增加服务日志

Makefile

@@ -1,6 +1,6 @@
 start:
 	cd server && \
-	gunicorn -w 2 -b 0.0.0.0:18000 -k uvicorn.workers.UvicornWorker server:app --daemon
+	gunicorn -w 1 -b 0.0.0.0:18000 -k uvicorn.workers.UvicornWorker server:app --daemon
 	@sleep 1s
 	@ps -ef | grep gunicorn
 

server/server.py

@@ -2,10 +2,25 @@ from pydantic import BaseModel, field_validator, model_validator, Field
 from typing import List, Optional, Generic, TypeVar
 from fastapi import FastAPI
 import uvicorn
+import logging
+
 
 from qwenvl import model
 from qwenvl import processor
-from qwen_vl_utils import process_vision_info
+# from qwen_vl_utils import process_vision_info
+
+logger = logging.getLogger()
+logger.setLevel(logging.INFO)
+handler1 = logging.StreamHandler()
+handler2 = logging.FileHandler(filename='../log/llmserver.log')
+formatter = logging.Formatter(
+    "%(asctime)s - %(module)s - %(funcName)s - line:%(lineno)d - %(levelname)s - %(message)s"
+)
+handler1.setFormatter(formatter)
+handler2.setFormatter(formatter)
+logger.addHandler(handler1)  # 将日志输出至屏幕
+logger.addHandler(handler2)  # 将日志输出至文件
+
 
 app = FastAPI()
 
@@ -46,32 +61,33 @@ async def detect(item: APIRequest):
             ],
         }
     ]
-    text = processor.apply_chat_template(
-        messages, tokenize=False, add_generation_prompt=True
-    )
-    image_inputs, video_inputs = process_vision_info(messages)
-    inputs = processor(
-        text=[text],
-        images=image_inputs,
-        videos=video_inputs,
-        padding=True,
-        return_tensors="pt",
-    )
-    inputs = inputs.to("cuda")
+    # text = processor.apply_chat_template(
+    #     messages, tokenize=False, add_generation_prompt=True
+    # )
+    # image_inputs, video_inputs = process_vision_info(messages)
+    # inputs = processor(
+    #     text=[text],
+    #     images=image_inputs,
+    #     videos=video_inputs,
+    #     padding=True,
+    #     return_tensors="pt",
+    # )
+    # inputs = inputs.to("cuda")
 
-    # Inference: Generation of the output
-    generated_ids = model.generate(**inputs, max_new_tokens=128)
-    generated_ids_trimmed = [
-        out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
-    ]
-    output_text = processor.batch_decode(
-        generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
-    )
-    print(output_text)
-    # 大模型检测后如果有违章
-    # response["data"]["illegal"] = 1
-    
+    # # Inference: Generation of the output
+    # generated_ids = model.generate(**inputs, max_new_tokens=128)
+    # generated_ids_trimmed = [
+    #     out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+    # ]
+    # output_text = processor.batch_decode(
+    #     generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+    # )
+    # print(output_text)
+    # # 大模型检测后如果有违章
+    # # response["data"]["illegal"] = 1
+    # if "yes" in output_text[0].lower():
+    #     response["data"]["illegal"] = 1
     return response
 
 if __name__ == "__main__":
-    uvicorn.run('server:app', host="0.0.0.0", port=18000)
+    uvicorn.run('server:app', host="0.0.0.0", port=18000)