Update app.py

app.py

@@ -53,93 +53,94 @@ def index():
 @app.route('/v1/chat/completions', methods=['POST'])
 @requires_api_key
 def chat_completions(api_key):
-    logging.info("Received request for chat completions")
-    print("requess received")
-    try:
-        logging.info("Received request for chat completions")
-        # Parse and validate request data
-        try:
-            data = request.get_json()
-            chat_request = ChatCompletionRequest(**data)
-        except ValidationError as e:
-            return jsonify({'detail': e.errors()}), 400
-
-        # Check API key validity and rate limit
-        is_valid, error_message = check_api_key_validity(api_key)
-        if not is_valid:
-            return jsonify({'detail': error_message}), 401
-
-        messages = [{"role": msg.role, "content": msg.content} for msg in chat_request.messages]
-
-        # Get model info
-        model_info = get_model_info(chat_request.model)
-        if not model_info:
-            return jsonify({'detail': 'Invalid model specified'}), 400
-
-        # Model mapping
-        model_mapping = {
-            "meta-llama-405b-turbo": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
-            "claude-3.5-sonnet": "claude-3-sonnet-20240229",
-        }
-        model_name = model_mapping.get(chat_request.model, chat_request.model)
-        credits_reduction = {
-            "gpt-4o": 1,
-            "claude-3-sonnet-20240229": 1,
-            "gemini-1.5-pro": 1,
-            "gemini-1-5-flash": 1,
-            "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": 1,
-            "o1-mini": 2,
-            "o1-preview": 3,
-        }.get(model_name, 0)
-
-        if chat_request.stream:
-            def generate():
-                try:
-                    for chunk in API_Inference(messages, model=model_name, stream=True,
-                                               max_tokens=chat_request.max_tokens,
-                                               temperature=chat_request.temperature,
-                                               top_p=chat_request.top_p):
-                        data = json.dumps({'choices': [{'delta': {'content': chunk}}]})
-                        yield f"data: {data}\n\n"
-                    yield f"data: [DONE]\n\nCredits used: {credits_reduction}\n\n"
-                    update_request_count(api_key, credits_reduction)
-                except Exception as e:
-                    yield f"data: [ERROR] {str(e)}\n\n"
-
-            return Response(generate(), mimetype='text/event-stream')
-        else:
-            response = API_Inference(messages, model=model_name, stream=False,
-                                     max_tokens=chat_request.max_tokens,
-                                     temperature=chat_request.temperature,
-                                     top_p=chat_request.top_p)
-            update_request_count(api_key, credits_reduction)
-            prompt_tokens = sum(len(msg['content'].split()) for msg in messages)
-            completion_tokens = len(response.split())
-            total_tokens = prompt_tokens + completion_tokens
-            return jsonify({
-                "id": f"chatcmpl-{str(uuid.uuid4())}",
-                "object": "chat.completion",
-                "created": int(uuid.uuid1().time // 1e7),
-                "model": model_name,
-                "choices": [
-                    {
-                        "index": 0,
-                        "message": {
-                            "role": "assistant",
-                            "content": response
-                        },
-                        "finish_reason": "stop"
-                    }
-                ],
-                "usage": {
-                    "prompt_tokens": prompt_tokens,
-                    "completion_tokens": completion_tokens,
-                    "total_tokens": total_tokens
-                },
-                "credits_used": credits_reduction
-            })
-    except Exception as e:
-        return jsonify({'detail': str(e)}), 500
+    return jsonify({'detail': "YOUUUUUUUUUU"), 500
+    # logging.info("Received request for chat completions")
+    # print("requess received")
+    # try:
+    #     logging.info("Received request for chat completions")
+    #     # Parse and validate request data
+    #     try:
+    #         data = request.get_json()
+    #         chat_request = ChatCompletionRequest(**data)
+    #     except ValidationError as e:
+    #         return jsonify({'detail': e.errors()}), 400
+
+    #     # Check API key validity and rate limit
+    #     is_valid, error_message = check_api_key_validity(api_key)
+    #     if not is_valid:
+    #         return jsonify({'detail': error_message}), 401
+
+    #     messages = [{"role": msg.role, "content": msg.content} for msg in chat_request.messages]
+
+    #     # Get model info
+    #     model_info = get_model_info(chat_request.model)
+    #     if not model_info:
+    #         return jsonify({'detail': 'Invalid model specified'}), 400
+
+    #     # Model mapping
+    #     model_mapping = {
+    #         "meta-llama-405b-turbo": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
+    #         "claude-3.5-sonnet": "claude-3-sonnet-20240229",
+    #     }
+    #     model_name = model_mapping.get(chat_request.model, chat_request.model)
+    #     credits_reduction = {
+    #         "gpt-4o": 1,
+    #         "claude-3-sonnet-20240229": 1,
+    #         "gemini-1.5-pro": 1,
+    #         "gemini-1-5-flash": 1,
+    #         "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": 1,
+    #         "o1-mini": 2,
+    #         "o1-preview": 3,
+    #     }.get(model_name, 0)
+
+    #     if chat_request.stream:
+    #         def generate():
+    #             try:
+    #                 for chunk in API_Inference(messages, model=model_name, stream=True,
+    #                                            max_tokens=chat_request.max_tokens,
+    #                                            temperature=chat_request.temperature,
+    #                                            top_p=chat_request.top_p):
+    #                     data = json.dumps({'choices': [{'delta': {'content': chunk}}]})
+    #                     yield f"data: {data}\n\n"
+    #                 yield f"data: [DONE]\n\nCredits used: {credits_reduction}\n\n"
+    #                 update_request_count(api_key, credits_reduction)
+    #             except Exception as e:
+    #                 yield f"data: [ERROR] {str(e)}\n\n"
+
+    #         return Response(generate(), mimetype='text/event-stream')
+    #     else:
+    #         response = API_Inference(messages, model=model_name, stream=False,
+    #                                  max_tokens=chat_request.max_tokens,
+    #                                  temperature=chat_request.temperature,
+    #                                  top_p=chat_request.top_p)
+    #         update_request_count(api_key, credits_reduction)
+    #         prompt_tokens = sum(len(msg['content'].split()) for msg in messages)
+    #         completion_tokens = len(response.split())
+    #         total_tokens = prompt_tokens + completion_tokens
+    #         return jsonify({
+    #             "id": f"chatcmpl-{str(uuid.uuid4())}",
+    #             "object": "chat.completion",
+    #             "created": int(uuid.uuid1().time // 1e7),
+    #             "model": model_name,
+    #             "choices": [
+    #                 {
+    #                     "index": 0,
+    #                     "message": {
+    #                         "role": "assistant",
+    #                         "content": response
+    #                     },
+    #                     "finish_reason": "stop"
+    #                 }
+    #             ],
+    #             "usage": {
+    #                 "prompt_tokens": prompt_tokens,
+    #                 "completion_tokens": completion_tokens,
+    #                 "total_tokens": total_tokens
+    #             },
+    #             "credits_used": credits_reduction
+    #         })
+    # except Exception as e:
+    #     return jsonify({'detail': str(e)}), 500
 
 @app.route('/rate_limit/status', methods=['GET'])
 @requires_api_key