LocalFoodAI_FerRo988/main.py

import json
import logging
import httpx
from fastapi import FastAPI, HTTPException
from fastapi.responses import HTMLResponse, StreamingResponse
from fastapi.staticfiles import StaticFiles
from pydantic import BaseModel
from typing import List, Generator

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

app = FastAPI(title="LocalFoodAI Chat")

OLLAMA_URL = "http://localhost:11434/api/chat"
MODEL_NAME = "llama3.1:8b"

# Mount static files to serve the frontend
app.mount("/static", StaticFiles(directory="static"), name="static")

class ChatMessage(BaseModel):
    role: str
    content: str

class ChatRequest(BaseModel):
    messages: List[ChatMessage]

@app.get("/", response_class=HTMLResponse)
async def read_root():
    """Serve the chat interface HTML"""
    try:
        with open("static/index.html", "r", encoding="utf-8") as f:
            return HTMLResponse(content=f.read())
    except FileNotFoundError:
        return HTMLResponse(content="<h1>Welcome to LocalFoodAI</h1><p>static/index.html not found. Please create the frontend.</p>")

@app.post("/chat")
async def chat_endpoint(request: ChatRequest):
    """Proxy chat requests to the local Ollama instance with streaming support"""
    payload = {
        "model": MODEL_NAME,
        "messages": [msg.model_dump() for msg in request.messages],
        "stream": True  # Enable streaming for a better UI experience
    }
    
    async def generate_response():
        try:
            async with httpx.AsyncClient() as client:
                async with client.stream("POST", OLLAMA_URL, json=payload, timeout=120.0) as response:
                    if response.status_code != 200:
                        error_detail = await response.aread()
                        logger.error(f"Error communicating with Ollama: {error_detail}")
                        yield f"data: {json.dumps({'error': 'Error communicating with local LLM.'})}\n\n"
                        return

                    async for line in response.aiter_lines():
                        if line:
                            data = json.loads(line)
                            if "message" in data and "content" in data["message"]:
                                content = data["message"]["content"]
                                yield f"data: {json.dumps({'content': content})}\n\n"
                            if data.get("done"):
                                break
        except Exception as e:
            logger.error(f"Unexpected error during stream: {e}")
            yield f"data: {json.dumps({'error': str(e)})}\n\n"

    return StreamingResponse(generate_response(), media_type="text/event-stream")

if __name__ == "__main__":
    import uvicorn
    uvicorn.run("main:app", host="127.0.0.1", port=8000, reload=True)