Update main.py

main.py

@@ -7,10 +7,6 @@ from aiohttp import ClientSession
 from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 from typing import List, Dict, Any, Optional
-import time
-import uuid
-import json
-from fastapi.responses import StreamingResponse
 
 # Mock implementations for ImageResponse and to_data_uri
 class ImageResponse:
@@ -186,7 +182,6 @@ class ChatRequest(BaseModel):
     model: str
     messages: List[Message]
 
-
 @app.post("/v1/chat/completions")
 async def chat_completions(request: ChatRequest):
     messages = [{"role": msg.role, "content": msg.content} for msg in request.messages]
@@ -197,45 +192,23 @@ async def chat_completions(request: ChatRequest):
         messages=messages
     )
 
-    response_id = f"chatcmpl-{uuid.uuid4()}"
-    created_timestamp = int(time.time())
-
-    async def generate_response():
-        # Stream the response content
-        async for chunk in async_generator:
-            if isinstance(chunk, str):
-                yield json.dumps({
-                    "id": response_id,
-                    "object": "chat.completion.chunk",
-                    "created": created_timestamp,
-                    "model": request.model,
-                    "choices": [
-                        {
-                            "message": {
-                                "role": "assistant",
-                                "content": chunk
-                            },
-                            "finish_reason": None,
-                            "index": 0
-                        }
-                    ]
-                }).encode('utf-8')
-            else:
-                yield json.dumps({
-                    "id": response_id,
-                    "object": "chat.completion.chunk",
-                    "created": created_timestamp,
-                    "model": request.model,
-                    "choices": [
-                        {
-                            "message": {
-                                "role": "assistant",
-                                "content": chunk.content
-                            },
-                            "finish_reason": None,
-                            "index": 0
-                        }
-                    ]
-                }).encode('utf-8')
-
-    return StreamingResponse(generate_response(), media_type="application/json")
+    response_content = ""
+    async for chunk in async_generator:
+        response_content += chunk if isinstance(chunk, str) else chunk.content  # Concatenate response
+
+    return {
+        "id": f"chatcmpl-{uuid.uuid4()}",  # Generate a unique ID
+        "object": "chat.completion",
+        "created": int(datetime.now().timestamp()),  # Current timestamp
+        "model": request.model,
+        "choices": [
+            {
+                "message": {
+                    "role": "assistant",
+                    "content": response_content
+                },
+                "finish_reason": "stop",
+                "index": 0
+            }
+        ]
+    }