app.py

import os
from openai import OpenAI
from gradio import Server
from fastapi.responses import HTMLResponse

app = Server()

client = OpenAI(
    base_url="https://router.huggingface.co/v1",
    api_key=os.environ["HF_TOKEN"],
    default_headers={
        "X-HF-Bill-To": "huggingface"
    }
)

@app.api()
def chat(message: str, history_json: list) -> str:
    messages = history_json + [{"role": "user", "content": message}]
    
    stream = client.chat.completions.create(
        model="deepseek-ai/DeepSeek-V4-Pro:fireworks-ai",
        messages=messages,
        stream=True,
    )
    
    full_response = ""
    for chunk in stream:
        if chunk.choices[0].delta.content is not None:
            full_response += chunk.choices[0].delta.content
            yield full_response

@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:
        return HTMLResponse(content=f.read())

if __name__ == "__main__":
    app.launch(show_error=True)