAME = "Open WebUI"
shutil.copyfile("../build/favicon.png", "./static/favicon.png")
####################################
# ENV (dev,test,prod)
@ -32,6 +30,141 @@ Path(UPLOAD_DIR).mkdir(parents=True, exist_ok=True)
ENV = os.environ.get("ENV", "dev")
try:
with open(f"../package.json", "r") as f:
PACKAGE_DATA = json.load(f)
except:
PACKAGE_DATA = {"version": "0.0.0"}
VERSION = PACKAGE_DATA["version"]
# Function to parse each section
def parse_section(section):
items = []
for li in section.find_all("li"):
# Extract raw HTML string
raw_html = str(li)
# Extract text without HTML tags
text = li.get_text(separator=" ", strip=True)
# Split into title and content
parts = text.split(": ", 1)
title = parts[0].strip() if len(parts) > 1 else ""
content = parts[1].strip() if len(parts) > 1 else text
items.append({"title": title, "content": content, "raw": raw_html})
return items
try:
with open("../CHANGELOG.md", "r") as file:
changelog_content = file.read()
except:
changelog_content = ""
# Convert markdown content to HTML
html_content = markdown.markdown(changelog_content)
# Parse the HTML content
soup = BeautifulSoup(html_content, "html.parser")
# Initialize JSON structure
changelog_json = {}
# Iterate over each version
for version in soup.find_all("h2"):
version_number = version.get_text().strip().split(" - ")[0][1:-1] # Remove brackets
date = version.get_text().strip().split(" - ")[1]
version_data = {"date": date}
# Find the next sibling that is a h3 tag (section title)
current = version.find_next_sibling()
print(current)
while current and current.name != "h2":
if current.name == "h3":
section_title = current.get_text().lower() # e.g., "added", "fixed"
section_items = parse_section(current.find_next_sibling("ul"))
version_data[section_title] = section_items
# Move to the next element
current = current.find_next_sibling()
changelog_json[version_number] = version_data
CHANGELOG = changelog_json
####################################
# CUSTOM_NAME
####################################
CUSTOM_NAME = os.environ.get("CUSTOM_NAME", "")
if CUSTOM_NAME:
try:
r = requests.get(f"https://api.openwebui.com/api/v1/custom/{CUSTOM_NAME}")
data = r.json()
if r.ok:
if "logo" in data:
url = (
f"https://api.openwebui.com{data['logo']}"
if data["logo"][0] == "/"
else data["logo"]
)
r = requests.get(url, stream=True)
if r.status_code == 200:
with open("./static/favicon.png", "wb") as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
WEBUI_NAME = data["name"]
except Exception as e:
print(e)
pass
####################################
# DATA/FRONTEND BUILD DIR
####################################
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
####################################
UPLOAD_DIR = f"{DATA_DIR}/uploads"
Path(UPLOAD_DIR).mkdir(parents=True, exist_ok=True)
####################################
# Cache DIR
####################################
CACHE_DIR = f"{DATA_DIR}/cache"
Path(CACHE_DIR).mkdir(parents=True, exist_ok=True)
####################################
# Docs DIR
####################################
DOCS_DIR = f"{DATA_DIR}/docs"
Path(DOCS_DIR).mkdir(parents=True, exist_ok=True)
####################################
# OLLAMA_API_BASE_URL
####################################
@ -54,11 +187,50 @@ OPENAI_API_BASE_URL = os.environ.get("OPENAI_API_BASE_URL", "")
if OPENAI_API_BASE_URL == "":
OPENAI_API_BASE_URL = "https://api.openai.com/v1"
####################################
# WEBUI
####################################
ENABLE_SIGNUP = os.environ.get("ENABLE_SIGNUP", True)
DEFAULT_MODELS = os.environ.get("DEFAULT_MODELS", None)
DEFAULT_PROMPT_SUGGESTIONS = (
CONFIG_DATA["ui"]["prompt_suggestions"]
if "ui" in CONFIG_DATA
and "prompt_suggestions" in CONFIG_DATA["ui"]
and type(CONFIG_DATA["ui"]["prompt_suggestions"]) is list
else [
{
"title": ["Help me study", "vocabulary for a college entrance exam"],
"content": "Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option.",
},
{
"title": ["Give me ideas", "for what to do with my kids' art"],
"content": "What are 5 creative things I could do with my kids' art? I don't want to throw them away, but it's also so much clutter.",
},
{
"title": ["Tell me a fun fact", "about the Roman Empire"],
"content": "Tell me a random fun fact about the Roman Empire",
},
{
"title": ["Show me a code snippet", "of a website's sticky header"],
"content": "Show me a code snippet of a website's sticky header in CSS and JavaScript.",
},
]
)
DEFAULT_USER_ROLE = os.getenv("DEFAULT_USER_ROLE", "pending")
USER_PERMISSIONS = {"chat": {"deletion": True}}
####################################
# WEBUI_VERSION
####################################
WEBUI_VERSION = os.environ.get("WEBUI_VERSION", "v1.0.0-alpha.50")
WEBUI_VERSION = os.environ.get("WEBUI_VERSION", "v1.0.0-alpha.100")
####################################
# WEBUI_AUTH (Required for security)
@ -67,22 +239,62 @@ WEBUI_VERSION = os.environ.get("WEBUI_VERSION", "v1.0.0-alpha.50")
WEBUI_AUTH = True
####################################
# WEBUI_JWT_SECRET_KEY
# WEBUI_SECRET_KEY
####################################
WEBUI_JWT_SECRET_KEY = os.environ.get("WEBUI_JWT_SECRET_KEY", "t0p-s3cr3t")
WEBUI_SECRET_KEY = os.environ.get(
"WEBUI_SECRET_KEY",
os.environ.get(
"WEBUI_JWT_SECRET_KEY", "t0p-s3cr3t"
), # DEPRECATED: remove at next major version
)
if WEBUI_AUTH and WEBUI_JWT_SECRET_KEY == "":
if WEBUI_AUTH and WEBUI_SECRET_KEY == "":
raise ValueError(ERROR_MESSAGES.ENV_VAR_NOT_FOUND)
####################################
# RAG
####################################
CHROMA_DATA_PATH = "./data/vector_db"
EMBED_MODEL = "all-MiniLM-L6-v2"
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"
)
CHROMA_CLIENT = chromadb.PersistentClient(
path=CHROMA_DATA_PATH, settings=Settings(allow_reset=True)
path=CHROMA_DATA_PATH,
settings=Settings(allow_reset=True, anonymized_telemetry=False),
)
CHUNK_SIZE = 1500
CHUNK_OVERLAP = 100
RAG_TEMPLATE = """Use the following context as your learned knowledge, inside <context></context> XML tags.
<context>
[context]
</context>
When answer to user:
- If you don't know, just say that you don't know.
- If you don't know when you are not sure, ask for clarification.
Avoid mentioning that you obtained the information from the context.
And answer according to the language of the user's question.
Given the context information, answer the query.
Query: [query]"""
####################################
# Transcribe
####################################
WHISPER_MODEL = os.getenv("WHISPER_MODEL", "base")
WHISPER_MODEL_DIR = os.getenv("WHISPER_MODEL_DIR", f"{CACHE_DIR}/whisper/models")
####################################
# Images
####################################
AUTOMATIC1111_BASE_URL = os.getenv("AUTOMATIC1111_BASE_URL", "")

8
backend/constants.py
View file

@ -18,6 +18,9 @@ class ERROR_MESSAGES(str, Enum):
"Uh-oh! This username is already registered. Please choose another username."
)
COMMAND_TAKEN = "Uh-oh! This command is already registered. Please choose another command string."
FILE_EXISTS = "Uh-oh! This file is already registered. Please choose another file."
NAME_TAG_TAKEN = "Uh-oh! This name tag is already registered. Please choose another name tag string."
INVALID_TOKEN = (
"Your session has expired or the token is invalid. Please sign in again."
)
@ -39,3 +42,8 @@ class ERROR_MESSAGES(str, Enum):
USER_NOT_FOUND = "We could not find what you're looking for :/"
API_KEY_NOT_FOUND = "Oops! It looks like there's a hiccup. The API key is missing. Please make sure to provide a valid API key to access this feature."
MALICIOUS = "Unusual activities detected, please try again in a few minutes."
PANDOC_NOT_INSTALLED = "Pandoc is not installed on the server. Please contact your administrator for assistance."
INCORRECT_FORMAT = (
lambda err="": f"Invalid format. Please use the correct format{err if err else ''}"
)

34
backend/data/config.json Normal file
View file

@ -0,0 +1,34 @@
{
"ui": {
"prompt_suggestions": [
{
"title": [
"Help me study",
"vocabulary for a college entrance exam"
],
"content": "Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option."
},
{
"title": [
"Give me ideas",
"for what to do with my kids' art"
],
"content": "What are 5 creative things I could do with my kids' art? I don't want to throw them away, but it's also so much clutter."
},
{
"title": [
"Tell me a fun fact",
"about the Roman Empire"
],
"content": "Tell me a random fun fact about the Roman Empire"
},
{
"title": [
"Show me a code snippet",
"of a website's sticky header"
],
"content": "Show me a code snippet of a website's sticky header in CSS and JavaScript."
}
]
}
}

3
backend/dev.sh
View file

@ -1 +1,2 @@
uvicorn main:app --port 8080 --host 0.0.0.0 --forwarded-allow-ips '*' --reload
PORT="${PORT:-8080}"
uvicorn main:app --port $PORT --host 0.0.0.0 --forwarded-allow-ips '*' --reload

42
backend/main.py
View file

@ -1,5 +1,9 @@
from bs4 import BeautifulSoup
import json
import markdown
import time
from fastapi import FastAPI, Request
from fastapi.staticfiles import StaticFiles
from fastapi import HTTPException
@ -10,11 +14,13 @@ from starlette.exceptions import HTTPException as StarletteHTTPException
from apps.ollama.main import app as ollama_app
from apps.openai.main import app as openai_app
from apps.web.main import app as webui_app
from apps.audio.main import app as audio_app
from apps.images.main import app as images_app
from apps.rag.main import app as rag_app
from config import ENV
from apps.web.main import app as webui_app
from config import WEBUI_NAME, ENV, VERSION, CHANGELOG, FRONTEND_BUILD_DIR
class SPAStaticFiles(StaticFiles):
@ -55,7 +61,35 @@ app.mount("/api/v1", webui_app)
app.mount("/ollama/api", ollama_app)
app.mount("/openai/api", openai_app)
app.mount("/images/api/v1", images_app)
app.mount("/audio/api/v1", audio_app)
app.mount("/rag/api/v1", rag_app)
app.mount("/", SPAStaticFiles(directory="../build", html=True), name="spa-static-files")
@app.get("/api/config")
async def get_app_config():
return {
"status": True,
"name": WEBUI_NAME,
"version": VERSION,
"images": images_app.state.ENABLED,
"default_models": webui_app.state.DEFAULT_MODELS,
"default_prompt_suggestions": webui_app.state.DEFAULT_PROMPT_SUGGESTIONS,
}
@app.get("/api/changelog")
async def get_app_changelog():
return CHANGELOG
app.mount("/static", StaticFiles(directory="static"), name="static")
app.mount(
"/",
SPAStaticFiles(directory=FRONTEND_BUILD_DIR, html=True),
name="spa-static-files",
)

11
backend/requirements.txt
View file

@ -22,8 +22,17 @@ chromadb
sentence_transformers
pypdf
docx2txt
unstructured
markdown
pypandoc
pandas
openpyxl
pyxlsb
xlrd
faster-whisper
PyJWT
pyjwt[crypto]
black
black

21
backend/start.sh
View file

@ -1,3 +1,22 @@
#!/usr/bin/env bash
uvicorn main:app --host 0.0.0.0 --port 8080 --forwarded-allow-ips '*'
SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
cd "$SCRIPT_DIR" || exit
KEY_FILE=.webui_secret_key
PORT="${PORT:-8080}"
if test "$WEBUI_SECRET_KEY $WEBUI_JWT_SECRET_KEY" = " "; then
echo No WEBUI_SECRET_KEY provided
if ! [ -e "$KEY_FILE" ]; then
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
fi
echo Loading WEBUI_SECRET_KEY from $KEY_FILE
WEBUI_SECRET_KEY=`cat $KEY_FILE`
fi
WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec uvicorn main:app --host 0.0.0.0 --port "$PORT" --forwarded-allow-ips '*'

32
backend/start_windows.bat Normal file
View file

@ -0,0 +1,32 @@
:: This method is not recommended, and we recommend you use the `start.sh` file with WSL instead.
@echo off
SETLOCAL ENABLEDELAYEDEXPANSION
:: Get the directory of the current script
SET "SCRIPT_DIR=%~dp0"
cd /d "%SCRIPT_DIR%" || exit /b
SET "KEY_FILE=.webui_secret_key"
SET "PORT=%PORT:8080%"
SET "WEBUI_SECRET_KEY=%WEBUI_SECRET_KEY%"
SET "WEBUI_JWT_SECRET_KEY=%WEBUI_JWT_SECRET_KEY%"
:: Check if WEBUI_SECRET_KEY and WEBUI_JWT_SECRET_KEY are not set
IF "%WEBUI_SECRET_KEY%%WEBUI_JWT_SECRET_KEY%" == " " (
echo No WEBUI_SECRET_KEY provided
IF NOT EXIST "%KEY_FILE%" (
echo Generating WEBUI_SECRET_KEY
:: Generate a random value to use as a WEBUI_SECRET_KEY in case the user didn't provide one
SET /p WEBUI_SECRET_KEY=<nul
FOR /L %%i IN (1,1,12) DO SET /p WEBUI_SECRET_KEY=<!random!>>%KEY_FILE%
echo WEBUI_SECRET_KEY generated
)
echo Loading WEBUI_SECRET_KEY from %KEY_FILE%
SET /p WEBUI_SECRET_KEY=<%KEY_FILE%
)
:: Execute uvicorn
SET "WEBUI_SECRET_KEY=%WEBUI_SECRET_KEY%"
uvicorn main:app --host 0.0.0.0 --port "%PORT%" --forwarded-allow-ips '*'

BIN
backend/static/favicon.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 6 KiB

81
backend/utils/misc.py
View file

@ -1,5 +1,8 @@
from pathlib import Path
import hashlib
import re
from datetime import timedelta
from typing import Optional
def get_gravatar_url(email):
@ -24,7 +27,85 @@ def calculate_sha256(file):
return sha256.hexdigest()
def calculate_sha256_string(string):
# Create a new SHA-256 hash object
sha256_hash = hashlib.sha256()
# Update the hash object with the bytes of the input string
sha256_hash.update(string.encode("utf-8"))
# Get the hexadecimal representation of the hash
hashed_string = sha256_hash.hexdigest()
return hashed_string
def validate_email_format(email: str) -> bool:
if not re.match(r"[^@]+@[^@]+\.[^@]+", email):
return False
return True
def sanitize_filename(file_name):
# Convert to lowercase
lower_case_file_name = file_name.lower()
# Remove special characters using regular expression
sanitized_file_name = re.sub(r"[^\w\s]", "", lower_case_file_name)
# Replace spaces with dashes
final_file_name = re.sub(r"\s+", "-", sanitized_file_name)
return final_file_name
def extract_folders_after_data_docs(path):
# Convert the path to a Path object if it's not already
path = Path(path)
# Extract parts of the path
parts = path.parts
# Find the index of '/data/docs' in the path
try:
index_data_docs = parts.index("data") + 1
index_docs = parts.index("docs", index_data_docs) + 1
except ValueError:
return []
# Exclude the filename and accumulate folder names
tags = []
folders = parts[index_docs:-1]
for idx, part in enumerate(folders):
tags.append("/".join(folders[: idx + 1]))
return tags
def parse_duration(duration: str) -> Optional[timedelta]:
if duration == "-1" or duration == "0":
return None
# Regular expression to find number and unit pairs
pattern = r"(-?\d+(\.\d+)?)(ms|s|m|h|d|w)"
matches = re.findall(pattern, duration)
if not matches:
raise ValueError("Invalid duration string")
total_duration = timedelta()
for number, _, unit in matches:
number = float(number)
if unit == "ms":
total_duration += timedelta(milliseconds=number)
elif unit == "s":
total_duration += timedelta(seconds=number)
elif unit == "m":
total_duration += timedelta(minutes=number)
elif unit == "h":
total_duration += timedelta(hours=number)
elif unit == "d":
total_duration += timedelta(days=number)
elif unit == "w":
total_duration += timedelta(weeks=number)
return total_duration

34
backend/utils/utils.py
View file

@ -14,14 +14,14 @@ import config
logging.getLogger("passlib").setLevel(logging.ERROR)
JWT_SECRET_KEY = config.WEBUI_JWT_SECRET_KEY
SESSION_SECRET = config.WEBUI_SECRET_KEY
ALGORITHM = "HS256"
##############
# Auth Utils
##############
bearer_scheme = HTTPBearer()
bearer_security = HTTPBearer()
pwd_context = CryptContext(schemes=["bcrypt"], deprecated="auto")
@ -42,13 +42,13 @@ def create_token(data: dict, expires_delta: Union[timedelta, None] = None) -> st
expire = datetime.utcnow() + expires_delta
payload.update({"exp": expire})
encoded_jwt = jwt.encode(payload, JWT_SECRET_KEY, algorithm=ALGORITHM)
encoded_jwt = jwt.encode(payload, SESSION_SECRET, algorithm=ALGORITHM)
return encoded_jwt
def decode_token(token: str) -> Optional[dict]:
try:
decoded = jwt.decode(token, JWT_SECRET_KEY, options={"verify_signature": False})
decoded = jwt.decode(token, SESSION_SECRET, algorithms=[ALGORITHM])
return decoded
except Exception as e:
return None
@ -58,10 +58,12 @@ def extract_token_from_auth_header(auth_header: str):
return auth_header[len("Bearer ") :]
def get_current_user(auth_token: HTTPAuthorizationCredentials = Depends(HTTPBearer())):
def get_current_user(
auth_token: HTTPAuthorizationCredentials = Depends(bearer_security),
):
data = decode_token(auth_token.credentials)
if data != None and "email" in data:
user = Users.get_user_by_email(data["email"])
if data != None and "id" in data:
user = Users.get_user_by_id(data["id"])
if user is None:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
@ -73,3 +75,21 @@ def get_current_user(auth_token: HTTPAuthorizationCredentials = Depends(HTTPBear
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.UNAUTHORIZED,
)
def get_verified_user(user=Depends(get_current_user)):
if user.role not in {"user", "admin"}:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
return user
def get_admin_user(user=Depends(get_current_user)):
if user.role != "admin":
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
return user

BIN
bun.lockb
View file

Binary file not shown.

