知识库retrival使用glm-4-plus,并且设置max_tokens=4095

app/services/zhipu_kb_service.py

@@ -7,7 +7,7 @@ logger = logging.getLogger(__name__)
 
 class ZhipuKbService:
     def __init__(self):
-        self.model_name = "glm-4"
+        self.model_name = "glm-4-plus"
         self.app_secret_key = "d54f764a1d67c17d857bd3983b772016.GRjowY0fyiMNurLc"
         logger.info("ZhipuKbService initialized with model: %s", self.model_name)
 
@@ -22,7 +22,7 @@ class ZhipuKbService:
             prompt_template = default_prompt
         try:
             response = client.chat.completions.create(
-                model="glm-4",
+                model=self.model_name,
                 messages=[
                     {"role": "user", "content": message},
                 ],
@@ -36,8 +36,9 @@ class ZhipuKbService:
                     }
                 ],
                 stream=False,
-                temperature=0.01,
-                top_p=0.1,
+                max_tokens=4095,
+                temperature=0.01,  # default=0.01
+                top_p=0.1, #default=0.1
             )
             result = response.choices[0].message.content
             end_time = time.time()
@@ -59,7 +60,7 @@ class ZhipuKbService:
             prompt_template = default_prompt
         try:
             response = client.chat.completions.create(
-                model="glm-4",
+                model=self.model_name,
                 messages=messages,
                 tools=[
                     {
@@ -71,8 +72,9 @@ class ZhipuKbService:
                     }
                 ],
                 stream=True,
-                temperature=0.01,
-                top_p=0.1,
+                max_tokens=4095,
+                temperature=0.01,  # default=0.01
+                top_p=0.1, #default=0.1
             )
             for chunk in response:
                 yield chunk.choices[0].delta.content