Implement chat endpoint and integrate with main API

api/chat.py

@@ -0,0 +1,34 @@
+from fastapi import APIRouter, HTTPException
+from fastapi.responses import StreamingResponse
+from core.llm import LLMClient
+from core.memory import save_user_state, load_user_state
+import json
+
+router = APIRouter()
+
+llm_client = LLMClient(provider="ollama")  # Default to Ollama
+
+@router.post("/chat")
+async def chat(user_id: str, message: str):
+    if not message:
+        raise HTTPException(status_code=400, detail="Message is required")
+
+    # Load user state from Redis
+    user_state = load_user_state(user_id)
+    conversation_history = json.loads(user_state.get("conversation", "[]")) if user_state else []
+
+    # Add user message to history
+    conversation_history.append({"role": "user", "content": message})
+
+    # Generate AI response
+    try:
+        response_stream = llm_client.generate(
+            prompt=message,
+            stream=True
+        )
+
+        # Stream response back
+        return StreamingResponse(response_stream, media_type="text/event-stream")
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"LLM generation failed: {e}")

api/main.py

@@ -1,10 +1,12 @@
 from fastapi import FastAPI
 from api.status import router as status_router
+from api.chat import router as chat_router
 
 app = FastAPI()
 
 # Mount status endpoint
 app.include_router(status_router, prefix="/api")
+app.include_router(chat_router, prefix="/api")
 
 @app.get("/")
 async def root():