BIN
demo.gif
View file

Binary file not shown.
Side by side Swipe Overlay

Before

Width:  |  Height:  |  Size: 5.9 MiB

After

Width:  |  Height:  |  Size: 6.1 MiB

11
docker-compose.yaml
View file

@ -10,26 +10,27 @@ services:
restart: unless-stopped
image: ollama/ollama:latest
ollama-webui:
open-webui:
build:
context: .
args:
OLLAMA_API_BASE_URL: '/ollama/api'
dockerfile: Dockerfile
image: ghcr.io/ollama-webui/ollama-webui:main
container_name: ollama-webui
image: ghcr.io/open-webui/open-webui:main
container_name: open-webui
volumes:
- ollama-webui:/app/backend/data
- open-webui:/app/backend/data
depends_on:
- ollama
ports:
- ${OLLAMA_WEBUI_PORT-3000}:8080
environment:
- 'OLLAMA_API_BASE_URL=http://ollama:11434/api'
- 'WEBUI_SECRET_KEY='
extra_hosts:
- host.docker.internal:host-gateway
restart: unless-stopped
volumes:
ollama: {}
ollama-webui: {}
open-webui: {}

61
docs/CONTRIBUTING.md Normal file
View file

@ -0,0 +1,61 @@
# Contributing to Open WebUI
🚀 **Welcome, Contributors!** 🚀
Your interest in contributing to Open WebUI is greatly appreciated. This document is here to guide you through the process, ensuring your contributions enhance the project effectively. Let's make Open WebUI even better, together!
## 📌 Key Points
### 🦙 Ollama vs. Open WebUI
It's crucial to distinguish between Ollama and Open WebUI:
- **Open WebUI** focuses on providing an intuitive and responsive web interface for chat interactions.
- **Ollama** is the underlying technology that powers these interactions.
If your issue or contribution pertains directly to the core Ollama technology, please direct it to the appropriate [Ollama project repository](https://ollama.com/). Open WebUI's repository is dedicated to the web interface aspect only.
### 🚨 Reporting Issues
Noticed something off? Have an idea? Check our [Issues tab](https://github.com/open-webui/oopen-webui/issues) to see if it's already been reported or suggested. If not, feel free to open a new issue. When reporting an issue, please follow our issue templates. These templates are designed to ensure that all necessary details are provided from the start, enabling us to address your concerns more efficiently.
> [!IMPORTANT]
>
> - **Template Compliance:** Please be aware that failure to follow the provided issue template, or not providing the requested information at all, will likely result in your issue being closed without further consideration. This approach is critical for maintaining the manageability and integrity of issue tracking.
>
> - **Detail is Key:** To ensure your issue is understood and can be effectively addressed, it's imperative to include comprehensive details. Descriptions should be clear, including steps to reproduce, expected outcomes, and actual results. Lack of sufficient detail may hinder our ability to resolve your issue.
### 🧭 Scope of Support
We've noticed an uptick in issues not directly related to Open WebUI but rather to the environment it's run in, especially Docker setups. While we strive to support Docker deployment, understanding Docker fundamentals is crucial for a smooth experience.
- **Docker Deployment Support**: Open WebUI supports Docker deployment. Familiarity with Docker is assumed. For Docker basics, please refer to the [official Docker documentation](https://docs.docker.com/get-started/overview/).
- **Advanced Configurations**: Setting up reverse proxies for HTTPS and managing Docker deployments requires foundational knowledge. There are numerous online resources available to learn these skills. Ensuring you have this knowledge will greatly enhance your experience with Open WebUI and similar projects.
## 💡 Contributing
Looking to contribute? Great! Here's how you can help:
### 🛠 Pull Requests
We welcome pull requests. Before submitting one, please:
1. Discuss your idea or issue in the [issues section](https://github.com/open-webui/open-webui/issues).
2. Follow the project's coding standards and include tests for new features.
3. Update documentation as necessary.
4. Write clear, descriptive commit messages.
### 📚 Documentation & Tutorials
Help us make Open WebUI more accessible by improving documentation, writing tutorials, or creating guides on setting up and optimizing the web UI.
### 🤔 Questions & Feedback
Got questions or feedback? Join our [Discord community](https://discord.gg/5rJgQTnV4s) or open an issue. We're here to help!
## 🙏 Thank You!
Your contributions, big or small, make a significant impact on Open WebUI. We're excited to see what you bring to the project!
Together, let's create an even more powerful tool for the community. 🌟

20
docs/SECURITY.md Normal file
View file

@ -0,0 +1,20 @@
# Security Policy
Our primary goal is to ensure the protection and confidentiality of sensitive data stored by users on open-webui.
## Supported Versions
| Version | Supported |
| ------- | ------------------ |
| main | :white_check_mark: |
| others | :x: |
## Reporting a Vulnerability
If you discover a security issue within our system, please notify us immediately via a pull request or contact us on discord.
## Product Security
We regularly audit our internal processes and system's architecture for vulnerabilities using a combination of automated and manual testing techniques.
We are planning on implementing SAST and SCA scans in our project soon.

199
docs/apache.md Normal file
View file

@ -0,0 +1,199 @@
# Hosting UI and Models separately
Sometimes, its beneficial to host Ollama, separate from the UI, but retain the RAG and RBAC support features shared across users:
# Open WebUI Configuration
## UI Configuration
For the UI configuration, you can set up the Apache VirtualHost as follows:
```
# Assuming you have a website hosting this UI at "server.com"
<VirtualHost 192.168.1.100:80>
ServerName server.com
DocumentRoot /home/server/public_html
ProxyPass / http://server.com:3000/ nocanon
ProxyPassReverse / http://server.com:3000/
</VirtualHost>
```
Enable the site first before you can request SSL:
`a2ensite server.com.conf` # this will enable the site. a2ensite is short for "Apache 2 Enable Site"
```
# For SSL
<VirtualHost 192.168.1.100:443>
ServerName server.com
DocumentRoot /home/server/public_html
ProxyPass / http://server.com:3000/ nocanon
ProxyPassReverse / http://server.com:3000/
SSLEngine on
SSLCertificateFile /etc/ssl/virtualmin/170514456861234/ssl.cert
SSLCertificateKeyFile /etc/ssl/virtualmin/170514456861234/ssl.key
SSLProtocol all -SSLv2 -SSLv3 -TLSv1 -TLSv1.1
SSLProxyEngine on
SSLCACertificateFile /etc/ssl/virtualmin/170514456865864/ssl.ca
</VirtualHost>
```
I'm using virtualmin here for my SSL clusters, but you can also use certbot directly or your preferred SSL method. To use SSL:
### Prerequisites.
Run the following commands:
`snap install certbot --classic`
`snap apt install python3-certbot-apache` (this will install the apache plugin).
Navigate to the apache sites-available directory:
`cd /etc/apache2/sites-available/`
Create server.com.conf if it is not yet already created, containing the above `<virtualhost>` configuration (it should match your case. Modify as necessary). Use the one without the SSL:
Once it's created, run `certbot --apache -d server.com`, this will request and add/create an SSL keys for you as well as create the server.com.le-ssl.conf
# Configuring Ollama Server
On your latest installation of Ollama, make sure that you have setup your api server from the official Ollama reference:
[Ollama FAQ](https://github.com/jmorganca/ollama/blob/main/docs/faq.md)
### TL;DR
The guide doesn't seem to match the current updated service file on linux. So, we will address it here:
Unless when you're compiling Ollama from source, installing with the standard install `curl https://ollama.com/install.sh | sh` creates a file called `ollama.service` in /etc/systemd/system. You can use nano to edit the file:
```
sudo nano /etc/systemd/system/ollama.service
```
Add the following lines:
```
Environment="OLLAMA_HOST=0.0.0.0:11434" # this line is mandatory. You can also specify
```
For instance:
```
[Unit]
Description=Ollama Service
After=network-online.target
[Service]
ExecStart=/usr/local/bin/ollama serve
Environment="OLLAMA_HOST=0.0.0.0:11434" # this line is mandatory. You can also specify 192.168.254.109:DIFFERENT_PORT, format
Environment="OLLAMA_ORIGINS=http://192.168.254.106:11434,https://models.server.city" # this line is optional
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/s>
[Install]
WantedBy=default.target
```
Save the file by pressing CTRL+S, then press CTRL+X
When your computer restarts, the Ollama server will now be listening on the IP:PORT you specified, in this case 0.0.0.0:11434, or 192.168.254.106:11434 (whatever your local IP address is). Make sure that your router is correctly configured to serve pages from that local IP by forwarding 11434 to your local IP server.
# Ollama Model Configuration
## For the Ollama model configuration, use the following Apache VirtualHost setup:
Navigate to the apache sites-available directory:
`cd /etc/apache2/sites-available/`
`nano models.server.city.conf` # match this with your ollama server domain
Add the folloing virtualhost containing this example (modify as needed):
```
# Assuming you have a website hosting this UI at "models.server.city"
<IfModule mod_ssl.c>
<VirtualHost 192.168.254.109:443>
DocumentRoot "/var/www/html/"
ServerName models.server.city
<Directory "/var/www/html/">
Options None
Require all granted
</Directory>
ProxyRequests Off
ProxyPreserveHost On
ProxyAddHeaders On
SSLProxyEngine on
ProxyPass / http://server.city:1000/ nocanon # or port 11434
ProxyPassReverse / http://server.city:1000/ # or port 11434
SSLCertificateFile /etc/letsencrypt/live/models.server.city/fullchain.pem
SSLCertificateKeyFile /etc/letsencrypt/live/models.server.city/privkey.pem
Include /etc/letsencrypt/options-ssl-apache.conf
</VirtualHost>
</IfModule>
```
You may need to enable the site first (if you haven't done so yet) before you can request SSL:
`a2ensite models.server.city.conf`
#### For the SSL part of Ollama server
Run the following commands:
Navigate to the apache sites-available directory:
`cd /etc/apache2/sites-available/`
`certbot --apache -d server.com`
```
<VirtualHost 192.168.254.109:80>
DocumentRoot "/var/www/html/"
ServerName models.server.city
<Directory "/var/www/html/">
Options None
Require all granted
</Directory>
ProxyRequests Off
ProxyPreserveHost On
ProxyAddHeaders On
SSLProxyEngine on
ProxyPass / http://server.city:1000/ nocanon # or port 11434
ProxyPassReverse / http://server.city:1000/ # or port 11434
RewriteEngine on
RewriteCond %{SERVER_NAME} =models.server.city
RewriteRule ^ https://%{SERVER_NAME}%{REQUEST_URI} [END,NE,R=permanent]
</VirtualHost>
```
Don't forget to restart/reload Apache with `systemctl reload apache2`
Open your site at https://server.com!
**Congratulations**, your _**Open-AI-like Chat-GPT style UI**_ is now serving AI with RAG, RBAC and multimodal features! Download Ollama models if you haven't yet done so!
If you encounter any misconfiguration or errors, please file an issue or engage with our discussion. There are a lot of friendly developers here to assist you.
Let's make this UI much more user friendly for everyone!
Thanks for making open-webui your UI Choice for AI!
This doc is made by **Bob Reyes**, your **Open-WebUI** fan from the Philippines.

1
kubernetes/helm/.helmignore
View file

@ -0,0 +1 @@
values-minikube.yaml

22
kubernetes/helm/Chart.yaml
View file

@ -1,5 +1,21 @@
apiVersion: v2
name: ollama-webui
description: "Ollama Web UI: A User-Friendly Web Interface for Chat Interactions 👋"
name: open-webui
version: 1.0.0
icon: https://raw.githubusercontent.com/ollama-webui/ollama-webui/main/static/favicon.png
appVersion: "latest"
home: https://www.openwebui.com/
icon: https://raw.githubusercontent.com/open-webui/open-webui/main/static/favicon.png
description: "Open WebUI: A User-Friendly Web Interface for Chat Interactions 👋"
keywords:
- llm
- chat
- web-ui
sources:
- https://github.com/open-webui/open-webui/tree/main/kubernetes/helm
- https://hub.docker.com/r/ollama/ollama
- https://github.com/open-webui/open-webui/pkgs/container/open-webui
annotations:
licenses: MIT

47
kubernetes/helm/templates/_helpers.tpl Normal file
View file

@ -0,0 +1,47 @@
{{- define "open-webui.name" -}}
{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
{{- end -}}
{{- define "ollama.name" -}}
ollama
{{- end -}}
{{- define "ollama.url" -}}
{{- printf "http://%s.%s.svc.cluster.local:%d/api" (include "ollama.name" .) (.Release.Namespace) (.Values.ollama.service.port | int) }}
{{- end }}
{{- define "chart.name" -}}
{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
{{- end }}
{{- define "base.labels" -}}
helm.sh/chart: {{ include "chart.name" . }}
{{- if .Chart.AppVersion }}
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
{{- end }}
app.kubernetes.io/managed-by: {{ .Release.Service }}
{{- end }}
{{- define "base.selectorLabels" -}}
app.kubernetes.io/instance: {{ .Release.Name }}
{{- end -}}
{{- define "open-webui.selectorLabels" -}}
{{ include "base.selectorLabels" . }}
app.kubernetes.io/component: {{ .Chart.Name }}
{{- end }}
{{- define "open-webui.labels" -}}
{{ include "base.labels" . }}
{{ include "open-webui.selectorLabels" . }}
{{- end }}
{{- define "ollama.selectorLabels" -}}
{{ include "base.selectorLabels" . }}
app.kubernetes.io/component: {{ include "ollama.name" . }}
{{- end }}
{{- define "ollama.labels" -}}
{{ include "base.labels" . }}
{{ include "ollama.selectorLabels" . }}
{{- end }}

4
kubernetes/helm/templates/ollama-namespace.yaml
View file

@ -1,4 +0,0 @@
apiVersion: v1
kind: Namespace
metadata:
name: {{ .Values.namespace }}

20
kubernetes/helm/templates/ollama-service.yaml
View file

@ -1,13 +1,21 @@
apiVersion: v1
kind: Service
metadata:
name: ollama-service
namespace: {{ .Values.namespace }}
name: {{ include "ollama.name" . }}
labels:
{{- include "ollama.labels" . | nindent 4 }}
{{- with .Values.ollama.service.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
type: {{ .Values.ollama.service.type }}
selector:
app: ollama
{{- include "ollama.selectorLabels" . | nindent 4 }}
{{- with .Values.ollama.service }}
type: {{ .type }}
ports:
- protocol: TCP
port: {{ .Values.ollama.servicePort }}
targetPort: {{ .Values.ollama.servicePort }}
name: http
port: {{ .port }}
targetPort: http
{{- end }}

83
kubernetes/helm/templates/ollama-statefulset.yaml
View file

@ -1,24 +1,43 @@
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: ollama
namespace: {{ .Values.namespace }}
name: {{ include "ollama.name" . }}
labels:
{{- include "ollama.labels" . | nindent 4 }}
{{- with .Values.ollama.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
serviceName: "ollama"
serviceName: {{ include "ollama.name" . }}
replicas: {{ .Values.ollama.replicaCount }}
selector:
matchLabels:
app: ollama
{{- include "ollama.selectorLabels" . | nindent 6 }}
template:
metadata:
labels:
app: ollama
{{- include "ollama.labels" . | nindent 8 }}
{{- with .Values.ollama.podAnnotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
enableServiceLinks: false
automountServiceAccountToken: false
{{- with .Values.ollama.runtimeClassName }}
runtimeClassName: {{ . }}
{{- end }}
containers:
- name: ollama
image: {{ .Values.ollama.image }}
- name: {{ include "ollama.name" . }}
{{- with .Values.ollama.image }}
image: {{ .repository }}:{{ .tag }}
imagePullPolicy: {{ .pullPolicy }}
{{- end }}
tty: true
ports:
- containerPort: {{ .Values.ollama.servicePort }}
- name: http
containerPort: {{ .Values.ollama.service.containerPort }}
env:
{{- if .Values.ollama.gpu.enabled }}
- name: PATH
@ -27,29 +46,51 @@ spec:
value: /usr/local/nvidia/lib:/usr/local/nvidia/lib64
- name: NVIDIA_DRIVER_CAPABILITIES
value: compute,utility
{{- end}}
{{- if .Values.ollama.resources }}
resources: {{- toYaml .Values.ollama.resources | nindent 10 }}
{{- end }}
{{- with .Values.ollama.resources }}
resources: {{- toYaml . | nindent 10 }}
{{- end }}
volumeMounts:
- name: ollama-volume
- name: data
mountPath: /root/.ollama
tty: true
{{- with .Values.ollama.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.ollama.tolerations }}
tolerations:
{{- if .Values.ollama.gpu.enabled }}
- key: nvidia.com/gpu
operator: Exists
effect: NoSchedule
{{- end }}
{{- toYaml . | nindent 8 }}
{{- end }}
volumes:
{{- if and .Values.ollama.persistence.enabled .Values.ollama.persistence.existingClaim }}
- name: data
persistentVolumeClaim:
claimName: {{ .Values.ollama.persistence.existingClaim }}
{{- else if not .Values.ollama.persistence.enabled }}
- name: data
emptyDir: {}
{{- else if and .Values.ollama.persistence.enabled (not .Values.ollama.persistence.existingClaim) }}
[]
volumeClaimTemplates:
- metadata:
name: ollama-volume
name: data
labels:
{{- include "ollama.selectorLabels" . | nindent 8 }}
{{- with .Values.ollama.persistence.annotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
accessModes: [ "ReadWriteOnce" ]
accessModes:
{{- range .Values.ollama.persistence.accessModes }}
- {{ . | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.ollama.volumeSize }}
storage: {{ .Values.ollama.persistence.size | quote }}
storageClass: {{ .Values.ollama.persistence.storageClass }}
{{- with .Values.ollama.persistence.selector }}
selector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- end }}

