From fd2ff358bf664d12bdeb960ff10274e3562e9afd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jos=C3=A9=20Carlos?= Date: Sat, 6 Dec 2025 09:50:12 -0300 Subject: [PATCH] fix(prompt): use language parameter in keywords_extraction prompt The language parameter was being passed to the prompt but was not being used. Added {language} placeholder to ensure keywords are extracted in the configured language. --- lightrag/prompt.py | 1 + 1 file changed, 1 insertion(+) diff --git a/lightrag/prompt.py b/lightrag/prompt.py index bf514fe8..64e105c2 100644 --- a/lightrag/prompt.py +++ b/lightrag/prompt.py @@ -374,6 +374,7 @@ Given a user query, your task is to extract two distinct types of keywords: 2. **Source of Truth**: All keywords must be explicitly derived from the user query, with both high-level and low-level keyword categories are required to contain content. 3. **Concise & Meaningful**: Keywords should be concise words or meaningful phrases. Prioritize multi-word phrases when they represent a single concept. For example, from "latest financial report of Apple Inc.", you should extract "latest financial report" and "Apple Inc." rather than "latest", "financial", "report", and "Apple". 4. **Handle Edge Cases**: For queries that are too simple, vague, or nonsensical (e.g., "hello", "ok", "asdfghjkl"), you must return a JSON object with empty lists for both keyword types. +5. **Language**: All extracted keywords MUST be in {language}. Proper nouns (e.g., personal names, place names, organization names) should be kept in their original language. ---Examples--- {examples}