Open TTTnlp opened 1 month ago
我都遇到這個問題,我是用ollama 行llama3.1的
我試過定義 role 是 "You are a helpful assistant of company ABC"
接問用local search 問"你是誰" 時, 會直接回答 I'm an artificial intelligence model known as Llama
但縮短了LOCAL_SEARCH_SYSTEM_PROMPT後(例如 直接刪走Data tables) , 他就懂得回答 "I am a helpful assistant of company ABC"
我都嚐試過直接把graphrag的 local search system prompts 抽出來 直接問 llama3.1或gemma2 同樣都會無視了 我定義的role 及不會在DataTables找答案
所以看來是system prompt 太長會 令LLM 無法正常運作
如果你是用Ollama的話可以參考這個方法
我找到原來Ollama限制了tokens長度為2000,可以用Modelfile或經API 設定num_ctx的上限(e.g: 12800),這樣LLM就接收到完整的system prompt了。
Is this happening when running global search? We have checks in place to filter out any community responses that the LLM deems low-relevance, which can sometimes mean no relevant summaries are collected together and the end result is that it can't answer the question. This is a somewhat cautious approach to avoid hallucination. You may be able to get better results if you tune the prompt to your domain for how the LLM assesses relevance and assigns the "Importance Score" here.
This issue has been marked stale due to inactivity after repo maintainer or community member responses that request more information or suggest a solution. It will be closed after five additional days.
Do you need to file an issue?
Describe the bug
当我使用默认的system prompt时,模型总是回答I apologize, but I don't have any information about...,然后当prompt变短时,模型可以正常回答,这是openai的问题吗,还是说在后续的处理中将system prompt截断了?
Steps to reproduce
No response
Expected Behavior
No response
GraphRAG Config Used
Logs and screenshots
No response
Additional Information