52
kubernetes/helm/templates/webui-deployment.yaml
View file

@ -1,38 +1,62 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: ollama-webui-deployment
namespace: {{ .Values.namespace }}
name: {{ include "open-webui.name" . }}
labels:
{{- include "open-webui.labels" . | nindent 4 }}
{{- with .Values.webui.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
replicas: 1
replicas: {{ .Values.webui.replicaCount }}
selector:
matchLabels:
app: ollama-webui
{{- include "open-webui.selectorLabels" . | nindent 6 }}
template:
metadata:
labels:
app: ollama-webui
{{- include "open-webui.labels" . | nindent 8 }}
{{- with .Values.webui.podAnnotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
enableServiceLinks: false
automountServiceAccountToken: false
containers:
- name: ollama-webui
image: {{ .Values.webui.image }}
- name: {{ .Chart.Name }}
{{- with .Values.webui.image }}
image: {{ .repository }}:{{ .tag | default $.Chart.AppVersion }}
imagePullPolicy: {{ .pullPolicy }}
{{- end }}
ports:
- containerPort: 8080
{{- if .Values.webui.resources }}
resources: {{- toYaml .Values.webui.resources | nindent 10 }}
- name: http
containerPort: {{ .Values.webui.service.containerPort }}
{{- with .Values.webui.resources }}
resources: {{- toYaml . | nindent 10 }}
{{- end }}
volumeMounts:
- name: webui-volume
- name: data
mountPath: /app/backend/data
env:
- name: OLLAMA_API_BASE_URL
value: "http://ollama-service.{{ .Values.namespace }}.svc.cluster.local:{{ .Values.ollama.servicePort }}/api"
value: {{ include "ollama.url" . | quote }}
tty: true
{{- with .Values.webui.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
volumes:
- name: webui-volume
{{- if and .Values.webui.persistence.enabled .Values.webui.persistence.existingClaim }}
- name: data
persistentVolumeClaim:
claimName: ollama-webui-pvc
claimName: {{ .Values.webui.persistence.existingClaim }}
{{- else if not .Values.webui.persistence.enabled }}
- name: data
emptyDir: {}
{{- else if and .Values.webui.persistence.enabled (not .Values.webui.persistence.existingClaim) }}
- name: data
persistentVolumeClaim:
claimName: {{ include "open-webui.name" . }}
{{- end }}

24
kubernetes/helm/templates/webui-ingress.yaml
View file

@ -2,13 +2,23 @@
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: ollama-webui-ingress
namespace: {{ .Values.namespace }}
{{- if .Values.webui.ingress.annotations }}
name: {{ include "open-webui.name" . }}
labels:
{{- include "open-webui.labels" . | nindent 4 }}
{{- with .Values.webui.ingress.annotations }}
annotations:
{{ toYaml .Values.webui.ingress.annotations | trimSuffix "\n" | indent 4 }}
{{- end }}
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
{{- with .Values.webui.ingress.class }}
ingressClassName: {{ . }}
{{- end }}
{{- if .Values.webui.ingress.tls }}
tls:
- hosts:
- {{ .Values.webui.ingress.host | quote }}
secretName: {{ default (printf "%s-tls" .Release.Name) .Values.webui.ingress.existingSecret }}
{{- end }}
rules:
- host: {{ .Values.webui.ingress.host }}
http:
@ -17,7 +27,7 @@ spec:
pathType: Prefix
backend:
service:
name: ollama-webui-service
name: {{ include "open-webui.name" . }}
port:
number: {{ .Values.webui.servicePort }}
name: http
{{- end }}

23
kubernetes/helm/templates/webui-pvc.yaml
View file

@ -1,12 +1,25 @@
{{- if and .Values.webui.persistence.enabled (not .Values.webui.persistence.existingClaim) }}
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ include "open-webui.name" . }}
labels:
app: ollama-webui
name: ollama-webui-pvc
namespace: {{ .Values.namespace }}
{{- include "open-webui.selectorLabels" . | nindent 4 }}
{{- with .Values.webui.persistence.annotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
accessModes: [ "ReadWriteOnce" ]
accessModes:
{{- range .Values.webui.persistence.accessModes }}
- {{ . | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.webui.volumeSize }}
storage: {{ .Values.webui.persistence.size }}
storageClass: {{ .Values.webui.persistence.storageClass }}
{{- with .Values.webui.persistence.selector }}
selector:
{{- toYaml . | nindent 4 }}
{{- end }}
{{- end }}

27
kubernetes/helm/templates/webui-service.yaml
View file

@ -1,15 +1,24 @@
apiVersion: v1
kind: Service
metadata:
name: ollama-webui-service
namespace: {{ .Values.namespace }}
name: {{ include "open-webui.name" . }}
labels:
{{- include "open-webui.labels" . | nindent 4 }}
{{- with .Values.webui.service.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
type: {{ .Values.webui.service.type }} # Default: NodePort # Use LoadBalancer if you're on a cloud that supports it
selector:
app: ollama-webui
{{- include "open-webui.selectorLabels" . | nindent 4 }}
{{- with .Values.webui.service }}
type: {{ .type }}
ports:
- protocol: TCP
port: {{ .Values.webui.servicePort }}
targetPort: {{ .Values.webui.servicePort }}
# If using NodePort, you can optionally specify the nodePort:
# nodePort: 30000
- protocol: TCP
name: http
port: {{ .port }}
targetPort: http
{{- if .nodePort }}
nodePort: {{ .nodePort | int }}
{{- end }}
{{- end }}

27
kubernetes/helm/values-minikube.yaml Normal file
View file

@ -0,0 +1,27 @@
ollama:
resources:
requests:
cpu: "2000m"
memory: "2Gi"
limits:
cpu: "4000m"
memory: "4Gi"
nvidia.com/gpu: "0"
service:
type: ClusterIP
gpu:
enabled: false
webui:
resources:
requests:
cpu: "500m"
memory: "500Mi"
limits:
cpu: "1000m"
memory: "1Gi"
ingress:
enabled: true
host: open-webui.minikube.local
service:
type: NodePort

96
kubernetes/helm/values.yaml
View file

@ -1,38 +1,72 @@
namespace: ollama-namespace
nameOverride: ""
ollama:
annotations: {}
podAnnotations: {}
replicaCount: 1
image: ollama/ollama:latest
servicePort: 11434
resources:
limits:
cpu: "2000m"
memory: "2Gi"
nvidia.com/gpu: "0"
volumeSize: 1Gi
image:
repository: ollama/ollama
tag: latest
pullPolicy: Always
resources: {}
persistence:
enabled: true
size: 30Gi
existingClaim: ""
accessModes:
- ReadWriteOnce
storageClass: ""
selector: {}
annotations: {}
nodeSelector: {}
# -- If using a special runtime container such as nvidia, set it here.
runtimeClassName: ""
tolerations:
- key: nvidia.com/gpu
operator: Exists
effect: NoSchedule
service:
type: ClusterIP
annotations: {}
port: 80
containerPort: 11434
gpu:
# -- Enable additional ENV values to help Ollama discover GPU usage
enabled: false
webui:
annotations: {}
podAnnotations: {}
replicaCount: 1
image:
repository: ghcr.io/open-webui/open-webui
tag: ""
pullPolicy: Always
resources: {}
ingress:
enabled: false
class: ""
# -- Use appropriate annotations for your Ingress controller, e.g., for NGINX:
# nginx.ingress.kubernetes.io/rewrite-target: /
annotations: {}
host: ""
tls: false
existingSecret: ""
persistence:
enabled: true
size: 2Gi
existingClaim: ""
# -- If using multiple replicas, you must update accessModes to ReadWriteMany
accessModes:
- ReadWriteOnce
storageClass: ""
selector: {}
annotations: {}
nodeSelector: {}
tolerations: []
service:
type: ClusterIP
gpu:
enabled: false
webui:
replicaCount: 1
image: ghcr.io/ollama-webui/ollama-webui:main
servicePort: 8080
resources:
limits:
cpu: "500m"
memory: "500Mi"
ingress:
enabled: true
annotations:
# Use appropriate annotations for your Ingress controller, e.g., for NGINX:
# nginx.ingress.kubernetes.io/rewrite-target: /
host: ollama.minikube.local
volumeSize: 1Gi
nodeSelector: {}
tolerations: []
service:
type: NodePort
annotations: {}
port: 80
containerPort: 8080
nodePort: ""

2
kubernetes/manifest/base/ollama-service.yaml
View file

@ -2,7 +2,7 @@ apiVersion: v1
kind: Service
metadata:
name: ollama-service
namespace: ollama-namespace
namespace: open-webui
spec:
selector:
app: ollama

10
kubernetes/manifest/base/ollama-statefulset.yaml
View file

@ -2,7 +2,7 @@ apiVersion: apps/v1
kind: StatefulSet
metadata:
name: ollama
namespace: ollama-namespace
namespace: open-webui
spec:
serviceName: "ollama"
replicas: 1
@ -20,9 +20,13 @@ spec:
ports:
- containerPort: 11434
resources:
limits:
requests:
cpu: "2000m"
memory: "2Gi"
limits:
cpu: "4000m"
memory: "4Gi"
nvidia.com/gpu: "0"
volumeMounts:
- name: ollama-volume
mountPath: /root/.ollama
@ -34,4 +38,4 @@ spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
storage: 1Gi
storage: 30Gi

2
kubernetes/manifest/base/ollama-namespace.yaml → kubernetes/manifest/base/open-webui.yaml
View file

@ -1,4 +1,4 @@
apiVersion: v1
kind: Namespace
metadata:
name: ollama-namespace
name: open-webui

28
kubernetes/manifest/base/webui-deployment.yaml
View file

@ -1,28 +1,38 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: ollama-webui-deployment
namespace: ollama-namespace
name: open-webui-deployment
namespace: open-webui
spec:
replicas: 1
selector:
matchLabels:
app: ollama-webui
app: open-webui
template:
metadata:
labels:
app: ollama-webui
app: open-webui
spec:
containers:
- name: ollama-webui
image: ghcr.io/ollama-webui/ollama-webui:main
- name: open-webui
image: ghcr.io/open-webui/open-webui:main
ports:
- containerPort: 8080
resources:
limits:
requests:
cpu: "500m"
memory: "500Mi"
limits:
cpu: "1000m"
memory: "1Gi"
env:
- name: OLLAMA_API_BASE_URL
value: "http://ollama-service.ollama-namespace.svc.cluster.local:11434/api"
tty: true
value: "http://ollama-service.open-webui.svc.cluster.local:11434/api"
tty: true
volumeMounts:
- name: webui-volume
mountPath: /app/backend/data
volumes:
- name: webui-volume
persistentVolumeClaim:
claimName: ollama-webui-pvc

8
kubernetes/manifest/base/webui-ingress.yaml
View file

@ -1,20 +1,20 @@
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: ollama-webui-ingress
namespace: ollama-namespace
name: open-webui-ingress
namespace: open-webui
#annotations:
# Use appropriate annotations for your Ingress controller, e.g., for NGINX:
# nginx.ingress.kubernetes.io/rewrite-target: /
spec:
rules:
- host: ollama.minikube.local
- host: open-webui.minikube.local
http:
paths:
- path: /
pathType: Prefix
backend:
service:
name: ollama-webui-service
name: open-webui-service
port:
number: 8080

12
kubernetes/manifest/base/webui-pvc.yaml Normal file
View file

@ -0,0 +1,12 @@
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
labels:
app: ollama-webui
name: ollama-webui-pvc
namespace: open-webui
spec:
accessModes: ["ReadWriteOnce"]
resources:
requests:
storage: 2Gi

6
kubernetes/manifest/base/webui-service.yaml
View file

@ -1,12 +1,12 @@
apiVersion: v1
kind: Service
metadata:
name: ollama-webui-service
namespace: ollama-namespace
name: open-webui-service
namespace: open-webui
spec:
type: NodePort # Use LoadBalancer if you're on a cloud that supports it
selector:
app: ollama-webui
app: open-webui
ports:
- protocol: TCP
port: 8080

3
kubernetes/manifest/kustomization.yaml
View file

@ -1,10 +1,11 @@
resources:
- base/ollama-namespace.yaml
- base/open-webui.yaml
- base/ollama-service.yaml
- base/ollama-statefulset.yaml
- base/webui-deployment.yaml
- base/webui-service.yaml
- base/webui-ingress.yaml
- base/webui-pvc.yaml
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization

2
kubernetes/manifest/patches/ollama-statefulset-gpu.yaml
View file

@ -2,7 +2,7 @@ apiVersion: apps/v1
kind: StatefulSet
metadata:
name: ollama
namespace: ollama-namespace
namespace: open-webui
spec:
selector:
matchLabels:

