From 75beaf249ec852cd3b91b57ed55066b44d16735f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81kos=20Luk=C3=A1cs?= Date: Tue, 22 Jul 2025 20:40:46 +0200 Subject: [PATCH] Better prompt for entity description extraction to avoid hallucinations --- lightrag/prompt.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lightrag/prompt.py b/lightrag/prompt.py index 656801c0..1b106590 100644 --- a/lightrag/prompt.py +++ b/lightrag/prompt.py @@ -21,7 +21,7 @@ Use {language} as output language. 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_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}{tuple_delimiter}{tuple_delimiter}) 2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other.