Updated Space.

app.py

@@ -559,7 +559,7 @@ async def respond(
         
 
 handleApiKeys();loadModels();checkModels();loadENV();
-lastUpdateMessage = "Better search faketool."
+lastUpdateMessage = "New API handling (the old one is shutdown)."
 demo = gr.ChatInterface(
     respond,
     title="GPT-4O-mini",
@@ -601,67 +601,6 @@ def test():
 def html():
     return FileResponse("index.html")
 
-@app.get("/api/v1/models")
-async def test_endpoint():
-    return JSONResponse(content=modelList)
-
-@app.post("/api/v1/chat/completions")
-async def chat_completion(request: Request):
-    try:
-        body = await request.json()
-
-        if not body.get("messages") or not body.get("model"):
-            return JSONResponse(content={"error": { "code": "MISSING_VALUE", "message": "Both 'messages' and 'model' are required fields."}}, status_code=400)
-        if not body.get("model") in models:
-            return JSONResponse(content={"error": { "code": "INVALID_MODEL", "message": "The model name provided in the request does not exists in predefined list of models."}}, status_code=400)
-
-        params = {
-            key: value for key, value in {
-                "model": body.get("model"),
-                "messages": body.get("messages"),
-                "max_tokens": body.get("max_tokens"),
-                "temperature": body.get("temperature"),
-                "top_p": body.get("top_p"),
-                "frequency_penalty": body.get("frequency_penalty"),
-                "logit_bias": body.get("logit_bias"),
-                "logprobs": body.get("logprobs"),
-                "top_logprobs": body.get("top_logprobs"),
-                "n": body.get("n"),
-                "presence_penalty": body.get("presence_penalty"),
-                "response_format": body.get("response_format"),
-                "seed": body.get("seed"),
-                "service_tier": body.get("service_tier"),
-                "stop": body.get("stop"),
-                "stream": body.get("stream"),
-                "stream_options": body.get("stream_options"),
-                "tools": body.get("tools"),
-                "tool_choice": body.get("tool_choice"),
-                "parallel_tool_calls": body.get("parallel_tool_calls"),
-                "user": rnd(),
-            }.items() if value is not None
-        }
-
-        if body.get("stream"):
-            async def event_generator():
-                async for event in streamChat(params):
-                    yield json.dumps(event)
-            return EventSourceResponse(event_generator())
-        else:
-            try:
-                response = requests.post(f"{base_url}/chat/completions", headers={"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}, json=params)
-                response.raise_for_status()
-            except requests.exceptions.RequestException:
-                try:
-                    response = requests.post("https://api.openai.com/v1/chat/completions", headers={"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}, json=params)
-                    response.raise_for_status()
-                except requests.exceptions.RequestException as e:
-                    return JSONResponse(content={"error": { "code": "SERVER_ERROR", "message": str(e)}}, status_code=400)
-            completion = response.json()
-            return JSONResponse(content=completion)
-    except Exception as e:
-        return JSONResponse(content={"error": { "code": "SERVER_ERROR", "message": str(e)}}, status_code=400)
-
-
 app = gr.mount_gradio_app(app, demo, path="/")
 
 class ArgParser(argparse.ArgumentParser):