Using the ai_service as backend for openwebui

ai_service/README.md

@@ -1,25 +1,28 @@
-# AI Service for Chatbot Application
+# OpenWebUI Backend Service
 
-This is the AI service component for the chatbot application. It provides APIs for document processing, embeddings, and chat functionality.
+This is a backend service for OpenWebUI that provides OpenWebUI-compatible API endpoints for chat functionality and model switching.
 
 ## Features
 
-- Document processing and embedding
-- Retrieval-augmented generation (RAG)
+- OpenWebUI-compatible API endpoints
+- Ollama API proxy
 - Chat functionality with model switching
-- Team chat support
+- Support for multiple LLM models (gemma3, llama3.3, llama3.1, mistral, deepseek)
 
 ## Project Structure
 
 ```
 ai_service/
-├── embeddings/       # Embedding and document processing services
 ├── models/           # Model and chat services
-├── utils/            # Utility functions
-├── data/             # Data storage
+│   ├── 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
-└── run.py            # Script to run the service
+└── deploy.sh         # Deployment script
 ```
 
 ## Setup Instructions
@@ -43,7 +46,7 @@ ai_service/
 
 4. Run the service:
    ```
-   python run.py
+   python ../run_ai_service.py
    ```
 
 ## API Documentation
@@ -70,20 +73,20 @@ This will start the service on port 5251 using uvicorn with nohup.
 
 ## API Endpoints
 
-### Document Endpoints
+### Health Check
 
-- `POST /documents` - Process a document for embedding
-- `GET /documents` - Get all documents
-- `GET /documents/{doc_id}` - Get a document by ID
-- `DELETE /documents/{doc_id}` - Delete a document
-- `POST /documents/search` - Search for documents
+- `GET /health` - Check if the service is running
 
-### Model Endpoints
+### OpenWebUI-Compatible Endpoints
 
-- `GET /models` - Get available models
-- `GET /models/{model_id}` - Get information about a model
+- `GET /api/models` - Get available models in OpenWebUI format
+- `POST /api/chat/completions` - OpenAI-compatible chat completions endpoint
 
-### Chat Endpoints
+### Ollama API Proxy
+
+- `POST /ollama/api/generate` - Proxy to Ollama's generate endpoint
+
+### Original API Endpoints
 
 - `POST /chats` - Create a new chat
 - `GET /chats/user/{user_id}` - Get all chats for a user