gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Unify entity extraction prompt between passes

Browse source 
- Disallow hallucinated info in descriptions
- Align reminder steps with main extraction
This commit is contained in:
yangdx 2025-07-27 23:06:55 +08:00
parent 4eef9f3778
commit 9c4e98ec3b
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
lightrag/prompt.py
View file

@ -19,7 +19,7 @@ Use {language} as output language.
---Steps--- ---Steps---
1. Identify all entities. For each identified entity, extract the following information: 1. Identify all entities. For each identified entity, extract the following information:
- entity_name: Name of the entity, use same language as input text. If English, capitalized the name. - entity_name: Name of the entity, use same language as input text. If English, capitalized the name
- entity_type: One of the following types: [{entity_types}] - entity_type: One of the following types: [{entity_types}]
- entity_description: Provide a comprehensive description of the entity's attributes and activities *based solely on the information present in the input text*. **Do not infer or hallucinate information not explicitly stated.** If the text provides insufficient information to create a comprehensive description, state "Description not available in text." - entity_description: Provide a comprehensive description of the entity's attributes and activities *based solely on the information present in the input text*. **Do not infer or hallucinate information not explicitly stated.** If the text provides insufficient information to create a comprehensive description, state "Description not available in text."
Format each entity as ("entity"{tuple_delimiter}<entity_name>{tuple_delimiter}<entity_type>{tuple_delimiter}<entity_description>) Format each entity as ("entity"{tuple_delimiter}<entity_name>{tuple_delimiter}<entity_type>{tuple_delimiter}<entity_description>)
@ -156,9 +156,9 @@ MANY entities and relationships were missed in the last extraction. Please find
---Remember Steps--- ---Remember Steps---
1. Identify all entities. For each identified entity, extract the following information: 1. Identify all entities. For each identified entity, extract the following information:
- entity_name: Name of the entity, use same language as input text. If English, capitalized the name. - entity_name: Name of the entity, use same language as input text. If English, capitalized the name
- entity_type: One of the following types: [{entity_types}] - entity_type: One of the following types: [{entity_types}]
- entity_description: Comprehensive description of the entity's attributes and activities - entity_description: Provide a comprehensive description of the entity's attributes and activities *based solely on the information present in the input text*. **Do not infer or hallucinate information not explicitly stated.** If the text provides insufficient information to create a comprehensive description, state "Description not available in text."
Format each entity as ("entity"{tuple_delimiter}<entity_name>{tuple_delimiter}<entity_type>{tuple_delimiter}<entity_description>) Format each entity as ("entity"{tuple_delimiter}<entity_name>{tuple_delimiter}<entity_type>{tuple_delimiter}<entity_description>)
2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other. 2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other.