You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Dify框架报Query or prefix prompt is too long, you can reduce the prefix prompt, or shrink the max token, or switch to a llm with a larger token limit size。
Dify version
0.3.32
Cloud or Self Hosted
Self Hosted (Docker)
Steps to reproduce
Dify框架报Query or prefix prompt is too long, you can reduce the prefix prompt, or shrink the max token, or switch to a llm with a larger token limit size。
后端模型基于Xinference进行本地部署的ChatGLM2,max_tokens 为8192(8K),直接在Xinference输入一段内容2000多字的中文文本,可以正常回答。
基于Dify构建的对话应用,max_tokens 设置为450,输入同一段内容就报上述错误。
✔️ Expected Behavior
正常回复
❌ Actual Behavior
Query or prefix prompt is too long, you can reduce the prefix prompt, or shrink the max token, or switch to a llm with a larger token limit size。
The text was updated successfully, but these errors were encountered: