app.py

import os
import json
from openai import OpenAI
from gradio import Server
from fastapi.responses import HTMLResponse, StreamingResponse
from fastapi import Request

# ── OpenAI-compatible client pointing at HF Router ──────────────────────────
client = OpenAI(
    base_url="https://router.huggingface.co/v1",
    api_key=os.environ.get("HF_TOKEN", ""),
    default_headers={"X-HF-Bill-To": "huggingface"},
)

MODEL = "MiniMaxAI/MiniMax-M3:novita"

app = Server()


# ── Serve the custom frontend ────────────────────────────────────────────────
@app.get("/")
async def homepage():
    html_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "index.html")
    with open(html_path, "r", encoding="utf-8") as f:
        content = f.read()
    return HTMLResponse(content=content)


# ── Streaming chat endpoint (SSE) ────────────────────────────────────────────
@app.post("/chat")
async def chat_stream(request: Request):
    """
    Accepts JSON body:
      {
        "messages": [
          { "role": "user", "content": "..." }          ← text-only
          { "role": "user", "content": [               ← multimodal
              {"type": "text", "text": "..."},
              {"type": "image_url", "image_url": {"url": "..."}}
            ]
          }
        ]
      }
    Returns an SSE stream of partial tokens.
    """
    body = await request.json()
    messages = body.get("messages", [])

    async def generate():
        try:
            stream = client.chat.completions.create(
                model=MODEL,
                messages=messages,
                stream=True,
            )
            for chunk in stream:
                delta = chunk.choices[0].delta
                content = delta.content
                if content:
                    payload = json.dumps({"token": content})
                    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"
            yield "data: [DONE]\n\n"

    return StreamingResponse(
        generate(),
        media_type="text/event-stream",
        headers={
            "Cache-Control": "no-cache",
            "X-Accel-Buffering": "no",
        },
    )


app.launch(show_error=True)