Create app.py

app.py

@@ -0,0 +1,63 @@
+import uvicorn
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from huggingface_hub import InferenceClient
+from pydantic import BaseModel
+
+app = FastAPI()
+
+# Configure CORS
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct")
+
+class ChatRequest(BaseModel):
+    message: str
+    history: list[tuple[str, str]]
+    system_message: str
+    max_tokens: int
+    temperature: float
+    top_p: float
+
+def generate_response(messages, max_tokens, temperature, top_p):
+    for chunk in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        yield chunk.choices[0].delta.content or ""
+
+@app.post("/api/chat")
+async def chat_stream(request: ChatRequest):
+    try:
+        messages = [{"role": "system", "content": request.system_message}]
+        
+        for user_msg, assistant_msg in request.history:
+            messages.extend([
+                {"role": "user", "content": user_msg},
+                {"role": "assistant", "content": assistant_msg}
+            ])
+            
+        messages.append({"role": "user", "content": request.message})
+
+        return StreamingResponse(
+            generate_response(
+                messages=messages,
+                max_tokens=request.max_tokens,
+                temperature=request.temperature,
+                top_p=request.top_p
+            ),
+            media_type="text/event-stream"
+        )
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)