Update app.py

app.py

@@ -6,17 +6,16 @@ from openai import AsyncOpenAI
 
 app = FastAPI()
 
-# Define a request model for the prompt and optional model name
 class GenerateRequest(BaseModel):
     prompt: str
-    model: str 
+    model: str  # e.g., "deepseek/DeepSeek-V3-0324"
 
 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")
-    
+
+    # You can also make this endpoint dynamic if needed
     endpoint = "https://models.github.ai/inference"
 
     client = AsyncOpenAI(base_url=endpoint, api_key=token)
@@ -27,7 +26,7 @@ async def generate_ai_response(prompt: str, model: str):
                 {"role": "system", "content": "You are a helpful assistant."},
                 {"role": "user", "content": prompt}
             ],
-            model=model,
+            model=model,  # dynamically set model from user input
             temperature=1.0,
             top_p=1.0,
             stream=True
@@ -45,11 +44,11 @@ async def generate_ai_response(prompt: str, model: str):
 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
+    return app