增加超时处理

config.py

@@ -2,3 +2,4 @@ API_KEY = "ollama"
 MODEL = "qwen2.5:32b-instruct-q5_K_M"
 # MODEL = "qwen2.5:7b"
 LLM_BASE_URL = "http://localhost:11434/v1"
+TIMEOUT_SECONDS = 300

entity_extraction_process.py

@@ -30,7 +30,11 @@ class entityExtractionProcess:
 
         response = (
             llm.chat.completions.create(
-                model=config.MODEL, messages=messages, temperature=0, max_tokens=128_000
+                model=config.MODEL,
+                messages=messages,
+                temperature=0,
+                max_tokens=128_000,
+                timeout=config.TIMEOUT_SECONDS,
             )
             .choices[0]
             .message.content

main.py

@@ -20,12 +20,12 @@ DEBUG = False
 
 class Main(QueueProcessor):
     def processor_handle(self, input):
-        print("input:", input)
+        # print("input:", input)
         currentEngineId = input["currentEngineId"]
         inputData = json.loads(input["inputData"])
         match currentEngineId:
             case 3000:  # InfoExtractor 实体信息提取
-                logger.warning(f"get queueing inputData= {inputData}")
+                # logger.warning(f"get queueing inputData= {inputData}")
                 input_text = inputData["text"]
                 result = entityExtractionProcess.entity_extract(input_text)