Using the ai_service as backend for openwebui

README.md

@@ -1,61 +1,90 @@
-# Chatbot Application
+# OpenWebUI Backend Service
 
-A chatbot application with document training, private/team chat options, and model switching capability.
+A backend service for OpenWebUI that provides OpenWebUI-compatible API endpoints for chat functionality and model switching.
 
 ## Features
 
-- Document training through library page
-- Private chat functionality
-- Team chat functionality (multiple users can see each other's interactions)
-- Model switching capability
+- OpenWebUI-compatible API endpoints
+- Ollama API proxy
+- Chat functionality with model switching
+- Support for multiple LLM models (gemma3, llama3.3, llama3.1, mistral, deepseek)
 
 ## Technology Stack
 
-- **Backend**: Flask with FastAPI
-- **Database**: MySQL
-- **Vector Database**: Pinecone
-- **Embeddings**: Sentence Transformers / OpenAI Embeddings
-- **Chat Models**: Various LLMs (configurable)
+- **Backend**: FastAPI
+- **Chat Models**: Ollama models via OpenWebUI
 
 ## Project Structure
 
 ```
-app/
-├── api/            # API endpoints (Flask and FastAPI)
-├── config/         # Configuration settings
-├── database/       # Database connection and utilities
-├── models/         # Database models
-├── services/       # Business logic services
-└── utils/          # Utility functions
-tests/              # Test cases
+ai_service/
+├── models/           # Model and chat services
+│   ├── model_service.py
+│   ├── chat_service.py
+│   └── model_parameters.py
+├── embeddings/       # Document processing for RAG
+│   └── document_service.py
+├── openwebui_api.py  # OpenWebUI-compatible API endpoints
+├── config.py         # Configuration settings
+├── api.py            # FastAPI application
+└── deploy.sh         # Deployment script
+run_ai_service.py     # Script to run the service
+deploy_ai_service.sh  # Local deployment script
+remote_deploy.sh      # Remote deployment script
 ```
 
 ## Setup Instructions
 
-1. Clone the repository
-2. Create a virtual environment:
+1. Create a virtual environment:
    ```
    python -m venv venv
    source venv/bin/activate  # On Windows: venv\Scripts\activate
    ```
-3. Install dependencies:
+
+2. Install dependencies:
    ```
    pip install -r requirements.txt
    ```
-4. Copy `.env.example` to `.env` and update the values
-5. Initialize the database:
+
+3. Copy `.env.example` to `.env` and update the values:
    ```
-   flask db init
-   flask db migrate
-   flask db upgrade
+   cp ai_service/.env.example ai_service/.env
+   # Edit the .env file with appropriate values
    ```
-6. Run the application:
+
+4. Run the service:
    ```
-   python run.py
+   python run_ai_service.py
+   ```
+
+## Deployment
+
+To deploy the service:
+
+1. Local deployment:
+   ```
+   ./deploy_ai_service.sh
+   ```
+
+2. Remote deployment:
+   ```
+   ./remote_deploy.sh [server_ip] [user] [port] [remote_dir]
    ```
 
 ## API Documentation
 
-Once the application is running, you can access the API documentation at:
-- FastAPI Swagger UI: http://localhost:5000/docs
-- FastAPI ReDoc: http://localhost:5000/redoc
+Once the service is running, you can access the API documentation at:
+- Swagger UI: http://localhost:5251/docs
+- ReDoc: http://localhost:5251/redoc
+
+## OpenWebUI Configuration
+
+To configure OpenWebUI to use this service as its backend:
+
+1. Set the following environment variables in OpenWebUI:
+   ```
+   OLLAMA_API_BASE_URL=http://your-server-ip:5251/ollama
+   OPENAI_API_BASE_URL=http://your-server-ip:5251/api
+   ```
+
+2. Restart OpenWebUI to apply the changes.