Merge pull request #897 from open-webui/main

dev

.dockerignore

+.github
 .DS_Store
+docs
+kubernetes
 node_modules
 /.svelte-kit
 /package

example.env → .env.example

@@ -3,4 +3,10 @@
 OLLAMA_API_BASE_URL='http://localhost:11434/api'
 
 OPENAI_API_BASE_URL=''
-OPENAI_API_KEY=''
\ No newline at end of file
+OPENAI_API_KEY=''
+
+# AUTOMATIC1111_BASE_URL="http://localhost:7860"
+
+# DO NOT TRACK
+SCARF_NO_ANALYTICS=true
+DO_NOT_TRACK=true
\ No newline at end of file

.gitattributes

+*.sh text eol=lf
\ No newline at end of file

.github/pull_request_template.md

+## 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]

.github/workflows/build-release.yml

+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 }}

.github/workflows/docker-build.yaml

@@ -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:

CHANGELOG.md

+# 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.

Dockerfile

@@ -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
+
+# 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/*
 
-# RUN python -c "from sentence_transformers import SentenceTransformer; model = SentenceTransformer('all-MiniLM-L6-v2')"
+# 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"]
\ No newline at end of file
+CMD [ "bash", "start.sh"]
\ No newline at end of file

INSTALLATION.md

-### 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
 

README.md

-# Ollama Web UI: A User-Friendly Web Interface for Chat Interactions 👋
-
-![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)
+# Open WebUI (Formerly Ollama WebUI) 👋
+
+![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.
+
+- 🌐 **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 [OllamaHub](https://ollamahub.com/) integration.
+- 📜 **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:**
-
-- **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
-```
+> [!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.
 
-This command will install both Ollama and Ollama Web UI on your system.
+### Quick Start with Docker 🐳
 
-##### Enable GPU
+> [!IMPORTANT]
+> When using Docker to install Open WebUI, make sure to include the `-v open-webui:/app/backend/data` in your Docker command. This step is crucial as it ensures your database is properly mounted and prevents any loss of data.
 
-Use the additional Docker Compose file designed to enable GPU support by running the following command:
+- **If Ollama is on your computer**, use this command:
 
-```bash
-docker compose -f docker-compose.yaml -f docker-compose.gpu.yaml up -d --build
-```
+  ```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
+  ```
 
-##### Expose Ollama API outside the container stack
+- **If Ollama is on a Different Server**, use this command:
 
-Deploy the service with an additional Docker Compose file designed for API exposure:
+- To connect to Ollama on another server, change the `OLLAMA_API_BASE_URL` to the server's URL:
 
-```bash
-docker compose -f docker-compose.yaml -f docker-compose.api.yaml up -d --build
-```
+  ```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
+  ```
 
-#### Using Provided `run-compose.sh` Script (Linux)
+- After installation, you can access Open WebUI at [http://localhost:3000](http://localhost:3000). Enjoy! 😄
 
-Also available on Windows under any docker-enabled WSL2 linux distro (you have to enable it from Docker Desktop)
+#### Troubleshooting
 
-Simply run the following command to grant execute permission to script:
+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).
 
-```bash
-chmod +x run-compose.sh
-```
+### Other Installation Methods
 
-##### For CPU only container
+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.
 
-```bash
-./run-compose.sh
-```
-
-##### Enable GPU
+### Keeping Your Docker Installation Up-to-Date
 
-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
+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
-./run-compose.sh --enable-gpu
+docker run --rm --volume /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower --run-once open-webui
 ```
 
-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.
-
-> [!IMPORTANT]
-> The backend is required for proper functionality
-
-### Requirements 📦
-
-- 🐰 [Bun](https://bun.sh) >= 1.0.21 or 🐢 [Node.js](https://nodejs.org/en) >= 20.10
-- 🐍 [Python](https://python.org) >= 3.11
-
-### Build and Install 🛠️
-
-Run the following commands to install:
-
-```sh
-git clone https://github.com/ollama-webui/ollama-webui.git
-cd ollama-webui/
-
-# Copying required .env file
-cp -RPp example.env .env
-
-# Building Frontend Using Node
-npm i
-npm run build
-
-# or Building Frontend Using Bun
-# bun install
-# bun run build
-
-# Serving Frontend with the Backend
-cd ./backend
-pip install -r requirements.txt -U
-sh start.sh
-```
-
-You should have the Ollama Web UI up and running at http://localhost:8080/. Enjoy! 😄
-
-## Troubleshooting
-
-See [TROUBLESHOOTING.md](/TROUBLESHOOTING.md) for information on how to troubleshoot and/or join our [Ollama Web UI Discord community](https://discord.gg/5rJgQTnV4s).
-
-## What's Next? 🚀
+In the last part of the command, replace `open-webui` with your container name if it is different.
 
-### Roadmap 📝
+### Moving from Ollama WebUI to Open WebUI
 
-Here are some exciting tasks on our roadmap:
+Check our Migration Guide available in our [Open WebUI Documentation](https://docs.openwebui.com/migration/).
 
-- 🌐 **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.
+## What's Next? 🌟
 
-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! 💪

TROUBLESHOOTING.md

-# 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.

backend/.gitignore

@@ -6,4 +6,6 @@ uploads
 *.db
 _test
 Pipfile
-data/*
\ No newline at end of file
+data/*
+!data/config.json
+.webui_secret_key
\ No newline at end of file

backend/apps/audio/main.py

+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),
+        )

backend/apps/images/main.py

+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))

backend/apps/ollama/main.py

-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()

backend/apps/ollama/old_main.py

@@ -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:

backend/apps/openai/main.py

 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()

backend/apps/rag/main.py

 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("/scan")
+def scan_docs_dir(user=Depends(get_admin_user)):
+    for path in Path(DOCS_DIR).rglob("./**/*"):
+        try:
+            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
 
 
 @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,
-        )
+def reset_vector_db(user=Depends(get_admin_user)):
+    CHROMA_CLIENT.reset()
 
 
 @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))
-
+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:
-            CHROMA_CLIENT.reset()
+            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(e)
+            print("Failed to delete %s. Reason: %s" % (file_path, e))
 
-        return True
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_403_FORBIDDEN,
-            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-        )
+    try:
+        CHROMA_CLIENT.reset()
+    except Exception as e:
+        print(e)
+
+    return True

backend/apps/web/internal/db.py

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

backend/apps/web/main.py

 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,
     }