Как создать продакшн AI-чат-бота на Python: FastAPI, стриминг SSE и память в Redis

import json
import asyncio
from fastapi import FastAPI, HTTPException
from fastapi.responses import StreamingResponse
from pydantic import BaseModel
from openai import AsyncOpenAI

app = FastAPI(title="Production AI Chat Service 2026")
client = AsyncOpenAI(api_key="your-api-key", base_url="https://api.deepseek.com")

class ChatRequest(BaseModel):
    user_id: str
    message: str

async def generate_token_stream(prompt: str):
    """Асинхронный генератор SSE-потока токенов."""
    try:
        response = await client.chat.completions.create(
            model="deepseek-chat",
            messages=[
                {"role": "system", "content": "Ты — полезный ассистент сервиса."},
                {"role": "user", "content": prompt}
            ],
            stream=True
        )
        async for chunk in response:
            token = chunk.choices[0].delta.content or ""
            if token:
                # Формат SSE: "data: <payload>\n\n"
                payload = json.dumps({"token": token})
                yield f"data: {payload}\n\n"
        yield "data: [DONE]\n\n"
    except Exception as e:
        yield f"data: {json.dumps({'error': str(e)})}\n\n"

@app.post("/api/chat/stream")
async def chat_stream_endpoint(req: ChatRequest):
    return StreamingResponse(
        generate_token_stream(req.message),
        media_type="text/event-stream",
        headers={
            "Cache-Control": "no-cache",
            "Connection": "keep-alive",
            "X-Accel-Buffering": "no" # Отключает буферизацию в Nginx!
        }
    )