gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

force keywords_extraction output as JSON

Browse Source
This commit is contained in:
Zhenya Zhu
2025-03-11 11:54:30 +08:00
committed by GitHub
parent 8317ec9757
commit 37754f14b5
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
lightrag/prompt.py
View File

@@ -236,7 +236,7 @@ Given the query and conversation history, list both high-level and low-level key
---Instructions--- ---Instructions---
- Consider both the current query and relevant conversation history when extracting keywords - Consider both the current query and relevant conversation history when extracting keywords
- Output the keywords in JSON format - Output the keywords in JSON format, it will be parsed by a JSON parser, do not add any extra content in output
- The JSON should have two keys: - The JSON should have two keys:
- "high_level_keywords" for overarching concepts or themes - "high_level_keywords" for overarching concepts or themes
- "low_level_keywords" for specific entities or details - "low_level_keywords" for specific entities or details