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

Improve entity extraction prompt clarity and make sure LLM output content only

Browse source
This commit is contained in:
yangdx 2025-09-14 17:50:56 +08:00
parent 4dafec8884
commit 92f8fc6fbf
1 changed files with 11 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
lightrag/prompt.py
View file

@ -74,23 +74,24 @@ PROMPTS["entity_extraction_user_prompt"] = """---Task---
Extract entities and relationships from the input text to be processed.
---Instructions---
1. Adhere strictly to the format requirements for entity and relationship lists as specified in the system prompts.
2. Output `{completion_delimiter}` only after all relevant entities and relationships have been extracted.
3. Ensure the output language is {language}. Proper nouns (e.g., personal names, place names, organization names) must be kept in their original language and not translated.
1. **Strict Adherence to Format:** Strictly adhere to all format requirements for entity and relationship lists, including output order, field delimiters, and proper noun handling, as specified in the system prompt.
2. **Output Content Only:** Output *only* the extracted list of entities and relationships. Do not include any introductory or concluding remarks, explanations, or additional text before or after the list.
3. **Completion Signal:** Output `{completion_delimiter}` as the final line after all relevant entities and relationships have been extracted and presented.
<Output>
"""
PROMPTS["entity_continue_extraction_user_prompt"] = """---Task---
Identify any missed entities or relationships from the input text to be processed based on the last extraction task.
Based on the last extraction task, identify and extract any **missed or incorrectly formatted** entities and relationships from the input text.
---Instructions---
1. Adhere strictly to the format requirements for entity and relationship lists as specified in the system prompts.
2. Do not include entities and relationships that were correctly extracted in the last extraction task.
3. If an entity or relationship output was truncated or had missing fields in the last extraction task, please re-output it in the correct format.
4. Output each entity and relationship on a single line; use `{tuple_delimiter}` as the field separator within each extracted item.
5. Output `{completion_delimiter}` only after all relevant entities and relationships have been extracted.
6. Ensure the output language is {language}. Proper nouns (e.g., personal names, place names, organization names) may in their original language if proper translation is not available.
1. **Strict Adherence to System Format:** Strictly adhere to all format requirements for entity and relationship lists, including output order, field delimiters, and proper noun handling, as specified in the system instructions.
2. **Focus on Corrections/Additions:**
* **Do NOT** re-output entities and relationships that were **correctly and fully** extracted in the last task.
* If an entity or relationship was **missed** in the last task, extract and output it now according to the system format.
* If an entity or relationship was **truncated, had missing fields, or was otherwise incorrectly formatted** in the last task, re-output the *corrected and complete* version in the specified format.
3. **Output Content Only:** Output *only* the extracted list of entities and relationships. Do not include any introductory or concluding remarks, explanations, or additional text before or after the list.
4. **Completion Signal:** Output `{completion_delimiter}` as the final line after all relevant missing or corrected entities and relationships have been extracted and presented.
<Output>
"""