Spaces:
Sleeping
Sleeping
File size: 1,721 Bytes
f7c0abb b9e465f fa8e2ce dc76d86 d0fc55f f7c0abb dc76d86 b9e465f fa8e2ce 6025f1c b9e465f 6025f1c f7c0abb d0fc55f f7c0abb d1cb607 f7c0abb 6025f1c d0fc55f f7c0abb d0fc55f 045ef7e f7c0abb 045ef7e b9e465f f7c0abb dc76d86 b9e465f 045ef7e fa8e2ce dc76d86 93c4b1f 7a83ce6 20d0b59 387e225 b9e465f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
import os
from fastapi import FastAPI, HTTPException
from fastapi.responses import StreamingResponse
from pydantic import BaseModel
from openai import AsyncOpenAI
app = FastAPI()
# Define a request model for the prompt and optional model name
class GenerateRequest(BaseModel):
prompt: str
model: str | None = "openai/gpt-4.1-mini" # Default model
async def generate_ai_response(prompt: str, model: str):
# Configuration for unofficial GitHub AI endpoint
token = os.getenv("GITHUB_TOKEN")
if not token:
raise HTTPException(status_code=500, detail="GitHub token not configured")
endpoint = "https://models.github.ai/inference"
client = AsyncOpenAI(base_url=endpoint, api_key=token)
try:
stream = await client.chat.completions.create(
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
],
model=model,
temperature=1.0,
top_p=1.0,
stream=True
)
async for chunk in stream:
if chunk.choices and chunk.choices[0].delta.content:
yield chunk.choices[0].delta.content
except Exception as err:
yield f"Error: {str(err)}"
raise HTTPException(status_code=500, detail="AI generation failed")
@app.post("/generate")
async def generate_response(request: GenerateRequest):
if not request.prompt:
raise HTTPException(status_code=400, detail="Prompt cannot be empty")
return StreamingResponse(
generate_ai_response(request.prompt, request.model),
media_type="text/event-stream"
)
def get_app():
return app |