477
package-lock.json generated
View file

@ -1,14 +1,15 @@
{
"name": "ollama-webui",
"version": "0.0.1",
"name": "open-webui",
"version": "v1.0.0-alpha.101",
"lockfileVersion": 2,
"requires": true,
"packages": {
"": {
"name": "ollama-webui",
"version": "0.0.1",
"name": "open-webui",
"version": "v1.0.0-alpha.101",
"dependencies": {
"@sveltejs/adapter-node": "^1.3.1",
"async": "^3.2.5",
"dayjs": "^1.11.10",
"file-saver": "^2.0.5",
"highlight.js": "^11.9.0",
@ -37,6 +38,7 @@
"prettier-plugin-svelte": "^2.10.1",
"svelte": "^4.0.5",
"svelte-check": "^3.4.3",
"svelte-confetti": "^1.3.2",
"tailwindcss": "^3.3.3",
"tslib": "^2.4.1",
"typescript": "^5.0.0",
@ -76,51 +78,6 @@
"node": ">=6.0.0"
}
},
"node_modules/@esbuild/android-arm": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.18.20.tgz",
"integrity": "sha512-fyi7TDI/ijKKNZTUJAQqiG5T7YjJXgnzkURqmGj13C6dCqckZBLdl4h7bkhHt/t0WP+zO9/zwroDvANaOqO5Sw==",
"cpu": [
"arm"
],
"optional": true,
"os": [
"android"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/android-arm64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.18.20.tgz",
"integrity": "sha512-Nz4rJcchGDtENV0eMKUNa6L12zz2zBDXuhj/Vjh18zGqB44Bi7MBMSXjgunJgjRhCmKOjnPuZp4Mb6OKqtMHLQ==",
"cpu": [
"arm64"
],
"optional": true,
"os": [
"android"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/android-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.18.20.tgz",
"integrity": "sha512-8GDdlePJA8D6zlZYJV/jnrRAi6rOiNaCC/JclcXpB+KIuvfBN4owLtgzY2bsxnx666XjJx2kDPUmnTtR8qKQUg==",
"cpu": [
"x64"
],
"optional": true,
"os": [
"android"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/darwin-arm64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.18.20.tgz",
@ -136,276 +93,6 @@
"node": ">=12"
}
},
"node_modules/@esbuild/darwin-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.18.20.tgz",
"integrity": "sha512-pc5gxlMDxzm513qPGbCbDukOdsGtKhfxD1zJKXjCCcU7ju50O7MeAZ8c4krSJcOIJGFR+qx21yMMVYwiQvyTyQ==",
"cpu": [
"x64"
],
"optional": true,
"os": [
"darwin"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/freebsd-arm64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.18.20.tgz",
"integrity": "sha512-yqDQHy4QHevpMAaxhhIwYPMv1NECwOvIpGCZkECn8w2WFHXjEwrBn3CeNIYsibZ/iZEUemj++M26W3cNR5h+Tw==",
"cpu": [
"arm64"
],
"optional": true,
"os": [
"freebsd"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/freebsd-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.18.20.tgz",
"integrity": "sha512-tgWRPPuQsd3RmBZwarGVHZQvtzfEBOreNuxEMKFcd5DaDn2PbBxfwLcj4+aenoh7ctXcbXmOQIn8HI6mCSw5MQ==",
"cpu": [
"x64"
],
"optional": true,
"os": [
"freebsd"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-arm": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.18.20.tgz",
"integrity": "sha512-/5bHkMWnq1EgKr1V+Ybz3s1hWXok7mDFUMQ4cG10AfW3wL02PSZi5kFpYKrptDsgb2WAJIvRcDm+qIvXf/apvg==",
"cpu": [
"arm"
],
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-arm64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.18.20.tgz",
"integrity": "sha512-2YbscF+UL7SQAVIpnWvYwM+3LskyDmPhe31pE7/aoTMFKKzIc9lLbyGUpmmb8a8AixOL61sQ/mFh3jEjHYFvdA==",
"cpu": [
"arm64"
],
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-ia32": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.18.20.tgz",
"integrity": "sha512-P4etWwq6IsReT0E1KHU40bOnzMHoH73aXp96Fs8TIT6z9Hu8G6+0SHSw9i2isWrD2nbx2qo5yUqACgdfVGx7TA==",
"cpu": [
"ia32"
],
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-loong64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.18.20.tgz",
"integrity": "sha512-nXW8nqBTrOpDLPgPY9uV+/1DjxoQ7DoB2N8eocyq8I9XuqJ7BiAMDMf9n1xZM9TgW0J8zrquIb/A7s3BJv7rjg==",
"cpu": [
"loong64"
],
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-mips64el": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.18.20.tgz",
"integrity": "sha512-d5NeaXZcHp8PzYy5VnXV3VSd2D328Zb+9dEq5HE6bw6+N86JVPExrA6O68OPwobntbNJ0pzCpUFZTo3w0GyetQ==",
"cpu": [
"mips64el"
],
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-ppc64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.18.20.tgz",
"integrity": "sha512-WHPyeScRNcmANnLQkq6AfyXRFr5D6N2sKgkFo2FqguP44Nw2eyDlbTdZwd9GYk98DZG9QItIiTlFLHJHjxP3FA==",
"cpu": [
"ppc64"
],
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-riscv64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.18.20.tgz",
"integrity": "sha512-WSxo6h5ecI5XH34KC7w5veNnKkju3zBRLEQNY7mv5mtBmrP/MjNBCAlsM2u5hDBlS3NGcTQpoBvRzqBcRtpq1A==",
"cpu": [
"riscv64"
],
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-s390x": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.18.20.tgz",
"integrity": "sha512-+8231GMs3mAEth6Ja1iK0a1sQ3ohfcpzpRLH8uuc5/KVDFneH6jtAJLFGafpzpMRO6DzJ6AvXKze9LfFMrIHVQ==",
"cpu": [
"s390x"
],
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.18.20.tgz",
"integrity": "sha512-UYqiqemphJcNsFEskc73jQ7B9jgwjWrSayxawS6UVFZGWrAAtkzjxSqnoclCXxWtfwLdzU+vTpcNYhpn43uP1w==",
"cpu": [
"x64"
],
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/netbsd-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.18.20.tgz",
"integrity": "sha512-iO1c++VP6xUBUmltHZoMtCUdPlnPGdBom6IrO4gyKPFFVBKioIImVooR5I83nTew5UOYrk3gIJhbZh8X44y06A==",
"cpu": [
"x64"
],
"optional": true,
"os": [
"netbsd"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/openbsd-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.18.20.tgz",
"integrity": "sha512-e5e4YSsuQfX4cxcygw/UCPIEP6wbIL+se3sxPdCiMbFLBWu0eiZOJ7WoD+ptCLrmjZBK1Wk7I6D/I3NglUGOxg==",
"cpu": [
"x64"
],
"optional": true,
"os": [
"openbsd"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/sunos-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.18.20.tgz",
"integrity": "sha512-kDbFRFp0YpTQVVrqUd5FTYmWo45zGaXe0X8E1G/LKFC0v8x0vWrhOWSLITcCn63lmZIxfOMXtCfti/RxN/0wnQ==",
"cpu": [
"x64"
],
"optional": true,
"os": [
"sunos"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/win32-arm64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.18.20.tgz",
"integrity": "sha512-ddYFR6ItYgoaq4v4JmQQaAI5s7npztfV4Ag6NrhiaW0RrnOXqBkgwZLofVTlq1daVTQNhtI5oieTvkRPfZrePg==",
"cpu": [
"arm64"
],
"optional": true,
"os": [
"win32"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/win32-ia32": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.18.20.tgz",
"integrity": "sha512-Wv7QBi3ID/rROT08SABTS7eV4hX26sVduqDOTe1MvGMjNd3EjOz4b7zeexIR62GTIEKrfJXKL9LFxTYgkyeu7g==",
"cpu": [
"ia32"
],
"optional": true,
"os": [
"win32"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/win32-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.18.20.tgz",
"integrity": "sha512-kTdfRcSiDfQca/y9QIkng02avJ+NCaQvrMejlsB3RRv5sE9rRoeBPISaZpKxHELzRxZyLvNts1P27W3wV+8geQ==",
"cpu": [
"x64"
],
"optional": true,
"os": [
"win32"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@eslint-community/eslint-utils": {
"version": "4.4.0",
"resolved": "https://registry.npmjs.org/@eslint-community/eslint-utils/-/eslint-utils-4.4.0.tgz",
@ -1250,6 +937,11 @@
"node": ">=8"
}
},
"node_modules/async": {
"version": "3.2.5",
"resolved": "https://registry.npmjs.org/async/-/async-3.2.5.tgz",
"integrity": "sha512-baNZyqaaLhyLVKm/DlvdW051MSgO6b8eVfIezl9E5PqWxFgzLm/wQntEW4zOytVburDEr0JlALEpdOFwvErLsg=="
},
"node_modules/autoprefixer": {
"version": "10.4.16",
"resolved": "https://registry.npmjs.org/autoprefixer/-/autoprefixer-10.4.16.tgz",
@ -3483,6 +3175,15 @@
"svelte": "^3.55.0 || ^4.0.0-next.0 || ^4.0.0"
}
},
"node_modules/svelte-confetti": {
"version": "1.3.2",
"resolved": "https://registry.npmjs.org/svelte-confetti/-/svelte-confetti-1.3.2.tgz",
"integrity": "sha512-R+JwFTC7hIgWVA/OuXrkj384B7CMoceb0t9VacyW6dORTQg0pWojVBB8Bo3tM30cLEQE48Fekzqgx+XSzHESMA==",
"dev": true,
"peerDependencies": {
"svelte": "^4.0.0"
}
},
"node_modules/svelte-eslint-parser": {
"version": "0.33.1",
"resolved": "https://registry.npmjs.org/svelte-eslint-parser/-/svelte-eslint-parser-0.33.1.tgz",
@ -4022,138 +3723,12 @@
"@jridgewell/trace-mapping": "^0.3.9"
}
},
"@esbuild/android-arm": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.18.20.tgz",
"integrity": "sha512-fyi7TDI/ijKKNZTUJAQqiG5T7YjJXgnzkURqmGj13C6dCqckZBLdl4h7bkhHt/t0WP+zO9/zwroDvANaOqO5Sw==",
"optional": true
},
"@esbuild/android-arm64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.18.20.tgz",
"integrity": "sha512-Nz4rJcchGDtENV0eMKUNa6L12zz2zBDXuhj/Vjh18zGqB44Bi7MBMSXjgunJgjRhCmKOjnPuZp4Mb6OKqtMHLQ==",
"optional": true
},
"@esbuild/android-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.18.20.tgz",
"integrity": "sha512-8GDdlePJA8D6zlZYJV/jnrRAi6rOiNaCC/JclcXpB+KIuvfBN4owLtgzY2bsxnx666XjJx2kDPUmnTtR8qKQUg==",
"optional": true
},
"@esbuild/darwin-arm64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.18.20.tgz",
"integrity": "sha512-bxRHW5kHU38zS2lPTPOyuyTm+S+eobPUnTNkdJEfAddYgEcll4xkT8DB9d2008DtTbl7uJag2HuE5NZAZgnNEA==",
"optional": true
},
"@esbuild/darwin-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.18.20.tgz",
"integrity": "sha512-pc5gxlMDxzm513qPGbCbDukOdsGtKhfxD1zJKXjCCcU7ju50O7MeAZ8c4krSJcOIJGFR+qx21yMMVYwiQvyTyQ==",
"optional": true
},
"@esbuild/freebsd-arm64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.18.20.tgz",
"integrity": "sha512-yqDQHy4QHevpMAaxhhIwYPMv1NECwOvIpGCZkECn8w2WFHXjEwrBn3CeNIYsibZ/iZEUemj++M26W3cNR5h+Tw==",
"optional": true
},
"@esbuild/freebsd-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.18.20.tgz",
"integrity": "sha512-tgWRPPuQsd3RmBZwarGVHZQvtzfEBOreNuxEMKFcd5DaDn2PbBxfwLcj4+aenoh7ctXcbXmOQIn8HI6mCSw5MQ==",
"optional": true
},
"@esbuild/linux-arm": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.18.20.tgz",
"integrity": "sha512-/5bHkMWnq1EgKr1V+Ybz3s1hWXok7mDFUMQ4cG10AfW3wL02PSZi5kFpYKrptDsgb2WAJIvRcDm+qIvXf/apvg==",
"optional": true
},
"@esbuild/linux-arm64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.18.20.tgz",
"integrity": "sha512-2YbscF+UL7SQAVIpnWvYwM+3LskyDmPhe31pE7/aoTMFKKzIc9lLbyGUpmmb8a8AixOL61sQ/mFh3jEjHYFvdA==",
"optional": true
},
"@esbuild/linux-ia32": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.18.20.tgz",
"integrity": "sha512-P4etWwq6IsReT0E1KHU40bOnzMHoH73aXp96Fs8TIT6z9Hu8G6+0SHSw9i2isWrD2nbx2qo5yUqACgdfVGx7TA==",
"optional": true
},
"@esbuild/linux-loong64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.18.20.tgz",
"integrity": "sha512-nXW8nqBTrOpDLPgPY9uV+/1DjxoQ7DoB2N8eocyq8I9XuqJ7BiAMDMf9n1xZM9TgW0J8zrquIb/A7s3BJv7rjg==",
"optional": true
},
"@esbuild/linux-mips64el": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.18.20.tgz",
"integrity": "sha512-d5NeaXZcHp8PzYy5VnXV3VSd2D328Zb+9dEq5HE6bw6+N86JVPExrA6O68OPwobntbNJ0pzCpUFZTo3w0GyetQ==",
"optional": true
},
"@esbuild/linux-ppc64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.18.20.tgz",
"integrity": "sha512-WHPyeScRNcmANnLQkq6AfyXRFr5D6N2sKgkFo2FqguP44Nw2eyDlbTdZwd9GYk98DZG9QItIiTlFLHJHjxP3FA==",
"optional": true
},
"@esbuild/linux-riscv64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.18.20.tgz",
"integrity": "sha512-WSxo6h5ecI5XH34KC7w5veNnKkju3zBRLEQNY7mv5mtBmrP/MjNBCAlsM2u5hDBlS3NGcTQpoBvRzqBcRtpq1A==",
"optional": true
},
"@esbuild/linux-s390x": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.18.20.tgz",
"integrity": "sha512-+8231GMs3mAEth6Ja1iK0a1sQ3ohfcpzpRLH8uuc5/KVDFneH6jtAJLFGafpzpMRO6DzJ6AvXKze9LfFMrIHVQ==",
"optional": true
},
"@esbuild/linux-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.18.20.tgz",
"integrity": "sha512-UYqiqemphJcNsFEskc73jQ7B9jgwjWrSayxawS6UVFZGWrAAtkzjxSqnoclCXxWtfwLdzU+vTpcNYhpn43uP1w==",
"optional": true
},
"@esbuild/netbsd-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.18.20.tgz",
"integrity": "sha512-iO1c++VP6xUBUmltHZoMtCUdPlnPGdBom6IrO4gyKPFFVBKioIImVooR5I83nTew5UOYrk3gIJhbZh8X44y06A==",
"optional": true
},
"@esbuild/openbsd-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.18.20.tgz",
"integrity": "sha512-e5e4YSsuQfX4cxcygw/UCPIEP6wbIL+se3sxPdCiMbFLBWu0eiZOJ7WoD+ptCLrmjZBK1Wk7I6D/I3NglUGOxg==",
"optional": true
},
"@esbuild/sunos-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.18.20.tgz",
"integrity": "sha512-kDbFRFp0YpTQVVrqUd5FTYmWo45zGaXe0X8E1G/LKFC0v8x0vWrhOWSLITcCn63lmZIxfOMXtCfti/RxN/0wnQ==",
"optional": true
},
"@esbuild/win32-arm64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.18.20.tgz",
"integrity": "sha512-ddYFR6ItYgoaq4v4JmQQaAI5s7npztfV4Ag6NrhiaW0RrnOXqBkgwZLofVTlq1daVTQNhtI5oieTvkRPfZrePg==",
"optional": true
},
"@esbuild/win32-ia32": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.18.20.tgz",
"integrity": "sha512-Wv7QBi3ID/rROT08SABTS7eV4hX26sVduqDOTe1MvGMjNd3EjOz4b7zeexIR62GTIEKrfJXKL9LFxTYgkyeu7g==",
"optional": true
},
"@esbuild/win32-x64": {
"version": "0.18.20",
"resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.18.20.tgz",
"integrity": "sha512-kTdfRcSiDfQca/y9QIkng02avJ+NCaQvrMejlsB3RRv5sE9rRoeBPISaZpKxHELzRxZyLvNts1P27W3wV+8geQ==",
"optional": true
},
"@eslint-community/eslint-utils": {
"version": "4.4.0",
"resolved": "https://registry.npmjs.org/@eslint-community/eslint-utils/-/eslint-utils-4.4.0.tgz",
@ -4735,6 +4310,11 @@
"integrity": "sha512-HGyxoOTYUyCM6stUe6EJgnd4EoewAI7zMdfqO+kGjnlZmBDz/cR5pf8r/cR4Wq60sL/p0IkcjUEEPwS3GFrIyw==",
"dev": true
},
"async": {
"version": "3.2.5",
"resolved": "https://registry.npmjs.org/async/-/async-3.2.5.tgz",
"integrity": "sha512-baNZyqaaLhyLVKm/DlvdW051MSgO6b8eVfIezl9E5PqWxFgzLm/wQntEW4zOytVburDEr0JlALEpdOFwvErLsg=="
},
"autoprefixer": {
"version": "10.4.16",
"resolved": "https://registry.npmjs.org/autoprefixer/-/autoprefixer-10.4.16.tgz",
@ -6282,6 +5862,13 @@
"typescript": "^5.0.3"
}
},
"svelte-confetti": {
"version": "1.3.2",
"resolved": "https://registry.npmjs.org/svelte-confetti/-/svelte-confetti-1.3.2.tgz",
"integrity": "sha512-R+JwFTC7hIgWVA/OuXrkj384B7CMoceb0t9VacyW6dORTQg0pWojVBB8Bo3tM30cLEQE48Fekzqgx+XSzHESMA==",
"dev": true,
"requires": {}
},
"svelte-eslint-parser": {
"version": "0.33.1",
"resolved": "https://registry.npmjs.org/svelte-eslint-parser/-/svelte-eslint-parser-0.33.1.tgz",

8
package.json
View file

@ -1,6 +1,6 @@
{
"name": "ollama-webui",
"version": "0.0.1",
"name": "open-webui",
"version": "0.1.102",
"private": true,
"scripts": {
"dev": "vite dev --host",
@ -32,6 +32,7 @@
"prettier-plugin-svelte": "^2.10.1",
"svelte": "^4.0.5",
"svelte-check": "^3.4.3",
"svelte-confetti": "^1.3.2",
"tailwindcss": "^3.3.3",
"tslib": "^2.4.1",
"typescript": "^5.0.0",
@ -40,6 +41,7 @@
"type": "module",
"dependencies": {
"@sveltejs/adapter-node": "^1.3.1",
"async": "^3.2.5",
"dayjs": "^1.11.10",
"file-saver": "^2.0.5",
"highlight.js": "^11.9.0",
@ -51,4 +53,4 @@
"tippy.js": "^6.3.7",
"uuid": "^9.0.1"
}
}
}

7
run-compose.sh
View file

@ -11,8 +11,8 @@ TICK='\u2713'
# Detect GPU driver
get_gpu_driver() {
# Detect NVIDIA GPUs
if lspci | grep -i nvidia >/dev/null; then
# Detect NVIDIA GPUs using lspci or nvidia-smi
if lspci | grep -i nvidia >/dev/null || nvidia-smi >/dev/null 2>&1; then
echo "nvidia"
return
fi
@ -181,6 +181,9 @@ else
DEFAULT_COMPOSE_COMMAND+=" -f docker-compose.data.yaml"
export OLLAMA_DATA_DIR=$data_dir # Set OLLAMA_DATA_DIR environment variable
fi
if [[ -n $webui_port ]]; then
export OLLAMA_WEBUI_PORT=$webui_port # Set OLLAMA_WEBUI_PORT environment variable
fi
DEFAULT_COMPOSE_COMMAND+=" up -d"
DEFAULT_COMPOSE_COMMAND+=" --remove-orphans"
DEFAULT_COMPOSE_COMMAND+=" --force-recreate"

22
run-ollama-docker.sh
View file

@ -1,7 +1,19 @@
#!/bin/bash
host_port=11434
container_port=11434
read -r -p "Do you want ollama in Docker with GPU support? (y/n): " use_gpu
docker rm -f ollama || true
docker pull ollama/ollama
# CPU Only
docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
# GPU Support
# docker run -d --gpus=all -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
docker pull ollama/ollama:latest
docker_args="-d -v ollama:/root/.ollama -p $host_port:$container_port --name ollama ollama/ollama"
if [ "$use_gpu" = "y" ]; then
docker_args="--gpus=all $docker_args"
fi
docker run $docker_args
docker image prune -f

24
run.sh
View file

@ -1,5 +1,19 @@
docker build -t ollama-webui .
docker stop ollama-webui || true
docker rm ollama-webui || true
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v ollama-webui:/app/backend/data --name ollama-webui --restart always ollama-webui
docker image prune -f
#!/bin/bash
image_name="open-webui"
container_name="open-webui"
host_port=3000
container_port=8080
docker build -t "$image_name" .
docker stop "$container_name" &>/dev/null || true
docker rm "$container_name" &>/dev/null || true
docker run -d -p "$host_port":"$container_port" \
--add-host=host.docker.internal:host-gateway \
-v "${image_name}:/app/backend/data" \
--name "$container_name" \
--restart always \
"$image_name"
docker image prune -f

4
src/app.css
View file

@ -37,8 +37,8 @@ math {
}
::-webkit-scrollbar {
height: 0.45rem;
width: 0.35rem;
height: 0.4rem;
width: 0.4rem;
}
::-webkit-scrollbar-track {

31
src/lib/apis/audio/index.ts Normal file
View file

@ -0,0 +1,31 @@
import { AUDIO_API_BASE_URL } from '$lib/constants';
export const transcribeAudio = async (token: string, file: File) => {
const data = new FormData();
data.append('file', file);
let error = null;
const res = await fetch(`${AUDIO_API_BASE_URL}/transcribe`, {
method: 'POST',
headers: {
Accept: 'application/json',
authorization: `Bearer ${token}`
},
body: data
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
error = err.detail;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};

145
src/lib/apis/auths/index.ts
View file

@ -89,6 +89,37 @@ export const userSignUp = async (name: string, email: string, password: string)
return res;
};
export const updateUserProfile = async (token: string, name: string, profileImageUrl: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/auths/update/profile`, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
},
body: JSON.stringify({
name: name,
profile_image_url: profileImageUrl
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = err.detail;
return null;
});
if (error) {
throw error;
}
return res;
};
export const updateUserPassword = async (token: string, password: string, newPassword: string) => {
let error = null;
@ -147,6 +178,63 @@ export const getSignUpEnabledStatus = async (token: string) => {
return res;
};
export const getDefaultUserRole = async (token: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/auths/signup/user/role`, {
method: 'GET',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${token}`
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = err.detail;
return null;
});
if (error) {
throw error;
}
return res;
};
export const updateDefaultUserRole = async (token: string, role: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/auths/signup/user/role`, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${token}`
},
body: JSON.stringify({
role: role
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = err.detail;
return null;
});
if (error) {
throw error;
}
return res;
};
export const toggleSignUpEnabledStatus = async (token: string) => {
let error = null;
@ -173,3 +261,60 @@ export const toggleSignUpEnabledStatus = async (token: string) => {
return res;
};
export const getJWTExpiresDuration = async (token: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/auths/token/expires`, {
method: 'GET',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${token}`
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = err.detail;
return null;
});
if (error) {
throw error;
}
return res;
};
export const updateJWTExpiresDuration = async (token: string, duration: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/auths/token/expires/update`, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${token}`
},
body: JSON.stringify({
duration: duration
})
})
.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;
};

