yujunjun/LightRAG
1
0
Fork 0
mirror of https://github.com/HKUDS/LightRAG.git synced 2025-11-30 17:06:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix: Improve keyword extraction prompt for robust JSON output.

Browse Source 
*   Emphasize strict JSON output in key extration prompt
*   Clean up prompt examples in key extration prompt
*   Log raw LLM response on JSON error
This commit is contained in:
yangdx 2025-07-27 21:10:47 +08:00
parent 3f5ade47cd
commit f2d051eea5
2 changed files with 13 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
lightrag/operate.py
View File

@ -1852,6 +1852,7 @@ async def extract_keywords_only(
keywords_data = json.loads(match.group(0))
except json.JSONDecodeError as e:
logger.error(f"JSON parsing error: {e}")
logger.error(f"LLM respond: {result}")
return [], []
hl_keywords = keywords_data.get("high_level_keywords", [])

21
lightrag/prompt.py
View File

@ -251,7 +251,7 @@ Given the query and conversation history, list both high-level and low-level key
######################
{examples}
#############################
######################
---Real Data---
######################
Conversation History:
@ -259,42 +259,45 @@ Conversation History:
Current Query: {query}
######################
The `Output` should be human text, not unicode characters. Keep the same language as `Query`.
Output:
The `Output` should be in JSON format, with no other text before and after the JSON. Use the same language as `Current Query`.
Output:
"""
PROMPTS["keywords_extraction_examples"] = [
"""Example 1:
Query: "How does international trade influence global economic stability?"
################
Output:
{
"high_level_keywords": ["International trade", "Global economic stability", "Economic impact"],
"low_level_keywords": ["Trade agreements", "Tariffs", "Currency exchange", "Imports", "Exports"]
}
#############################""",
""",
"""Example 2:
Query: "What are the environmental consequences of deforestation on biodiversity?"
################
Output:
{
"high_level_keywords": ["Environmental consequences", "Deforestation", "Biodiversity loss"],
"low_level_keywords": ["Species extinction", "Habitat destruction", "Carbon emissions", "Rainforest", "Ecosystem"]
}
#############################""",
""",
"""Example 3:
Query: "What is the role of education in reducing poverty?"
################
Output:
{
"high_level_keywords": ["Education", "Poverty reduction", "Socioeconomic development"],
"low_level_keywords": ["School access", "Literacy rates", "Job training", "Income inequality"]
}
#############################""",
""",
]
PROMPTS["naive_rag_response"] = """---Role---