Backend Boilerplates python Advanced

OpenAI Streaming Response

Stream a ChatGPT response token-by-token to the client using FastAPI StreamingResponse.

python

from fastapi import FastAPI
from fastapi.responses import StreamingResponse
from openai import AsyncOpenAI

app = FastAPI()
client = AsyncOpenAI()

@app.post("/chat")
async def chat(prompt: str):
    async def token_stream():
        async for chunk in await client.chat.completions.create(
            model="gpt-4o-mini",
            messages=[{"role": "user", "content": prompt}],
            stream=True,
        ):
            delta = chunk.choices[0].delta.content or ""
            if delta:
                yield delta
    return StreamingResponse(token_stream(), media_type="text/plain")