228
src/lib/apis/chats/index.ts
View file

@ -93,6 +93,99 @@ export const getAllChats = async (token: string) => {
return res;
};
export const getAllUserChats = async (token: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/chats/all/db`, {
method: 'GET',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.then((json) => {
return json;
})
.catch((err) => {
error = err;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};
export const getAllChatTags = async (token: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/chats/tags/all`, {
method: 'GET',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.then((json) => {
return json;
})
.catch((err) => {
error = err;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};
export const getChatListByTagName = async (token: string = '', tagName: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/chats/tags/tag/${tagName}`, {
method: 'GET',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.then((json) => {
return json;
})
.catch((err) => {
error = err;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};
export const getChatById = async (token: string, id: string) => {
let error = null;
@ -170,6 +263,141 @@ export const deleteChatById = async (token: string, id: string) => {
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.then((json) => {
return json;
})
.catch((err) => {
error = err.detail;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};
export const getTagsById = async (token: string, id: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/tags`, {
method: 'GET',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.then((json) => {
return json;
})
.catch((err) => {
error = err;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};
export const addTagById = async (token: string, id: string, tagName: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/tags`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
},
body: JSON.stringify({
tag_name: tagName,
chat_id: id
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.then((json) => {
return json;
})
.catch((err) => {
error = err;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};
export const deleteTagById = async (token: string, id: string, tagName: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/tags`, {
method: 'DELETE',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
},
body: JSON.stringify({
tag_name: tagName,
chat_id: id
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.then((json) => {
return json;
})
.catch((err) => {
error = err;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};
export const deleteTagsById = async (token: string, id: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/tags/all`, {
method: 'DELETE',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();

30
src/lib/apis/configs/index.ts
View file

@ -29,3 +29,33 @@ export const setDefaultModels = async (token: string, models: string) => {
return res;
};
export const setDefaultPromptSuggestions = async (token: string, promptSuggestions: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/configs/default/suggestions`, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${token}`
},
body: JSON.stringify({
suggestions: promptSuggestions
})
})
.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;
};

218
src/lib/apis/documents/index.ts Normal file
View file

@ -0,0 +1,218 @@
import { WEBUI_API_BASE_URL } from '$lib/constants';
export const createNewDoc = async (
token: string,
collection_name: string,
filename: string,
name: string,
title: string
) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/documents/create`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
authorization: `Bearer ${token}`
},
body: JSON.stringify({
collection_name: collection_name,
filename: filename,
name: name,
title: title
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
error = err.detail;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};
export const getDocs = async (token: string = '') => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/documents/`, {
method: 'GET',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
authorization: `Bearer ${token}`
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.then((json) => {
return json;
})
.catch((err) => {
error = err.detail;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};
export const getDocByName = async (token: string, name: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/documents/name/${name}`, {
method: 'GET',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
authorization: `Bearer ${token}`
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.then((json) => {
return json;
})
.catch((err) => {
error = err.detail;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};
type DocUpdateForm = {
name: string;
title: string;
};
export const updateDocByName = async (token: string, name: string, form: DocUpdateForm) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/documents/name/${name}/update`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
authorization: `Bearer ${token}`
},
body: JSON.stringify({
name: form.name,
title: form.title
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.then((json) => {
return json;
})
.catch((err) => {
error = err.detail;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};
type TagDocForm = {
name: string;
tags: string[];
};
export const tagDocByName = async (token: string, name: string, form: TagDocForm) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/documents/name/${name}/tags`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
authorization: `Bearer ${token}`
},
body: JSON.stringify({
name: form.name,
tags: form.tags
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.then((json) => {
return json;
})
.catch((err) => {
error = err.detail;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};
export const deleteDocByName = async (token: string, name: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/documents/name/${name}/delete`, {
method: 'DELETE',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
authorization: `Bearer ${token}`
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.then((json) => {
return json;
})
.catch((err) => {
error = err.detail;
console.log(err);
return null;
});
if (error) {
throw error;
}
return res;
};

333
src/lib/apis/images/index.ts Normal file
View file

@ -0,0 +1,333 @@
import { IMAGES_API_BASE_URL } from '$lib/constants';
export const getImageGenerationEnabledStatus = async (token: string = '') => {
let error = null;
const res = await fetch(`${IMAGES_API_BASE_URL}/enabled`, {
method: 'GET',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
if ('detail' in err) {
error = err.detail;
} else {
error = 'Server connection failed';
}
return null;
});
if (error) {
throw error;
}
return res;
};
export const toggleImageGenerationEnabledStatus = async (token: string = '') => {
let error = null;
const res = await fetch(`${IMAGES_API_BASE_URL}/enabled/toggle`, {
method: 'GET',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
if ('detail' in err) {
error = err.detail;
} else {
error = 'Server connection failed';
}
return null;
});
if (error) {
throw error;
}
return res;
};
export const getAUTOMATIC1111Url = async (token: string = '') => {
let error = null;
const res = await fetch(`${IMAGES_API_BASE_URL}/url`, {
method: 'GET',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
if ('detail' in err) {
error = err.detail;
} else {
error = 'Server connection failed';
}
return null;
});
if (error) {
throw error;
}
return res.AUTOMATIC1111_BASE_URL;
};
export const updateAUTOMATIC1111Url = async (token: string = '', url: string) => {
let error = null;
const res = await fetch(`${IMAGES_API_BASE_URL}/url/update`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
},
body: JSON.stringify({
url: url
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
if ('detail' in err) {
error = err.detail;
} else {
error = 'Server connection failed';
}
return null;
});
if (error) {
throw error;
}
return res.AUTOMATIC1111_BASE_URL;
};
export const getImageSize = async (token: string = '') => {
let error = null;
const res = await fetch(`${IMAGES_API_BASE_URL}/size`, {
method: 'GET',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
if ('detail' in err) {
error = err.detail;
} else {
error = 'Server connection failed';
}
return null;
});
if (error) {
throw error;
}
return res.IMAGE_SIZE;
};
export const updateImageSize = async (token: string = '', size: string) => {
let error = null;
const res = await fetch(`${IMAGES_API_BASE_URL}/size/update`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
},
body: JSON.stringify({
size: size
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
if ('detail' in err) {
error = err.detail;
} else {
error = 'Server connection failed';
}
return null;
});
if (error) {
throw error;
}
return res.IMAGE_SIZE;
};
export const getDiffusionModels = async (token: string = '') => {
let error = null;
const res = await fetch(`${IMAGES_API_BASE_URL}/models`, {
method: 'GET',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
if ('detail' in err) {
error = err.detail;
} else {
error = 'Server connection failed';
}
return null;
});
if (error) {
throw error;
}
return res;
};
export const getDefaultDiffusionModel = async (token: string = '') => {
let error = null;
const res = await fetch(`${IMAGES_API_BASE_URL}/models/default`, {
method: 'GET',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
if ('detail' in err) {
error = err.detail;
} else {
error = 'Server connection failed';
}
return null;
});
if (error) {
throw error;
}
return res.model;
};
export const updateDefaultDiffusionModel = async (token: string = '', model: string) => {
let error = null;
const res = await fetch(`${IMAGES_API_BASE_URL}/models/default/update`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
},
body: JSON.stringify({
model: model
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
if ('detail' in err) {
error = err.detail;
} else {
error = 'Server connection failed';
}
return null;
});
if (error) {
throw error;
}
return res.model;
};
export const imageGenerations = async (token: string = '', prompt: string) => {
let error = null;
const res = await fetch(`${IMAGES_API_BASE_URL}/generations`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
},
body: JSON.stringify({
prompt: prompt
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
if ('detail' in err) {
error = err.detail;
} else {
error = 'Server connection failed';
}
return null;
});
if (error) {
throw error;
}
return res;
};

26
src/lib/apis/index.ts
View file

@ -1,9 +1,31 @@
import { WEBUI_API_BASE_URL } from '$lib/constants';
import { WEBUI_BASE_URL } from '$lib/constants';
export const getBackendConfig = async () => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/`, {
const res = await fetch(`${WEBUI_BASE_URL}/api/config`, {
method: 'GET',
headers: {
'Content-Type': 'application/json'
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = err;
return null;
});
return res;
};
export const getChangelog = async () => {
let error = null;
const res = await fetch(`${WEBUI_BASE_URL}/api/changelog`, {
method: 'GET',
headers: {
'Content-Type': 'application/json'

96
src/lib/apis/ollama/index.ts
View file

@ -133,9 +133,19 @@ export const getOllamaModels = async (token: string = '') => {
});
};
export const generateTitle = async (token: string = '', model: string, prompt: string) => {
// TODO: migrate to backend
export const generateTitle = async (
token: string = '',
template: string,
model: string,
prompt: string
) => {
let error = null;
template = template.replace(/{{prompt}}/g, prompt);
console.log(template);
const res = await fetch(`${OLLAMA_API_BASE_URL}/generate`, {
method: 'POST',
headers: {
@ -144,7 +154,7 @@ export const generateTitle = async (token: string = '', model: string, prompt: s
},
body: JSON.stringify({
model: model,
prompt: `Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title': ${prompt}`,
prompt: template,
stream: false
})
})
@ -167,10 +177,50 @@ export const generateTitle = async (token: string = '', model: string, prompt: s
return res?.response ?? 'New Chat';
};
export const generatePrompt = async (token: string = '', model: string, conversation: string) => {
let error = null;
if (conversation === '') {
conversation = '[no existing conversation]';
}
const res = await fetch(`${OLLAMA_API_BASE_URL}/generate`, {
method: 'POST',
headers: {
'Content-Type': 'text/event-stream',
Authorization: `Bearer ${token}`
},
body: JSON.stringify({
model: model,
prompt: `Conversation:
${conversation}
As USER in the conversation above, your task is to continue the conversation. Remember, Your responses should be crafted as if you're a human conversing in a natural, realistic manner, keeping in mind the context and flow of the dialogue. Please generate a fitting response to the last message in the conversation, or if there is no existing conversation, initiate one as a normal person would.
Response:
`
})
}).catch((err) => {
console.log(err);
if ('detail' in err) {
error = err.detail;
}
return null;
});
if (error) {
throw error;
}
return res;
};
export const generateChatCompletion = async (token: string = '', body: object) => {
let controller = new AbortController();
let error = null;
const res = await fetch(`${OLLAMA_API_BASE_URL}/chat`, {
signal: controller.signal,
method: 'POST',
headers: {
'Content-Type': 'text/event-stream',
@ -186,6 +236,27 @@ export const generateChatCompletion = async (token: string = '', body: object) =
throw error;
}
return [res, controller];
};
export const cancelChatCompletion = async (token: string = '', requestId: string) => {
let error = null;
const res = await fetch(`${OLLAMA_API_BASE_URL}/cancel/${requestId}`, {
method: 'GET',
headers: {
'Content-Type': 'text/event-stream',
Authorization: `Bearer ${token}`
}
}).catch((err) => {
error = err;
return null;
});
if (error) {
throw error;
}
return res;
};
@ -261,13 +332,30 @@ export const pullModel = async (token: string, tagName: string) => {
name: tagName
})
}).catch((err) => {
console.log(err);
error = err;
if ('detail' in err) {
error = err.detail;
}
return null;
});
if (error) {
throw error;
}
return res;
};
// export const pullModel = async (token: string, tagName: string) => {
// return await fetch(`${OLLAMA_API_BASE_URL}/pull`, {
// method: 'POST',
// headers: {
// 'Content-Type': 'text/event-stream',
// Authorization: `Bearer ${token}`
// },
// body: JSON.stringify({
// name: tagName
// })
// });
// };

31
src/lib/apis/openai/index.ts
View file

@ -229,3 +229,34 @@ export const generateOpenAIChatCompletion = async (token: string = '', body: obj
return res;
};
export const synthesizeOpenAISpeech = async (
token: string = '',
speaker: string = 'alloy',
text: string = ''
) => {
let error = null;
const res = await fetch(`${OPENAI_API_BASE_URL}/audio/speech`, {
method: 'POST',
headers: {
Authorization: `Bearer ${token}`,
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'tts-1',
input: text,
voice: speaker
})
}).catch((err) => {
console.log(err);
error = err;
return null;
});
if (error) {
throw error;
}
return res;
};

203
src/lib/apis/rag/index.ts
View file

@ -1,5 +1,120 @@
import { RAG_API_BASE_URL } from '$lib/constants';
export const getChunkParams = async (token: string) => {
let error = null;
const res = await fetch(`${RAG_API_BASE_URL}/chunk`, {
method: 'GET',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${token}`
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = err.detail;
return null;
});
if (error) {
throw error;
}
return res;
};
export const updateChunkParams = async (token: string, size: number, overlap: number) => {
let error = null;
const res = await fetch(`${RAG_API_BASE_URL}/chunk/update`, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${token}`
},
body: JSON.stringify({
chunk_size: size,
chunk_overlap: overlap
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = err.detail;
return null;
});
if (error) {
throw error;
}
return res;
};
export const getRAGTemplate = async (token: string) => {
let error = null;
const res = await fetch(`${RAG_API_BASE_URL}/template`, {
method: 'GET',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${token}`
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = err.detail;
return null;
});
if (error) {
throw error;
}
return res?.template ?? '';
};
export const updateRAGTemplate = async (token: string, template: string) => {
let error = null;
const res = await fetch(`${RAG_API_BASE_URL}/template/update`, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${token}`
},
body: JSON.stringify({
template: template
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = err.detail;
return null;
});
if (error) {
throw error;
}
return res;
};
export const uploadDocToVectorDB = async (token: string, collection_name: string, file: File) => {
const data = new FormData();
data.append('file', file);
@ -64,30 +179,90 @@ export const uploadWebToVectorDB = async (token: string, collection_name: string
return res;
};
export const queryVectorDB = async (
export const queryDoc = async (
token: string,
collection_name: string,
query: string,
k: number
) => {
let error = null;
const searchParams = new URLSearchParams();
searchParams.set('query', query);
if (k) {
searchParams.set('k', k.toString());
const res = await fetch(`${RAG_API_BASE_URL}/query/doc`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
authorization: `Bearer ${token}`
},
body: JSON.stringify({
collection_name: collection_name,
query: query,
k: k
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
error = err.detail;
return null;
});
if (error) {
throw error;
}
const res = await fetch(
`${RAG_API_BASE_URL}/query/${collection_name}/?${searchParams.toString()}`,
{
method: 'GET',
headers: {
Accept: 'application/json',
authorization: `Bearer ${token}`
}
return res;
};
export const queryCollection = async (
token: string,
collection_names: string,
query: string,
k: number
) => {
let error = null;
const res = await fetch(`${RAG_API_BASE_URL}/query/collection`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
authorization: `Bearer ${token}`
},
body: JSON.stringify({
collection_names: collection_names,
query: query,
k: k
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
error = err.detail;
return null;
});
if (error) {
throw error;
}
return res;
};
export const scanDocs = async (token: string) => {
let error = null;
const res = await fetch(`${RAG_API_BASE_URL}/scan`, {
method: 'GET',
headers: {
Accept: 'application/json',
authorization: `Bearer ${token}`
}
)
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();

57
src/lib/apis/users/index.ts
View file

@ -1,5 +1,62 @@
import { WEBUI_API_BASE_URL } from '$lib/constants';
export const getUserPermissions = async (token: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/users/permissions/user`, {
method: 'GET',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${token}`
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = err.detail;
return null;
});
if (error) {
throw error;
}
return res;
};
export const updateUserPermissions = async (token: string, permissions: object) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/users/permissions/user`, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${token}`
},
body: JSON.stringify({
...permissions
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = err.detail;
return null;
});
if (error) {
throw error;
}
return res;
};
export const updateUserRole = async (token: string, id: string, role: string) => {
let error = null;

23
src/lib/apis/utils/index.ts Normal file
View file

@ -0,0 +1,23 @@
import { WEBUI_API_BASE_URL } from '$lib/constants';
export const getGravatarUrl = async (email: string) => {
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/utils/gravatar?email=${email}`, {
method: 'GET',
headers: {
'Content-Type': 'application/json'
}
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = err;
return null;
});
return res;
};

8
src/lib/components/AddFilesPlaceholder.svelte Normal file
View file

@ -0,0 +1,8 @@
<div class=" text-center text-6xl mb-3">📄</div>
<div class="text-center dark:text-white text-2xl font-semibold z-50">Add Files</div>
<slot
><div class=" mt-2 text-center text-sm dark:text-gray-200 w-full">
Drop any files here to add to the conversation
</div>
</slot>

115
src/lib/components/ChangelogModal.svelte Normal file
View file

@ -0,0 +1,115 @@
<script lang="ts">
import { onMount } from 'svelte';
import { Confetti } from 'svelte-confetti';
import { WEBUI_NAME, config } from '$lib/stores';
import { WEBUI_VERSION } from '$lib/constants';
import { getChangelog } from '$lib/apis';
import Modal from './common/Modal.svelte';
export let show = false;
let changelog = null;
onMount(async () => {
const res = await getChangelog();
changelog = res;
});
</script>
<Modal bind:show>
<div class="px-5 py-4 dark:text-gray-300">
<div class="flex justify-between items-start">
<div class="text-xl font-bold">
What’s New in {$WEBUI_NAME}
<Confetti x={[-1, -0.25]} y={[0, 0.5]} />
</div>
<button
class="self-center"
on:click={() => {
show = false;
}}
>
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 20 20"
fill="currentColor"
class="w-5 h-5"
>
<path
d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
/>
</svg>
</button>
</div>
<div class="flex items-center mt-1">
<div class="text-sm dark:text-gray-200">Release Notes</div>
<div class="flex self-center w-[1px] h-6 mx-2.5 bg-gray-200 dark:bg-gray-700" />
<div class="text-sm dark:text-gray-200">
v{WEBUI_VERSION}
</div>
</div>
</div>
<hr class=" dark:border-gray-800" />
<div class=" w-full p-4 px-5">
<div class=" overflow-y-scroll max-h-80">
<div class="mb-3">
{#if changelog}
{#each Object.keys(changelog) as version}
<div class=" mb-3 pr-2">
<div class="font-bold text-xl mb-1 dark:text-white">
v{version} - {changelog[version].date}
</div>
<hr class=" dark:border-gray-800 my-2" />
{#each Object.keys(changelog[version]).filter((section) => section !== 'date') as section}
<div class="">
<div
class="font-bold uppercase text-xs {section === 'added'
? 'text-white bg-blue-600'
: section === 'fixed'
? 'text-white bg-green-600'
: section === 'changed'
? 'text-white bg-yellow-600'
: section === 'removed'
? 'text-white bg-red-600'
: ''} w-fit px-3 rounded-full my-2.5"
>
{section}
</div>
<div class="my-2.5 px-1.5">
{#each Object.keys(changelog[version][section]) as item}
<div class="text-sm mb-2">
<div class="font-semibold uppercase">
{changelog[version][section][item].title}
</div>
<div class="mb-2 mt-1">{changelog[version][section][item].content}</div>
</div>
{/each}
</div>
</div>
{/each}
</div>
{/each}
{/if}
</div>
</div>
<div class="flex justify-end pt-3 text-sm font-medium">
<button
on:click={() => {
localStorage.version = $config.version;
show = false;
}}
class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
>
<span class="relative">Okay, Let's Go!</span>
</button>
</div>
</div>
</Modal>

