Update app.py

app.py

@@ -3,19 +3,15 @@ from fastapi.responses import StreamingResponse
 from pydantic import BaseModel
 from typing import List
 from g4f import ChatCompletion
-from slowapi import Limiter
-from slowapi.util import get_remote_address
 
 app = FastAPI()
 
-# Initialize the rate limiter
-limiter = Limiter(key_func=get_remote_address)
-
 # List of available models
 models = [
     "gpt-4o", "gpt-4o-mini", "gpt-4",
     "gpt-4-turbo", "gpt-3.5-turbo",
-    "claude-3.7-sonnet", "o3-mini", "o1", "claude-3.5", "llama-3.1-405b", "gemini-flash", "blackboxai-pro", "openchat-3.5", "glm-4-9B", "blackboxai"
+    "claude-3.7-sonnet", "o3-mini", "o1", "claude-3.5", 
+    "llama-3.1-405b"
 ]
 
 # Request model
@@ -26,7 +22,7 @@ class Message(BaseModel):
 class ChatRequest(BaseModel):
     model: str
     messages: List[Message]
-    streaming: bool = True  # Add streaming support
+    streaming: bool = True
 
 class ChatResponse(BaseModel):
     role: str
@@ -34,7 +30,7 @@ class ChatResponse(BaseModel):
 
 # Dependency to check API key
 async def verify_api_key(x_api_key: str = Header(...)):
-    if x_api_key != "vs-5wEvIw6vfLKIypGm7uiNoWuXrJcg4vAL":  # Replace with your actual API key
+    if x_api_key != "fb207532285886a5568298b4b4e61124":
         raise HTTPException(status_code=403, detail="Invalid API key")
 
 @app.get("/v1/models", tags=["Models"])
@@ -43,12 +39,14 @@ async def get_models():
     return {"models": models}
 
 @app.post("/v1/chat/completions", tags=["Chat Completion"])
-@limiter.limit("10/minute")  # Rate limit to 10 requests per minute
 async def chat_completion(
-    request: Request,
     chat_request: ChatRequest,
     api_key: str = Depends(verify_api_key)
 ):
+    """
+    Handle chat completion requests with optional streaming.
+    Removed rate limiting for unrestricted access.
+    """
     # Validate model
     if chat_request.model not in models:
         raise HTTPException(status_code=400, detail="Invalid model selected.")
@@ -67,34 +65,37 @@ async def chat_completion(
                 response = ChatCompletion.create(
                     model=chat_request.model,
                     messages=formatted_messages,
-                    stream=True  # Enable streaming
+                    stream=True
                 )
                 
                 for chunk in response:
                     if isinstance(chunk, dict) and 'choices' in chunk:
                         for choice in chunk['choices']:
-                            if 'message' in choice:
-                                yield f"data: {choice['message']['content']}\n\n"
+                            if 'delta' in choice and 'content' in choice['delta']:
+                                yield f"data: {json.dumps({'content': choice['delta']['content']})}\n\n"
+                            elif 'message' in choice:
+                                yield f"data: {json.dumps({'content': choice['message']['content']})}\n\n"
                     else:
-                        yield f"data: {chunk}\n\n"  # Fallback if chunk is not as expected
+                        yield f"data: {json.dumps({'content': str(chunk)})}\n\n"
 
             return StreamingResponse(event_stream(), media_type="text/event-stream")
         else:
             # Non-streaming response
             response = ChatCompletion.create(
                 model=chat_request.model,
-                messages=formatted_messages
+                messages=formatted_messages,
+                stream=False
             )
 
             if isinstance(response, str):
-                response_content = response  # Directly use if it's a string
+                return ChatResponse(role="assistant", content=response)
+            elif isinstance(response, dict) and 'choices' in response:
+                return ChatResponse(
+                    role="assistant",
+                    content=response['choices'][0]['message']['content']
+                )
             else:
-                try:
-                    response_content = response['choices'][0]['message']['content']
-                except (IndexError, KeyError):
-                    raise HTTPException(status_code=500, detail="Unexpected response structure.")
-
-            return ChatResponse(role="assistant", content=response_content)
+                raise HTTPException(status_code=500, detail="Unexpected response structure.")
 
     except Exception as e:
         raise HTTPException(status_code=500, detail=str(e))