Skip to content

armgit / storm

Public Imported from GitHub
0

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

update storm question answering module to be more compatible with additional lm

Yucheng-Jiangbb9c89136c28
diff --git a/knowledge_storm/storm_wiki/modules/knowledge_curation.py b/knowledge_storm/storm_wiki/modules/knowledge_curation.py
index ca6377d..d6b8929 100644
--- a/knowledge_storm/storm_wiki/modules/knowledge_curation.py
+++ b/knowledge_storm/storm_wiki/modules/knowledge_curation.py
@@ -166,7 +166,7 @@ class QuestionToQuery(dspy.Signature):
class AnswerQuestion(dspy.Signature):
"""You are an expert who can use information effectively. You are chatting with a Wikipedia writer who wants to write a Wikipedia page on topic you know. You have gathered the related information and will now use the information to form a response.
- Make your response as informative as possible and make sure every sentence is supported by the gathered information. If [Gathered information] is not related to he [Topic] and [Question], output "Sorry, I don't have enough information to answer the question.".
+ Make your response as informative as possible, ensuring that every sentence is supported by the gathered information. If the [gathered information] is not directly related to the [topic] or [question], provide the most relevant answer based on the available information. If no appropriate answer can be formulated, respond with, “I cannot answer this question based on the available information,” and explain any limitations or gaps.
"""
topic = dspy.InputField(prefix="Topic you are discussing about:", format=str)