140
src/lib/components/admin/Settings/General.svelte Normal file
View file

@ -0,0 +1,140 @@
<script lang="ts">
import {
getDefaultUserRole,
getJWTExpiresDuration,
getSignUpEnabledStatus,
toggleSignUpEnabledStatus,
updateDefaultUserRole,
updateJWTExpiresDuration
} from '$lib/apis/auths';
import { onMount } from 'svelte';
export let saveHandler: Function;
let signUpEnabled = true;
let defaultUserRole = 'pending';
let JWTExpiresIn = '';
const toggleSignUpEnabled = async () => {
signUpEnabled = await toggleSignUpEnabledStatus(localStorage.token);
};
const updateDefaultUserRoleHandler = async (role) => {
defaultUserRole = await updateDefaultUserRole(localStorage.token, role);
};
const updateJWTExpiresDurationHandler = async (duration) => {
JWTExpiresIn = await updateJWTExpiresDuration(localStorage.token, duration);
};
onMount(async () => {
signUpEnabled = await getSignUpEnabledStatus(localStorage.token);
defaultUserRole = await getDefaultUserRole(localStorage.token);
JWTExpiresIn = await getJWTExpiresDuration(localStorage.token);
});
</script>
<form
class="flex flex-col h-full justify-between space-y-3 text-sm"
on:submit|preventDefault={() => {
// console.log('submit');
updateJWTExpiresDurationHandler(JWTExpiresIn);
saveHandler();
}}
>
<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
<div>
<div class=" mb-2 text-sm font-medium">General Settings</div>
<div class=" flex w-full justify-between">
<div class=" self-center text-xs font-medium">Enable New Sign Ups</div>
<button
class="p-1 px-3 text-xs flex rounded transition"
on:click={() => {
toggleSignUpEnabled();
}}
type="button"
>
{#if signUpEnabled}
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 16 16"
fill="currentColor"
class="w-4 h-4"
>
<path
d="M11.5 1A3.5 3.5 0 0 0 8 4.5V7H2.5A1.5 1.5 0 0 0 1 8.5v5A1.5 1.5 0 0 0 2.5 15h7a1.5 1.5 0 0 0 1.5-1.5v-5A1.5 1.5 0 0 0 9.5 7V4.5a2 2 0 1 1 4 0v1.75a.75.75 0 0 0 1.5 0V4.5A3.5 3.5 0 0 0 11.5 1Z"
/>
</svg>
<span class="ml-2 self-center">Enabled</span>
{:else}
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 16 16"
fill="currentColor"
class="w-4 h-4"
>
<path
fill-rule="evenodd"
d="M8 1a3.5 3.5 0 0 0-3.5 3.5V7A1.5 1.5 0 0 0 3 8.5v5A1.5 1.5 0 0 0 4.5 15h7a1.5 1.5 0 0 0 1.5-1.5v-5A1.5 1.5 0 0 0 11.5 7V4.5A3.5 3.5 0 0 0 8 1Zm2 6V4.5a2 2 0 1 0-4 0V7h4Z"
clip-rule="evenodd"
/>
</svg>
<span class="ml-2 self-center">Disabled</span>
{/if}
</button>
</div>
<div class=" flex w-full justify-between">
<div class=" self-center text-xs font-medium">Default User Role</div>
<div class="flex items-center relative">
<select
class="w-fit pr-8 rounded py-2 px-2 text-xs bg-transparent outline-none text-right"
bind:value={defaultUserRole}
placeholder="Select a theme"
on:change={(e) => {
updateDefaultUserRoleHandler(e.target.value);
}}
>
<option value="pending">Pending</option>
<option value="user">User</option>
<option value="admin">Admin</option>
</select>
</div>
</div>
<hr class=" dark:border-gray-700 my-3" />
<div class=" w-full justify-between">
<div class="flex w-full justify-between">
<div class=" self-center text-xs font-medium">JWT Expiration</div>
</div>
<div class="flex mt-2 space-x-2">
<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="text"
placeholder={`e.g.) "30m","1h", "10d". `}
bind:value={JWTExpiresIn}
/>
</div>
<div class="mt-2 text-xs text-gray-400 dark:text-gray-500">
Valid time units: <span class=" text-gray-300 font-medium"
>'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.</span
>
</div>
</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"
type="submit"
>
Save
</button>
</div>
</form>

82
src/lib/components/admin/Settings/Users.svelte Normal file
View file

@ -0,0 +1,82 @@
<script lang="ts">
import { getSignUpEnabledStatus, toggleSignUpEnabledStatus } from '$lib/apis/auths';
import { getUserPermissions, updateUserPermissions } from '$lib/apis/users';
import { onMount } from 'svelte';
export let saveHandler: Function;
let permissions = {
chat: {
deletion: true
}
};
onMount(async () => {
permissions = await getUserPermissions(localStorage.token);
});
</script>
<form
class="flex flex-col h-full justify-between space-y-3 text-sm"
on:submit|preventDefault={async () => {
// console.log('submit');
await updateUserPermissions(localStorage.token, permissions);
saveHandler();
}}
>
<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
<div>
<div class=" mb-2 text-sm font-medium">User Permissions</div>
<div class=" flex w-full justify-between">
<div class=" self-center text-xs font-medium">Allow Chat Deletion</div>
<button
class="p-1 px-3 text-xs flex rounded transition"
on:click={() => {
permissions.chat.deletion = !permissions.chat.deletion;
}}
type="button"
>
{#if permissions.chat.deletion}
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 16 16"
fill="currentColor"
class="w-4 h-4"
>
<path
d="M11.5 1A3.5 3.5 0 0 0 8 4.5V7H2.5A1.5 1.5 0 0 0 1 8.5v5A1.5 1.5 0 0 0 2.5 15h7a1.5 1.5 0 0 0 1.5-1.5v-5A1.5 1.5 0 0 0 9.5 7V4.5a2 2 0 1 1 4 0v1.75a.75.75 0 0 0 1.5 0V4.5A3.5 3.5 0 0 0 11.5 1Z"
/>
</svg>
<span class="ml-2 self-center">Allow</span>
{:else}
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 16 16"
fill="currentColor"
class="w-4 h-4"
>
<path
fill-rule="evenodd"
d="M8 1a3.5 3.5 0 0 0-3.5 3.5V7A1.5 1.5 0 0 0 3 8.5v5A1.5 1.5 0 0 0 4.5 15h7a1.5 1.5 0 0 0 1.5-1.5v-5A1.5 1.5 0 0 0 11.5 7V4.5A3.5 3.5 0 0 0 8 1Zm2 6V4.5a2 2 0 1 0-4 0V7h4Z"
clip-rule="evenodd"
/>
</svg>
<span class="ml-2 self-center">Don't Allow</span>
{/if}
</button>
</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"
type="submit"
>
Save
</button>
</div>
</form>

107
src/lib/components/admin/SettingsModal.svelte Normal file
View file

@ -0,0 +1,107 @@
<script>
import Modal from '../common/Modal.svelte';
import General from './Settings/General.svelte';
import Users from './Settings/Users.svelte';
export let show = false;
let selectedTab = 'general';
</script>
<Modal bind:show>
<div>
<div class=" flex justify-between dark:text-gray-300 px-5 py-4">
<div class=" text-lg font-medium self-center">Admin Settings</div>
<button
class="self-center"
on:click={() => {
show = false;
}}
>
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 20 20"
fill="currentColor"
class="w-5 h-5"
>
<path
d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
/>
</svg>
</button>
</div>
<hr class=" dark:border-gray-800" />
<div class="flex flex-col md:flex-row w-full p-4 md:space-x-4">
<div
class="tabs flex flex-row overflow-x-auto space-x-1 md:space-x-0 md:space-y-1 md:flex-col flex-1 md:flex-none md:w-40 dark:text-gray-200 text-xs text-left mb-3 md:mb-0"
>
<button
class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
'general'
? 'bg-gray-200 dark:bg-gray-700'
: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
on:click={() => {
selectedTab = 'general';
}}
>
<div class=" self-center mr-2">
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 16 16"
fill="currentColor"
class="w-4 h-4"
>
<path
fill-rule="evenodd"
d="M6.955 1.45A.5.5 0 0 1 7.452 1h1.096a.5.5 0 0 1 .497.45l.17 1.699c.484.12.94.312 1.356.562l1.321-1.081a.5.5 0 0 1 .67.033l.774.775a.5.5 0 0 1 .034.67l-1.08 1.32c.25.417.44.873.561 1.357l1.699.17a.5.5 0 0 1 .45.497v1.096a.5.5 0 0 1-.45.497l-1.699.17c-.12.484-.312.94-.562 1.356l1.082 1.322a.5.5 0 0 1-.034.67l-.774.774a.5.5 0 0 1-.67.033l-1.322-1.08c-.416.25-.872.44-1.356.561l-.17 1.699a.5.5 0 0 1-.497.45H7.452a.5.5 0 0 1-.497-.45l-.17-1.699a4.973 4.973 0 0 1-1.356-.562L4.108 13.37a.5.5 0 0 1-.67-.033l-.774-.775a.5.5 0 0 1-.034-.67l1.08-1.32a4.971 4.971 0 0 1-.561-1.357l-1.699-.17A.5.5 0 0 1 1 8.548V7.452a.5.5 0 0 1 .45-.497l1.699-.17c.12-.484.312-.94.562-1.356L2.629 4.107a.5.5 0 0 1 .034-.67l.774-.774a.5.5 0 0 1 .67-.033L5.43 3.71a4.97 4.97 0 0 1 1.356-.561l.17-1.699ZM6 8c0 .538.212 1.026.558 1.385l.057.057a2 2 0 0 0 2.828-2.828l-.058-.056A2 2 0 0 0 6 8Z"
clip-rule="evenodd"
/>
</svg>
</div>
<div class=" self-center">General</div>
</button>
<button
class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
'users'
? 'bg-gray-200 dark:bg-gray-700'
: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
on:click={() => {
selectedTab = 'users';
}}
>
<div class=" self-center mr-2">
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 16 16"
fill="currentColor"
class="w-4 h-4"
>
<path
d="M8 8a2.5 2.5 0 1 0 0-5 2.5 2.5 0 0 0 0 5ZM3.156 11.763c.16-.629.44-1.21.813-1.72a2.5 2.5 0 0 0-2.725 1.377c-.136.287.102.58.418.58h1.449c.01-.077.025-.156.045-.237ZM12.847 11.763c.02.08.036.16.046.237h1.446c.316 0 .554-.293.417-.579a2.5 2.5 0 0 0-2.722-1.378c.374.51.653 1.09.813 1.72ZM14 7.5a1.5 1.5 0 1 1-3 0 1.5 1.5 0 0 1 3 0ZM3.5 9a1.5 1.5 0 1 0 0-3 1.5 1.5 0 0 0 0 3ZM5 13c-.552 0-1.013-.455-.876-.99a4.002 4.002 0 0 1 7.753 0c.136.535-.324.99-.877.99H5Z"
/>
</svg>
</div>
<div class=" self-center">Users</div>
</button>
</div>
<div class="flex-1 md:min-h-[380px]">
{#if selectedTab === 'general'}
<General
saveHandler={() => {
show = false;
}}
/>
{:else if selectedTab === 'users'}
<Users
saveHandler={() => {
show = false;
}}
/>
{/if}
</div>
</div>
</div>
</Modal>

