gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Optimize prompt template for naive query

Browse Source
This commit is contained in:
yangdx
2025-05-07 18:11:12 +08:00
parent 3eb3b170ab
commit 1c5bbe396a
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
lightrag/prompt.py
View File

@@ -311,7 +311,7 @@ When handling content with timestamps:
---Conversation History--- ---Conversation History---
{history} {history}
---Document Chunks--- ---Document Chunks(DC)---
{content_data} {content_data}
---Response Rules--- ---Response Rules---
@@ -320,7 +320,7 @@ When handling content with timestamps:
- Use markdown formatting with appropriate section headings - Use markdown formatting with appropriate section headings
- Please respond in the same language as the user's question. - Please respond in the same language as the user's question.
- Ensure the response maintains continuity with the conversation history. - Ensure the response maintains continuity with the conversation history.
- List up to 5 most important reference sources at the end under "References" section. Clearly indicating whether each source is from Knowledge Graph (KG) or Vector Data (DC), and include the file path if available, in the following format: [KG/DC] file_path - List up to 5 most important reference sources at the end under "References" section. Clearly indicating each source from Document Chunks(DC), and include the file path if available, in the following format: [DC] file_path
- If you don't know the answer, just say so. - If you don't know the answer, just say so.
- Do not include information not provided by the Document Chunks.""" - Do not include information not provided by the Document Chunks."""