preparations for demo html page

services/rag/langchain/PLANNING.md

@@ -46,5 +46,13 @@ Chosen data folder: relatve ./../../../data - from the current folder
 
 # Phase 8 (http endpoint to retrieve data from the vector storage by query)
 
-- [ ] Create file `server.py`, with web framework fastapi, for example
+- [x] Create file `server.py`, with web framework fastapi, for example
-- [ ] Add POST endpoint "/api/test-query" which will use agent, and retrieve response for query, sent in JSON format, field "query"
+- [x] Add POST endpoint "/api/test-query" which will use agent, and retrieve response for query, sent in JSON format, field "query"
+
+# Phase 9 (simple html web page with chat interface)
+
+- [ ] Create html webpage called demo.html, with simple UI for chat interface. It can be taken with predefined data from codepen or something
+- [ ] Adjust demo.html code, so it would in fact work with the API endpoint, as chat with the agent. API endpoint should be asked beforehand in propmt message.
+- [ ] After accepting API endpont address, it should be used to send requests and process responses to imitate chat with the agent by the provided API endpoint.
+- [ ] Show API endpoint in the header of the chat.
+- [ ] If there is error connecting with the API, imitate bot sending message about error with the connection and suggestion to reload page to provide new API endpoint

services/rag/langchain/QWEN.md

@@ -28,6 +28,7 @@ rag-solution/services/rag/langchain/
 ├── PLANNING.md        # Development roadmap and phases
 ├── QWEN.md            # Current file - project context
 ├── requirements.txt   # Python dependencies
+├── server.py          # Web server with API endpoints for the RAG agent
 ├── vector_storage.py  # Vector storage module with Qdrant and Ollama embeddings
 └── venv/              # Virtual environment
 ```
@@ -85,7 +86,11 @@ The project is organized into 8 development phases as outlined in `PLANNING.md`:
 - [x] Allow switching between "ollama" and "openai" strategies
 
 ### Phase 8: HTTP Endpoint
-- [ ] Create web framework with POST endpoint `/api/test-query` for agent queries
+- [x] Create web framework with POST endpoint `/api/test-query` for agent queries
+- [x] Implement server using FastAPI and LangServe
+- [x] Add request/response validation with Pydantic models
+- [x] Include CORS middleware for cross-origin requests
+- [x] Add health check endpoint
 
 ## Environment Configuration
 
@@ -195,6 +200,15 @@ The project is in early development phase. The virtual environment is set up and
 - When strategy is "ollama" (default), uses existing `ChatOllama` implementation
 - Updated CLI chat command to show which model strategy is being used
 
+### Phase 8 Implementation Notes
+- Created `server.py` with FastAPI and integrated with existing agent functionality
+- Implemented `/api/test-query` POST endpoint that accepts JSON with "query" field
+- Added request/response validation using Pydantic models
+- Included CORS middleware to support cross-origin requests
+- Added health check endpoint at root path
+- Server runs on port 8000 by default
+- Supports both Ollama and OpenAI strategies through existing configuration
+
 ### Issue Fix Notes
 - Fixed DocumentRetrievalTool class to properly declare and initialize the retriever field
 - Resolved Pydantic field declaration issue that caused "object has no field" error

services/rag/langchain/server.py

@@ -0,0 +1,118 @@
+"""Web server for the RAG solution with LangServe integration."""
+
+import json
+import os
+from contextlib import asynccontextmanager
+from typing import Any, Dict
+
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from loguru import logger
+from pydantic import BaseModel
+
+from agent import chat_with_agent
+
+
+class QueryRequest(BaseModel):
+    """Request model for the query endpoint."""
+
+    query: str
+    collection_name: str = "documents_langchain"
+    # llm_model: str = None
+
+
+class QueryResponse(BaseModel):
+    """Response model for the query endpoint."""
+
+    response: str
+    query: str
+    success: bool
+    error: str = None
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    """Lifespan event handler for startup and shutdown."""
+    # Startup
+    logger.info("Starting RAG server...")
+    yield
+    # Shutdown
+    logger.info("Shutting down RAG server...")
+
+
+# Create FastAPI app
+app = FastAPI(
+    title="RAG Solution API",
+    description="API for Retrieval-Augmented Generation solution with Langchain",
+    version="1.0.0",
+    lifespan=lifespan,
+)
+
+# Add CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # In production, configure this properly
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.post("/api/test-query", response_model=QueryResponse)
+async def test_query(request: QueryRequest) -> QueryResponse:
+    """
+    POST endpoint to query the RAG agent.
+
+    Accepts a JSON payload with a "query" field and returns the agent's response.
+    """
+    logger.info(f"Received query: {request.query}")
+
+    try:
+        # Call the existing chat_with_agent function from agent.py
+        response_data = chat_with_agent(
+            query=request.query,
+            collection_name=request.collection_name,
+            llm_model=request.llm_model,
+        )
+
+        logger.info("Query processed successfully")
+
+        return QueryResponse(
+            response=response_data.get("response", ""),
+            query=request.query,
+            success=response_data.get("success", False),
+        )
+
+    except Exception as e:
+        logger.error(f"Error processing query: {str(e)}")
+        error_msg = f"Error processing query: {str(e)}"
+
+        return QueryResponse(
+            response="I encountered an error while processing your request.",
+            query=request.query,
+            success=False,
+            error=error_msg,
+        )
+
+
+@app.get("/")
+async def root():
+    """Root endpoint for health check."""
+    return {"message": "RAG Solution API is running", "status": "healthy"}
+
+
+if __name__ == "__main__":
+    import uvicorn
+
+    # Configure logging to output to both file and stdout as specified in requirements
+    logs_dir = os.path.join(os.getcwd(), "logs")
+    os.makedirs(logs_dir, exist_ok=True)
+    logger.add("logs/dev.log", rotation="10 MB", retention="10 days")
+
+    # Run the server
+    uvicorn.run(
+        "server:app",
+        host="0.0.0.0",
+        port=8000,
+        reload=True,  # Enable auto-reload during development
+    )