496
src/lib/components/chat/MessageInput.svelte
View file

@ -2,11 +2,16 @@
import toast from 'svelte-french-toast';
import { onMount, tick } from 'svelte';
import { settings } from '$lib/stores';
import { calculateSHA256, findWordIndices } from '$lib/utils';
import { blobToFile, calculateSHA256, findWordIndices } from '$lib/utils';
import Prompts from './MessageInput/PromptCommands.svelte';
import Suggestions from './MessageInput/Suggestions.svelte';
import { uploadDocToVectorDB } from '$lib/apis/rag';
import { uploadDocToVectorDB, uploadWebToVectorDB } from '$lib/apis/rag';
import AddFilesPlaceholder from '../AddFilesPlaceholder.svelte';
import { SUPPORTED_FILE_TYPE, SUPPORTED_FILE_EXTENSIONS } from '$lib/constants';
import Documents from './MessageInput/Documents.svelte';
import Models from './MessageInput/Models.svelte';
import { transcribeAudio } from '$lib/apis/audio';
export let submitPrompt: Function;
export let stopResponse: Function;
@ -15,78 +20,205 @@
export let autoScroll = true;
let filesInputElement;
let promptsElement;
let documentsElement;
let modelsElement;
let inputFiles;
let dragged = false;
let user = null;
let chatInputPlaceholder = '';
export let files = [];
export let fileUploadEnabled = true;
export let speechRecognitionEnabled = true;
export let speechRecognitionListening = false;
export let prompt = '';
export let messages = [];
let speechRecognition;
$: if (prompt) {
const chatInput = document.getElementById('chat-textarea');
if (chatInput) {
chatInput.style.height = '';
chatInput.style.height = Math.min(chatInput.scrollHeight, 200) + 'px';
}
}
let mediaRecorder;
let audioChunks = [];
let isRecording = false;
const MIN_DECIBELS = -45;
const scrollToBottom = () => {
const element = document.getElementById('messages-container');
element.scrollTop = element.scrollHeight;
};
const startRecording = async () => {
const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
mediaRecorder = new MediaRecorder(stream);
mediaRecorder.onstart = () => {
isRecording = true;
console.log('Recording started');
};
mediaRecorder.ondataavailable = (event) => audioChunks.push(event.data);
mediaRecorder.onstop = async () => {
isRecording = false;
console.log('Recording stopped');
// Create a blob from the audio chunks
const audioBlob = new Blob(audioChunks, { type: 'audio/wav' });
const file = blobToFile(audioBlob, 'recording.wav');
const res = await transcribeAudio(localStorage.token, file).catch((error) => {
toast.error(error);
return null;
});
if (res) {
prompt = res.text;
await tick();
const inputElement = document.getElementById('chat-textarea');
inputElement?.focus();
if (prompt !== '' && $settings?.speechAutoSend === true) {
submitPrompt(prompt, user);
}
}
// saveRecording(audioBlob);
audioChunks = [];
};
// Start recording
mediaRecorder.start();
// Monitor silence
monitorSilence(stream);
};
const monitorSilence = (stream) => {
const audioContext = new AudioContext();
const audioStreamSource = audioContext.createMediaStreamSource(stream);
const analyser = audioContext.createAnalyser();
analyser.minDecibels = MIN_DECIBELS;
audioStreamSource.connect(analyser);
const bufferLength = analyser.frequencyBinCount;
const domainData = new Uint8Array(bufferLength);
let lastSoundTime = Date.now();
const detectSound = () => {
analyser.getByteFrequencyData(domainData);
if (domainData.some((value) => value > 0)) {
lastSoundTime = Date.now();
}
if (isRecording && Date.now() - lastSoundTime > 3000) {
mediaRecorder.stop();
audioContext.close();
return;
}
window.requestAnimationFrame(detectSound);
};
window.requestAnimationFrame(detectSound);
};
const saveRecording = (blob) => {
const url = URL.createObjectURL(blob);
const a = document.createElement('a');
document.body.appendChild(a);
a.style = 'display: none';
a.href = url;
a.download = 'recording.wav';
a.click();
window.URL.revokeObjectURL(url);
};
const speechRecognitionHandler = () => {
// Check if SpeechRecognition is supported
if (speechRecognitionListening) {
speechRecognition.stop();
if (isRecording) {
if (speechRecognition) {
speechRecognition.stop();
}
if (mediaRecorder) {
mediaRecorder.stop();
}
} else {
if ('SpeechRecognition' in window || 'webkitSpeechRecognition' in window) {
// Create a SpeechRecognition object
speechRecognition = new (window.SpeechRecognition || window.webkitSpeechRecognition)();
isRecording = true;
// Set continuous to true for continuous recognition
speechRecognition.continuous = true;
// Set the timeout for turning off the recognition after inactivity (in milliseconds)
const inactivityTimeout = 3000; // 3 seconds
let timeoutId;
// Start recognition
speechRecognition.start();
speechRecognitionListening = true;
// Event triggered when speech is recognized
speechRecognition.onresult = function (event) {
// Clear the inactivity timeout
clearTimeout(timeoutId);
// Handle recognized speech
console.log(event);
const transcript = event.results[Object.keys(event.results).length - 1][0].transcript;
prompt = `${prompt}${transcript}`;
// Restart the inactivity timeout
timeoutId = setTimeout(() => {
console.log('Speech recognition turned off due to inactivity.');
speechRecognition.stop();
}, inactivityTimeout);
};
// Event triggered when recognition is ended
speechRecognition.onend = function () {
// Restart recognition after it ends
console.log('recognition ended');
speechRecognitionListening = false;
if (prompt !== '' && $settings?.speechAutoSend === true) {
submitPrompt(prompt);
}
};
// Event triggered when an error occurs
speechRecognition.onerror = function (event) {
console.log(event);
toast.error(`Speech recognition error: ${event.error}`);
speechRecognitionListening = false;
};
if ($settings?.audio?.STTEngine ?? '' !== '') {
startRecording();
} else {
toast.error('SpeechRecognition API is not supported in this browser.');
if ('SpeechRecognition' in window || 'webkitSpeechRecognition' in window) {
// Create a SpeechRecognition object
speechRecognition = new (window.SpeechRecognition || window.webkitSpeechRecognition)();
// Set continuous to true for continuous recognition
speechRecognition.continuous = true;
// Set the timeout for turning off the recognition after inactivity (in milliseconds)
const inactivityTimeout = 3000; // 3 seconds
let timeoutId;
// Start recognition
speechRecognition.start();
// Event triggered when speech is recognized
speechRecognition.onresult = async (event) => {
// Clear the inactivity timeout
clearTimeout(timeoutId);
// Handle recognized speech
console.log(event);
const transcript = event.results[Object.keys(event.results).length - 1][0].transcript;
prompt = `${prompt}${transcript}`;
await tick();
const inputElement = document.getElementById('chat-textarea');
inputElement?.focus();
// Restart the inactivity timeout
timeoutId = setTimeout(() => {
console.log('Speech recognition turned off due to inactivity.');
speechRecognition.stop();
}, inactivityTimeout);
};
// Event triggered when recognition is ended
speechRecognition.onend = function () {
// Restart recognition after it ends
console.log('recognition ended');
isRecording = false;
if (prompt !== '' && $settings?.speechAutoSend === true) {
submitPrompt(prompt, user);
}
};
// Event triggered when an error occurs
speechRecognition.onerror = function (event) {
console.log(event);
toast.error(`Speech recognition error: ${event.error}`);
isRecording = false;
};
} else {
toast.error('SpeechRecognition API is not supported in this browser.');
}
}
}
};
@ -102,25 +234,77 @@
error: ''
};
files = [...files, doc];
const res = await uploadDocToVectorDB(localStorage.token, '', file);
try {
files = [...files, doc];
if (res) {
doc.upload_status = true;
doc.collection_name = res.collection_name;
files = files;
if (['audio/mpeg', 'audio/wav'].includes(file['type'])) {
const res = await transcribeAudio(localStorage.token, file).catch((error) => {
toast.error(error);
return null;
});
if (res) {
console.log(res);
const blob = new Blob([res.text], { type: 'text/plain' });
file = blobToFile(blob, `${file.name}.txt`);
}
}
const res = await uploadDocToVectorDB(localStorage.token, '', file);
if (res) {
doc.upload_status = true;
doc.collection_name = res.collection_name;
files = files;
}
} catch (e) {
// Remove the failed doc from the files array
files = files.filter((f) => f.name !== file.name);
toast.error(e);
}
};
const uploadWeb = async (url) => {
console.log(url);
const doc = {
type: 'doc',
name: url,
collection_name: '',
upload_status: false,
url: url,
error: ''
};
try {
files = [...files, doc];
const res = await uploadWebToVectorDB(localStorage.token, '', url);
if (res) {
doc.upload_status = true;
doc.collection_name = res.collection_name;
files = files;
}
} catch (e) {
// Remove the failed doc from the files array
files = files.filter((f) => f.name !== url);
toast.error(e);
}
};
onMount(() => {
const dropZone = document.querySelector('body');
dropZone?.addEventListener('dragover', (e) => {
const onDragOver = (e) => {
e.preventDefault();
dragged = true;
});
};
dropZone.addEventListener('drop', async (e) => {
const onDragLeave = () => {
dragged = false;
};
const onDrop = async (e) => {
e.preventDefault();
console.log(e);
@ -141,19 +325,19 @@
if (inputFiles && inputFiles.length > 0) {
const file = inputFiles[0];
console.log(file, file.name.split('.').at(-1));
if (['image/gif', 'image/jpeg', 'image/png'].includes(file['type'])) {
reader.readAsDataURL(file);
} else if (
[
'application/pdf',
'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
'text/plain',
'text/csv'
].includes(file['type'])
SUPPORTED_FILE_TYPE.includes(file['type']) ||
SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))
) {
uploadDoc(file);
} else {
toast.error(`Unsupported File Type '${file['type']}'.`);
toast.error(
`Unknown File Type '${file['type']}', but accepting and treating as plain text`
);
uploadDoc(file);
}
} else {
toast.error(`File not found.`);
@ -161,11 +345,17 @@
}
dragged = false;
});
};
dropZone?.addEventListener('dragleave', () => {
dragged = false;
});
dropZone?.addEventListener('dragover', onDragOver);
dropZone?.addEventListener('drop', onDrop);
dropZone?.addEventListener('dragleave', onDragLeave);
return () => {
dropZone?.removeEventListener('dragover', onDragOver);
dropZone?.removeEventListener('drop', onDrop);
dropZone?.removeEventListener('dragleave', onDragLeave);
};
});
</script>
@ -179,29 +369,24 @@
<div class="absolute rounded-xl w-full h-full backdrop-blur bg-gray-800/40 flex justify-center">
<div class="m-auto pt-64 flex flex-col justify-center">
<div class="max-w-md">
<div class=" text-center text-6xl mb-3">🗂️</div>
<div class="text-center dark:text-white text-2xl font-semibold z-50">Add Files</div>
<div class=" mt-2 text-center text-sm dark:text-gray-200 w-full">
Drop any files/images here to add to the conversation
</div>
<AddFilesPlaceholder />
</div>
</div>
</div>
</div>
{/if}
<div class="fixed bottom-0 w-full">
<div class="px-2.5 pt-2.5 -mb-0.5 mx-auto inset-x-0 bg-transparent flex justify-center">
<div class="w-full">
<div class="px-2.5 -mb-0.5 mx-auto inset-x-0 bg-transparent flex justify-center">
<div class="flex flex-col max-w-3xl w-full">
<div>
<div class="relative">
{#if autoScroll === false && messages.length > 0}
<div class=" flex justify-center mb-4">
<div class=" absolute -top-12 left-0 right-0 flex justify-center">
<button
class=" bg-white border border-gray-100 dark:border-none dark:bg-white/20 p-1.5 rounded-full"
on:click={() => {
autoScroll = true;
window.scrollTo({ top: document.body.scrollHeight, behavior: 'smooth' });
scrollToBottom();
}}
>
<svg
@ -221,18 +406,48 @@
{/if}
</div>
<div class="w-full">
<div class="w-full relative">
{#if prompt.charAt(0) === '/'}
<Prompts bind:this={promptsElement} bind:prompt />
{:else if messages.length == 0 && suggestionPrompts.length !== 0}
{:else if prompt.charAt(0) === '#'}
<Documents
bind:this={documentsElement}
bind:prompt
on:url={(e) => {
console.log(e);
uploadWeb(e.detail);
}}
on:select={(e) => {
console.log(e);
files = [
...files,
{
type: e?.detail?.type ?? 'doc',
...e.detail,
upload_status: true
}
];
}}
/>
{:else if prompt.charAt(0) === '@'}
<Models
bind:this={modelsElement}
bind:prompt
bind:user
bind:chatInputPlaceholder
{messages}
/>
{/if}
{#if messages.length == 0 && suggestionPrompts.length !== 0}
<Suggestions {suggestionPrompts} {submitPrompt} />
{/if}
</div>
</div>
</div>
<div class="bg-white dark:bg-gray-800">
<div class="max-w-3xl px-2.5 -mb-0.5 mx-auto inset-x-0">
<div class="bg-gradient-to-t from-white dark:from-gray-800 from-40% pb-2">
<div class="bg-white dark:bg-gray-900">
<div class="max-w-3xl px-2.5 mx-auto inset-x-0">
<div class=" pb-2">
<input
bind:this={filesInputElement}
bind:files={inputFiles}
@ -257,18 +472,17 @@
if (['image/gif', 'image/jpeg', 'image/png'].includes(file['type'])) {
reader.readAsDataURL(file);
} else if (
[
'application/pdf',
'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
'text/plain',
'text/csv'
].includes(file['type'])
SUPPORTED_FILE_TYPE.includes(file['type']) ||
SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))
) {
uploadDoc(file);
filesInputElement.value = '';
} else {
toast.error(`Unsupported File Type '${file['type']}'.`);
inputFiles = null;
toast.error(
`Unknown File Type '${file['type']}', but accepting and treating as plain text`
);
uploadDoc(file);
filesInputElement.value = '';
}
} else {
toast.error(`File not found.`);
@ -276,9 +490,9 @@
}}
/>
<form
class=" flex flex-col relative w-full rounded-xl border dark:border-gray-600 bg-white dark:bg-gray-800 dark:text-gray-100"
class=" flex flex-col relative w-full rounded-xl border dark:border-gray-700 bg-white dark:bg-gray-900 dark:text-gray-100"
on:submit|preventDefault={() => {
submitPrompt(prompt);
submitPrompt(prompt, user);
}}
>
{#if files.length > 0}
@ -361,6 +575,34 @@
<div class=" text-gray-500 text-sm">Document</div>
</div>
</div>
{:else if file.type === 'collection'}
<div
class="h-16 w-[15rem] flex items-center space-x-3 px-2.5 dark:bg-gray-600 rounded-xl border border-gray-200 dark:border-none"
>
<div class="p-2.5 bg-red-400 text-white rounded-lg">
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 24 24"
fill="currentColor"
class="w-6 h-6"
>
<path
d="M7.5 3.375c0-1.036.84-1.875 1.875-1.875h.375a3.75 3.75 0 0 1 3.75 3.75v1.875C13.5 8.161 14.34 9 15.375 9h1.875A3.75 3.75 0 0 1 21 12.75v3.375C21 17.16 20.16 18 19.125 18h-9.75A1.875 1.875 0 0 1 7.5 16.125V3.375Z"
/>
<path
d="M15 5.25a5.23 5.23 0 0 0-1.279-3.434 9.768 9.768 0 0 1 6.963 6.963A5.23 5.23 0 0 0 17.25 7.5h-1.875A.375.375 0 0 1 15 7.125V5.25ZM4.875 6H6v10.125A3.375 3.375 0 0 0 9.375 19.5H16.5v1.125c0 1.035-.84 1.875-1.875 1.875h-9.75A1.875 1.875 0 0 1 3 20.625V7.875C3 6.839 3.84 6 4.875 6Z"
/>
</svg>
</div>
<div class="flex flex-col justify-center -space-y-0.5">
<div class=" dark:text-gray-100 text-sm font-medium line-clamp-1">
{file?.title ?? `#${file.name}`}
</div>
<div class=" text-gray-500 text-sm">Collection</div>
</div>
</div>
{/if}
<div class=" absolute -top-1 -right-1">
@ -417,20 +659,38 @@
<textarea
id="chat-textarea"
class=" dark:bg-gray-800 dark:text-gray-100 outline-none w-full py-3 px-2 {fileUploadEnabled
class=" dark:bg-gray-900 dark:text-gray-100 outline-none w-full py-3 px-2 {fileUploadEnabled
? ''
: ' pl-4'} rounded-xl resize-none h-[48px]"
placeholder={speechRecognitionListening ? 'Listening...' : 'Send a message'}
placeholder={chatInputPlaceholder !== ''
? chatInputPlaceholder
: isRecording
? 'Listening...'
: 'Send a message'}
bind:value={prompt}
on:keypress={(e) => {
if (e.keyCode == 13 && !e.shiftKey) {
e.preventDefault();
}
if (prompt !== '' && e.keyCode == 13 && !e.shiftKey) {
submitPrompt(prompt);
submitPrompt(prompt, user);
}
}}
on:keydown={async (e) => {
const isCtrlPressed = e.ctrlKey || e.metaKey; // metaKey is for Cmd key on Mac
// Check if Ctrl + R is pressed
if (prompt === '' && isCtrlPressed && e.key.toLowerCase() === 'r') {
e.preventDefault();
console.log('regenerate');
const regenerateButton = [
...document.getElementsByClassName('regenerate-response-button')
]?.at(-1);
regenerateButton?.click();
}
if (prompt === '' && e.key == 'ArrowUp') {
e.preventDefault();
@ -448,8 +708,10 @@
editButton?.click();
}
if (prompt.charAt(0) === '/' && e.key === 'ArrowUp') {
promptsElement.selectUp();
if (['/', '#', '@'].includes(prompt.charAt(0)) && e.key === 'ArrowUp') {
e.preventDefault();
(promptsElement || documentsElement || modelsElement).selectUp();
const commandOptionButton = [
...document.getElementsByClassName('selected-command-option-button')
@ -457,8 +719,10 @@
commandOptionButton.scrollIntoView({ block: 'center' });
}
if (prompt.charAt(0) === '/' && e.key === 'ArrowDown') {
promptsElement.selectDown();
if (['/', '#', '@'].includes(prompt.charAt(0)) && e.key === 'ArrowDown') {
e.preventDefault();
(promptsElement || documentsElement || modelsElement).selectDown();
const commandOptionButton = [
...document.getElementsByClassName('selected-command-option-button')
@ -466,7 +730,7 @@
commandOptionButton.scrollIntoView({ block: 'center' });
}
if (prompt.charAt(0) === '/' && e.key === 'Enter') {
if (['/', '#', '@'].includes(prompt.charAt(0)) && e.key === 'Enter') {
e.preventDefault();
const commandOptionButton = [
@ -476,7 +740,7 @@
commandOptionButton?.click();
}
if (prompt.charAt(0) === '/' && e.key === 'Tab') {
if (['/', '#', '@'].includes(prompt.charAt(0)) && e.key === 'Tab') {
e.preventDefault();
const commandOptionButton = [
@ -507,6 +771,11 @@
on:input={(e) => {
e.target.style.height = '';
e.target.style.height = Math.min(e.target.scrollHeight, 200) + 'px';
user = null;
}}
on:focus={(e) => {
e.target.style.height = '';
e.target.style.height = Math.min(e.target.scrollHeight, 200) + 'px';
}}
on:paste={(e) => {
const clipboardData = e.clipboardData || window.clipboardData;
@ -538,13 +807,14 @@
{#if messages.length == 0 || messages.at(-1).done == true}
{#if speechRecognitionEnabled}
<button
id="voice-input-button"
class=" text-gray-600 dark:text-gray-300 transition rounded-lg p-1.5 mr-0.5 self-center"
type="button"
on:click={() => {
speechRecognitionHandler();
}}
>
{#if speechRecognitionListening}
{#if isRecording}
<svg
class=" w-5 h-5 translate-y-[0.5px]"
fill="currentColor"
@ -599,19 +869,19 @@
<button
class="{prompt !== ''
? 'bg-black text-white hover:bg-gray-900 dark:bg-white dark:text-black dark:hover:bg-gray-100 '
: 'text-white bg-gray-100 dark:text-gray-800 dark:bg-gray-600 disabled'} transition rounded-lg p-1 mr-0.5 w-7 h-7 self-center"
: 'text-white bg-gray-100 dark:text-gray-900 dark:bg-gray-800 disabled'} transition rounded-lg p-1 mr-0.5 w-7 h-7 self-center"
type="submit"
disabled={prompt === ''}
>
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 20 20"
viewBox="0 0 16 16"
fill="currentColor"
class="w-5 h-5"
class="w-4.5 h-4.5 mx-auto"
>
<path
fill-rule="evenodd"
d="M10 17a.75.75 0 01-.75-.75V5.612L5.29 9.77a.75.75 0 01-1.08-1.04l5.25-5.5a.75.75 0 011.08 0l5.25 5.5a.75.75 0 11-1.08 1.04l-3.96-4.158V16.25A.75.75 0 0110 17z"
d="M8 14a.75.75 0 0 1-.75-.75V4.56L4.03 7.78a.75.75 0 0 1-1.06-1.06l4.5-4.5a.75.75 0 0 1 1.06 0l4.5 4.5a.75.75 0 0 1-1.06 1.06L8.75 4.56v8.69A.75.75 0 0 1 8 14Z"
clip-rule="evenodd"
/>
</svg>

159
src/lib/components/chat/MessageInput/Documents.svelte Normal file
View file

@ -0,0 +1,159 @@
<script lang="ts">
import { createEventDispatcher } from 'svelte';
import { documents } from '$lib/stores';
import { removeFirstHashWord, isValidHttpUrl } from '$lib/utils';
import { tick } from 'svelte';
import toast from 'svelte-french-toast';
export let prompt = '';
const dispatch = createEventDispatcher();
let selectedIdx = 0;
let filteredItems = [];
let filteredDocs = [];
let collections = [];
$: collections = [
...($documents.length > 0
? [
{
name: 'All Documents',
type: 'collection',
title: 'All Documents',
collection_names: $documents.map((doc) => doc.collection_name)
}
]
: []),
...$documents
.reduce((a, e, i, arr) => {
return [...new Set([...a, ...(e?.content?.tags ?? []).map((tag) => tag.name)])];
}, [])
.map((tag) => ({
name: tag,
type: 'collection',
collection_names: $documents
.filter((doc) => (doc?.content?.tags ?? []).map((tag) => tag.name).includes(tag))
.map((doc) => doc.collection_name)
}))
];
$: filteredCollections = collections
.filter((collection) => collection.name.includes(prompt.split(' ')?.at(0)?.substring(1) ?? ''))
.sort((a, b) => a.name.localeCompare(b.name));
$: filteredDocs = $documents
.filter((doc) => doc.name.includes(prompt.split(' ')?.at(0)?.substring(1) ?? ''))
.sort((a, b) => a.title.localeCompare(b.title));
$: filteredItems = [...filteredCollections, ...filteredDocs];
$: if (prompt) {
selectedIdx = 0;
console.log(filteredCollections);
}
export const selectUp = () => {
selectedIdx = Math.max(0, selectedIdx - 1);
};
export const selectDown = () => {
selectedIdx = Math.min(selectedIdx + 1, filteredItems.length - 1);
};
const confirmSelect = async (doc) => {
dispatch('select', doc);
prompt = removeFirstHashWord(prompt);
const chatInputElement = document.getElementById('chat-textarea');
await tick();
chatInputElement?.focus();
await tick();
};
const confirmSelectWeb = async (url) => {
dispatch('url', url);
prompt = removeFirstHashWord(prompt);
const chatInputElement = document.getElementById('chat-textarea');
await tick();
chatInputElement?.focus();
await tick();
};
</script>
{#if filteredItems.length > 0 || prompt.split(' ')?.at(0)?.substring(1).startsWith('http')}
<div class="md:px-2 mb-3 text-left w-full absolute bottom-0 left-0 right-0">
<div class="flex w-full rounded-lg border border-gray-100 dark:border-gray-700">
<div class=" bg-gray-100 dark:bg-gray-700 w-10 rounded-l-lg text-center">
<div class=" text-lg font-semibold mt-2">#</div>
</div>
<div class="max-h-60 flex flex-col w-full rounded-r-lg">
<div class=" overflow-y-auto bg-white p-2 rounded-tr-lg space-y-0.5">
{#each filteredItems as doc, docIdx}
<button
class=" px-3 py-1.5 rounded-lg w-full text-left {docIdx === selectedIdx
? ' bg-gray-100 selected-command-option-button'
: ''}"
type="button"
on:click={() => {
console.log(doc);
confirmSelect(doc);
}}
on:mousemove={() => {
selectedIdx = docIdx;
}}
on:focus={() => {}}
>
{#if doc.type === 'collection'}
<div class=" font-medium text-black line-clamp-1">
{doc?.title ?? `#${doc.name}`}
</div>
<div class=" text-xs text-gray-600 line-clamp-1">Collection</div>
{:else}
<div class=" font-medium text-black line-clamp-1">
#{doc.name} ({doc.filename})
</div>
<div class=" text-xs text-gray-600 line-clamp-1">
{doc.title}
</div>
{/if}
</button>
{/each}
{#if prompt.split(' ')?.at(0)?.substring(1).startsWith('http')}
<button
class="px-3 py-1.5 rounded-lg w-full text-left bg-gray-100 selected-command-option-button"
type="button"
on:click={() => {
const url = prompt.split(' ')?.at(0)?.substring(1);
if (isValidHttpUrl(url)) {
confirmSelectWeb(url);
} else {
toast.error(
'Oops! Looks like the URL is invalid. Please double-check and try again.'
);
}
}}
>
<div class=" font-medium text-black line-clamp-1">
{prompt.split(' ')?.at(0)?.substring(1)}
</div>
<div class=" text-xs text-gray-600 line-clamp-1">Web</div>
</button>
{/if}
</div>
</div>
</div>
</div>
{/if}

