Added Rag Featured

README_RAG.md

@@ -0,0 +1,73 @@
+# Document-Based Question Answering with OpenWebUI
+
+This document explains how to use the document-based question answering (RAG) functionality in the AI service.
+
+## Overview
+
+The AI service now supports Retrieval Augmented Generation (RAG) by leveraging OpenWebUI's built-in knowledge database. This allows users to:
+
+1. Upload documents to OpenWebUI
+2. Ask questions about those documents
+3. Receive responses that incorporate information from the documents
+
+## How It Works
+
+When RAG is enabled:
+
+1. The AI service forwards the request to OpenWebUI with `use_knowledge=True`
+2. OpenWebUI searches its knowledge database for relevant information
+3. The retrieved information is used to augment the model's response
+4. The response is returned to the user
+
+## Using RAG in API Requests
+
+To enable RAG in your API requests, set the `use_rag` parameter to `true`:
+
+```json
+POST /chats/{chat_id}/messages
+{
+  "message": "What information do you have about project X?",
+  "user_id": "user123",
+  "use_rag": true
+}
+```
+
+## Testing RAG Functionality
+
+You can test the RAG functionality using the `/test-rag` endpoint:
+
+```
+POST /test-rag?query=What information do you have about project X?
+```
+
+This will return a response that includes information from documents in OpenWebUI's knowledge database.
+
+## Uploading Documents to OpenWebUI
+
+To use RAG effectively, you need to upload documents to OpenWebUI:
+
+1. Log in to OpenWebUI at your configured URL (default: http://104.225.217.215:8080)
+2. Navigate to the Knowledge section
+3. Upload your documents (PDF, TXT, DOCX, etc.)
+4. OpenWebUI will automatically process and index the documents
+
+## Troubleshooting
+
+If RAG is not working as expected:
+
+1. Ensure OpenWebUI is running and accessible
+2. Check that documents are properly uploaded and indexed in OpenWebUI
+3. Verify that the `use_rag` parameter is set to `true` in your requests
+4. Check the logs for any errors related to OpenWebUI API calls
+
+If there are connection issues with OpenWebUI, the AI service will automatically fall back to using the direct Ollama API without RAG.
+
+## Configuration
+
+The following configuration settings affect RAG functionality:
+
+- `OPENWEBUI_URL`: URL of your OpenWebUI instance
+- `OPENWEBUI_API_KEY`: API key for OpenWebUI (if required)
+- `API_TIMEOUT`: Timeout for API requests (in seconds)
+
+These can be set in your environment variables or in the `.env` file.