Update app.py

app.py

@@ -1,7 +1,7 @@
 import os
 from fastapi import FastAPI, HTTPException
 from fastapi.responses import StreamingResponse
-from openai import AsyncOpenAI
+import openai  # Use OpenAI's official API library
 from pydantic import BaseModel
 
 # Initialize FastAPI app
@@ -16,44 +16,34 @@ token = os.getenv("GITHUB_TOKEN")
 if not token:
     raise ValueError("GITHUB_TOKEN environment variable not set")
 
-# Use the correct endpoint for GitHub Models or fallback to a compatible OpenAI-like API
-endpoint = os.getenv("API_ENDPOINT", "https://api.github.com/models")  # Adjust based on GitHub Models documentation
-model = os.getenv("MODEL_NAME", "gpt-4o-mini")  # Use a valid model name, e.g., gpt-4o-mini or equivalent
+# Initialize OpenAI API client with API key
+openai.api_key = token  # Set the OpenAI API key
 
-# Initialize AsyncOpenAI client without proxies to avoid TypeError
-client = AsyncOpenAI(
-    base_url=endpoint,
-    api_key=token,
-    # Explicitly disable proxies if not needed
-    http_client=None  # Avoid passing unexpected kwargs like proxies
-)
-
-# Async generator to stream chunks
+# Async generator to stream chunks from OpenAI's API
 async def stream_response(prompt: str):
     try:
-        # Create streaming chat completion
-        stream = await client.chat.completions.create(
+        # Create streaming chat completion with OpenAI API
+        response = openai.ChatCompletion.create(
+            model="gpt-4",  # Replace with the model you're using (e.g., gpt-3.5-turbo or gpt-4)
             messages=[
                 {"role": "system", "content": "You are a helpful assistant."},
                 {"role": "user", "content": prompt}
             ],
             temperature=1.0,
             top_p=1.0,
-            model=model,
-            stream=True
+            stream=True  # Enable streaming
         )
 
-        # Yield each chunk as it arrives
-        async for chunk in stream:
-            if chunk.choices and len(chunk.choices) > 0:
-                content = chunk.choices[0].delta.content or ""
-                if content:  # Only yield non-empty content
-                    yield content
+        # Yield each chunk of the response as it arrives
+        for chunk in response:
+            content = chunk.get("choices", [{}])[0].get("delta", {}).get("content", "")
+            if content:
+                yield content  # Yield the generated content
 
     except Exception as err:
         yield f"Error: {str(err)}"
 
-# Endpoint to handle prompt and stream response
+# Endpoint to handle the prompt and stream response
 @app.post("/generate")
 async def generate_response(request: PromptRequest):
     try:
@@ -68,4 +58,4 @@ async def generate_response(request: PromptRequest):
 # Health check endpoint for Hugging Face Spaces
 @app.get("/")
 async def health_check():
-    return {"status": "healthy"}
+    return {"status": "healthy"}