158
src/lib/components/chat/MessageInput/Models.svelte Normal file
View file

@ -0,0 +1,158 @@
<script lang="ts">
import { generatePrompt } from '$lib/apis/ollama';
import { models } from '$lib/stores';
import { splitStream } from '$lib/utils';
import { tick } from 'svelte';
import toast from 'svelte-french-toast';
export let prompt = '';
export let user = null;
export let chatInputPlaceholder = '';
export let messages = [];
let selectedIdx = 0;
let filteredModels = [];
$: filteredModels = $models
.filter(
(p) =>
p.name !== 'hr' &&
!p.external &&
p.name.includes(prompt.split(' ')?.at(0)?.substring(1) ?? '')
)
.sort((a, b) => a.name.localeCompare(b.name));
$: if (prompt) {
selectedIdx = 0;
}
export const selectUp = () => {
selectedIdx = Math.max(0, selectedIdx - 1);
};
export const selectDown = () => {
selectedIdx = Math.min(selectedIdx + 1, filteredModels.length - 1);
};
const confirmSelect = async (model) => {
// dispatch('select', model);
prompt = '';
user = JSON.parse(JSON.stringify(model.name));
await tick();
chatInputPlaceholder = `'${model.name}' is thinking...`;
const chatInputElement = document.getElementById('chat-textarea');
await tick();
chatInputElement?.focus();
await tick();
const convoText = messages.reduce((a, message, i, arr) => {
return `${a}### ${message.role.toUpperCase()}\n${message.content}\n\n`;
}, '');
const res = await generatePrompt(localStorage.token, model.name, convoText);
if (res && res.ok) {
const reader = res.body
.pipeThrough(new TextDecoderStream())
.pipeThrough(splitStream('\n'))
.getReader();
while (true) {
const { value, done } = await reader.read();
if (done) {
break;
}
try {
let lines = value.split('\n');
for (const line of lines) {
if (line !== '') {
console.log(line);
let data = JSON.parse(line);
if ('detail' in data) {
throw data;
}
if (data.done == false) {
if (prompt == '' && data.response == '\n') {
continue;
} else {
prompt += data.response;
console.log(data.response);
chatInputElement.scrollTop = chatInputElement.scrollHeight;
await tick();
}
}
}
}
} catch (error) {
console.log(error);
if ('detail' in error) {
toast.error(error.detail);
}
break;
}
}
} else {
if (res !== null) {
const error = await res.json();
console.log(error);
if ('detail' in error) {
toast.error(error.detail);
} else {
toast.error(error.error);
}
} else {
toast.error(`Uh-oh! There was an issue connecting to Ollama.`);
}
}
chatInputPlaceholder = '';
console.log(user);
};
</script>
{#if filteredModels.length > 0}
<div class="md:px-2 mb-3 text-left w-full absolute bottom-0 left-0 right-0">
<div class="flex w-full rounded-lg border border-gray-100 dark:border-gray-700">
<div class=" bg-gray-100 dark:bg-gray-700 w-10 rounded-l-lg text-center">
<div class=" text-lg font-semibold mt-2">@</div>
</div>
<div class="max-h-60 flex flex-col w-full rounded-r-lg">
<div class=" overflow-y-auto bg-white p-2 rounded-tr-lg space-y-0.5">
{#each filteredModels as model, modelIdx}
<button
class=" px-3 py-1.5 rounded-lg w-full text-left {modelIdx === selectedIdx
? ' bg-gray-100 selected-command-option-button'
: ''}"
type="button"
on:click={() => {
confirmSelect(model);
}}
on:mousemove={() => {
selectedIdx = modelIdx;
}}
on:focus={() => {}}
>
<div class=" font-medium text-black line-clamp-1">
{model.name}
</div>
<!-- <div class=" text-xs text-gray-600 line-clamp-1">
{doc.title}
</div> -->
</button>
{/each}
</div>
</div>
</div>
</div>
{/if}

16
src/lib/components/chat/MessageInput/PromptCommands.svelte
View file

@ -2,6 +2,7 @@
import { prompts } from '$lib/stores';
import { findWordIndices } from '$lib/utils';
import { tick } from 'svelte';
import toast from 'svelte-french-toast';
export let prompt = '';
let selectedCommandIdx = 0;
@ -24,7 +25,18 @@
};
const confirmCommand = async (command) => {
prompt = command.content;
let text = command.content;
if (command.content.includes('{{CLIPBOARD}}')) {
const clipboardText = await navigator.clipboard.readText().catch((err) => {
toast.error('Failed to read clipboard contents');
return '{{CLIPBOARD}}';
});
text = command.content.replaceAll('{{CLIPBOARD}}', clipboardText);
}
prompt = text;
const chatInputElement = document.getElementById('chat-textarea');
@ -47,7 +59,7 @@
</script>
{#if filteredPromptCommands.length > 0}
<div class="md:px-2 mb-3 text-left w-full">
<div class="md:px-2 mb-3 text-left w-full absolute bottom-0 left-0 right-0">
<div class="flex w-full rounded-lg border border-gray-100 dark:border-gray-700">
<div class=" bg-gray-100 dark:bg-gray-700 w-10 rounded-l-lg text-center">
<div class=" text-lg font-semibold mt-2">/</div>

25
src/lib/components/chat/MessageInput/Suggestions.svelte
View file

@ -1,21 +1,30 @@
<script lang="ts">
export let submitPrompt: Function;
export let suggestionPrompts = [];
let prompts = [];
$: prompts =
suggestionPrompts.length <= 4
? suggestionPrompts
: suggestionPrompts.sort(() => Math.random() - 0.5).slice(0, 4);
</script>
<div class=" flex flex-wrap-reverse mb-3 md:p-1 text-left w-full">
{#each suggestionPrompts as prompt, promptIdx}
<div class="{promptIdx > 1 ? 'hidden sm:inline-flex' : ''} basis-full sm:basis-1/2 p-[5px]">
{#each prompts as prompt, promptIdx}
<div
class="{promptIdx > 1 ? 'hidden sm:inline-flex' : ''} basis-full sm:basis-1/2 p-[5px] px-2"
>
<button
class=" flex-1 flex justify-between w-full h-full px-4 py-2.5 bg-white hover:bg-gray-50 dark:bg-gray-800 dark:hover:bg-gray-700 outline outline-1 outline-gray-200 dark:outline-gray-600 rounded-lg transition group"
class=" flex-1 flex justify-between w-full h-full px-4 py-2.5 bg-white hover:bg-gray-50 dark:bg-gray-900 dark:hover:bg-gray-700 outline outline-1 outline-gray-200 dark:outline-gray-800 rounded-lg transition group"
on:click={() => {
submitPrompt(prompt.content);
}}
>
<div class="flex flex-col text-left self-center">
{#if prompt.title}
{#if prompt.title && prompt.title[0] !== ''}
<div class="text-sm font-medium dark:text-gray-300">{prompt.title[0]}</div>
<div class="text-sm text-gray-500">{prompt.title[1]}</div>
<div class="text-sm text-gray-500 line-clamp-1">{prompt.title[1]}</div>
{:else}
<div class=" self-center text-sm font-medium dark:text-gray-300 line-clamp-2">
{prompt.content}
@ -24,17 +33,17 @@
</div>
<div
class="self-center p-1 rounded-lg text-white group-hover:bg-gray-100 group-hover:text-gray-800 dark:group-hover:bg-gray-800 dark:group-hover:text-gray-300 dark:text-gray-800 transition"
class="self-center p-1 rounded-lg text-white group-hover:bg-gray-100 group-hover:text-gray-800 dark:group-hover:bg-gray-800 dark:group-hover:text-gray-100 dark:text-gray-900 transition"
>
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 20 20"
viewBox="0 0 16 16"
fill="currentColor"
class="w-4 h-4"
>
<path
fill-rule="evenodd"
d="M10 17a.75.75 0 01-.75-.75V5.612L5.29 9.77a.75.75 0 01-1.08-1.04l5.25-5.5a.75.75 0 011.08 0l5.25 5.5a.75.75 0 11-1.08 1.04l-3.96-4.158V16.25A.75.75 0 0110 17z"
d="M8 14a.75.75 0 0 1-.75-.75V4.56L4.03 7.78a.75.75 0 0 1-1.06-1.06l4.5-4.5a.75.75 0 0 1 1.06 0l4.5 4.5a.75.75 0 0 1-1.06 1.06L8.75 4.56v8.69A.75.75 0 0 1 8 14Z"
clip-rule="evenodd"
/>
</svg>

237
src/lib/components/chat/Messages.svelte
View file

@ -11,9 +11,11 @@
import ResponseMessage from './Messages/ResponseMessage.svelte';
import Placeholder from './Messages/Placeholder.svelte';
import Spinner from '../common/Spinner.svelte';
import { imageGenerations } from '$lib/apis/images';
export let chatId = '';
export let sendPrompt: Function;
export let continueGeneration: Function;
export let regenerateResponse: Function;
export let processing = '';
@ -28,10 +30,15 @@
$: if (autoScroll && bottomPadding) {
(async () => {
await tick();
window.scrollTo({ top: document.body.scrollHeight, behavior: 'smooth' });
scrollToBottom();
})();
}
const scrollToBottom = () => {
const element = document.getElementById('messages-container');
element.scrollTop = element.scrollHeight;
};
const copyToClipboard = (text) => {
if (!navigator.clipboard) {
var textArea = document.createElement('textarea');
@ -159,10 +166,11 @@
await tick();
autoScroll = window.innerHeight + window.scrollY >= document.body.offsetHeight - 40;
const element = document.getElementById('messages-container');
autoScroll = element.scrollHeight - element.scrollTop <= element.clientHeight + 50;
setTimeout(() => {
window.scrollTo({ top: document.body.scrollHeight, behavior: 'smooth' });
scrollToBottom();
}, 100);
};
@ -207,100 +215,151 @@
await tick();
autoScroll = window.innerHeight + window.scrollY >= document.body.offsetHeight - 40;
const element = document.getElementById('messages-container');
autoScroll = element.scrollHeight - element.scrollTop <= element.clientHeight + 50;
setTimeout(() => {
window.scrollTo({ top: document.body.scrollHeight, behavior: 'smooth' });
scrollToBottom();
}, 100);
};
// TODO: change delete behaviour
// const deleteMessageAndDescendants = async (messageId: string) => {
// if (history.messages[messageId]) {
// history.messages[messageId].deleted = true;
// for (const childId of history.messages[messageId].childrenIds) {
// await deleteMessageAndDescendants(childId);
// }
// }
// };
// const triggerDeleteMessageRecursive = async (messageId: string) => {
// await deleteMessageAndDescendants(messageId);
// await updateChatById(localStorage.token, chatId, { history });
// await chats.set(await getChatList(localStorage.token));
// };
const messageDeleteHandler = async (messageId) => {
if (history.messages[messageId]) {
history.messages[messageId].deleted = true;
for (const childId of history.messages[messageId].childrenIds) {
history.messages[childId].deleted = true;
}
}
await updateChatById(localStorage.token, chatId, { history });
};
</script>
{#if messages.length == 0}
<Placeholder models={selectedModels} modelfiles={selectedModelfiles} />
{:else}
{#key chatId}
{#each messages as message, messageIdx}
<div class=" w-full">
<div class="flex flex-col justify-between px-5 mb-3 max-w-3xl mx-auto rounded-lg group">
{#if message.role === 'user'}
<UserMessage
user={$user}
{message}
siblings={message.parentId !== null
? history.messages[message.parentId]?.childrenIds ?? []
: Object.values(history.messages)
.filter((message) => message.parentId === null)
.map((message) => message.id) ?? []}
{confirmEditMessage}
{showPreviousMessage}
{showNextMessage}
{copyToClipboard}
/>
<div class=" pb-10">
{#key chatId}
{#each messages as message, messageIdx}
{#if !message.deleted}
<div class=" w-full">
<div
class="flex flex-col justify-between px-5 mb-3 {$settings?.fullScreenMode ?? null
? 'max-w-full'
: 'max-w-3xl'} mx-auto rounded-lg group"
>
{#if message.role === 'user'}
<UserMessage
on:delete={() => messageDeleteHandler(message.id)}
user={$user}
{message}
isFirstMessage={messageIdx === 0}
siblings={message.parentId !== null
? history.messages[message.parentId]?.childrenIds ?? []
: Object.values(history.messages)
.filter((message) => message.parentId === null)
.map((message) => message.id) ?? []}
{confirmEditMessage}
{showPreviousMessage}
{showNextMessage}
{copyToClipboard}
/>
{#if messages.length - 1 === messageIdx && processing !== ''}
<div class="flex my-2.5 ml-12 items-center w-fit space-x-2.5">
<div class=" dark:text-blue-100">
<svg
class=" w-4 h-4 translate-y-[0.5px]"
fill="currentColor"
viewBox="0 0 24 24"
xmlns="http://www.w3.org/2000/svg"
><style>
.spinner_qM83 {
animation: spinner_8HQG 1.05s infinite;
}
.spinner_oXPr {
animation-delay: 0.1s;
}
.spinner_ZTLf {
animation-delay: 0.2s;
}
@keyframes spinner_8HQG {
0%,
57.14% {
animation-timing-function: cubic-bezier(0.33, 0.66, 0.66, 1);
transform: translate(0);
}
28.57% {
animation-timing-function: cubic-bezier(0.33, 0, 0.66, 0.33);
transform: translateY(-6px);
}
100% {
transform: translate(0);
}
}
</style><circle class="spinner_qM83" cx="4" cy="12" r="2.5" /><circle
class="spinner_qM83 spinner_oXPr"
cx="12"
cy="12"
r="2.5"
/><circle class="spinner_qM83 spinner_ZTLf" cx="20" cy="12" r="2.5" /></svg
>
</div>
<div class=" text-sm font-medium">
{processing}
</div>
</div>
{/if}
{:else}
<ResponseMessage
{message}
modelfiles={selectedModelfiles}
siblings={history.messages[message.parentId]?.childrenIds ?? []}
isLastMessage={messageIdx + 1 === messages.length}
{confirmEditResponseMessage}
{showPreviousMessage}
{showNextMessage}
{rateMessage}
{copyToClipboard}
{regenerateResponse}
/>
{/if}
</div>
</div>
{/each}
{#if messages.length - 1 === messageIdx && processing !== ''}
<div class="flex my-2.5 ml-12 items-center w-fit space-x-2.5">
<div class=" dark:text-blue-100">
<svg
class=" w-4 h-4 translate-y-[0.5px]"
fill="currentColor"
viewBox="0 0 24 24"
xmlns="http://www.w3.org/2000/svg"
><style>
.spinner_qM83 {
animation: spinner_8HQG 1.05s infinite;
}
.spinner_oXPr {
animation-delay: 0.1s;
}
.spinner_ZTLf {
animation-delay: 0.2s;
}
@keyframes spinner_8HQG {
0%,
57.14% {
animation-timing-function: cubic-bezier(0.33, 0.66, 0.66, 1);
transform: translate(0);
}
28.57% {
animation-timing-function: cubic-bezier(0.33, 0, 0.66, 0.33);
transform: translateY(-6px);
}
100% {
transform: translate(0);
}
}
</style><circle class="spinner_qM83" cx="4" cy="12" r="2.5" /><circle
class="spinner_qM83 spinner_oXPr"
cx="12"
cy="12"
r="2.5"
/><circle class="spinner_qM83 spinner_ZTLf" cx="20" cy="12" r="2.5" /></svg
>
</div>
<div class=" text-sm font-medium">
{processing}
</div>
</div>
{/if}
{:else}
<ResponseMessage
{message}
modelfiles={selectedModelfiles}
siblings={history.messages[message.parentId]?.childrenIds ?? []}
isLastMessage={messageIdx + 1 === messages.length}
{confirmEditResponseMessage}
{showPreviousMessage}
{showNextMessage}
{rateMessage}
{copyToClipboard}
{continueGeneration}
{regenerateResponse}
on:save={async (e) => {
console.log('save', e);
{#if bottomPadding}
<div class=" mb-10" />
{/if}
{/key}
const message = e.detail;
history.messages[message.id] = message;
await updateChatById(localStorage.token, chatId, {
messages: messages,
history: history
});
}}
/>
{/if}
</div>
</div>
{/if}
{/each}
{#if bottomPadding}
<div class=" mb-10" />
{/if}
{/key}
</div>
{/if}

Some files were not shown because too many files have changed in this diff Show more