File size: 2,769 Bytes
f7c0abb
045ef7e
387e225
d0fc55f
f7c0abb
 
 
93c4b1f
6025f1c
387e225
6025f1c
 
 
 
 
 
 
 
 
f7c0abb
d0fc55f
f7c0abb
 
 
 
6025f1c
 
 
d0fc55f
f7c0abb
 
d0fc55f
045ef7e
 
f7c0abb
 
045ef7e
 
f7c0abb
387e225
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f7c0abb
045ef7e
 
 
 
387e225
 
 
 
93c4b1f
7a83ce6
20d0b59
387e225
1287daf
 
387e225
 
 
 
 
 
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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
import os
from fastapi import FastAPI, HTTPException
from fastapi.responses import StreamingResponse, Response
from openai import AsyncOpenAI

app = FastAPI()

async def generate_ai_response(prompt: str):
    # Configuration for unofficial GitHub AI endpoint
    global token
    token = os.getenv("GITHUB_TOKEN")
    if not token:
        raise HTTPException(status_code=500, detail="GitHub token not configured")
    
    endpoint = "https://models.github.ai/inference"
    model = "openai/gpt-4.1-mini"  # Unofficial model name

    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")

class CustomStreamingResponse(Response):
    def __init__(self, content, token, media_type="text/event-stream", status_code=200):
        super().__init__(content=content, media_type=media_type, status_code=status_code)
        self.token = token

    async def __call__(self, scope, receive, send):
        await send({
            "type": "http.response.start",
            "status": self.status_code,
            "headers": [
                (b"content-type", self.media_type.encode()),
                (b"x-token-value", self.token.encode())
            ]
        })
        async for chunk in self.body_iterator:
            await send({
                "type": "http.response.body",
                "body": chunk.encode() if isinstance(chunk, str) else chunk,
                "more_body": True
            })
        await send({
            "type": "http.response.body",
            "body": b"",
            "more_body": False
        })

@app.post("/generate")
async def generate_response(prompt: str):
    if not prompt:
        raise HTTPException(status_code=400, detail="Prompt cannot be empty")
    
    global token
    return CustomStreamingResponse(
        content=generate_ai_response(prompt),
        token=token,
        media_type="text/event-stream"
    )

@app.get("/get-token")  # New endpoint to return the token
async def get_token():
    global token
    if not token:
        raise HTTPException(status_code=500, detail="GitHub token not configured")
    return {"token": token}

def get_app():
    return app