force keywords_extraction output as JSON
Browse files- lightrag/prompt.py +1 -1
lightrag/prompt.py
CHANGED
|
@@ -236,7 +236,7 @@ Given the query and conversation history, list both high-level and low-level key
|
|
| 236 |
---Instructions---
|
| 237 |
|
| 238 |
- Consider both the current query and relevant conversation history when extracting keywords
|
| 239 |
-
- Output the keywords in JSON format
|
| 240 |
- The JSON should have two keys:
|
| 241 |
- "high_level_keywords" for overarching concepts or themes
|
| 242 |
- "low_level_keywords" for specific entities or details
|
|
|
|
| 236 |
---Instructions---
|
| 237 |
|
| 238 |
- Consider both the current query and relevant conversation history when extracting keywords
|
| 239 |
+
- Output the keywords in JSON format, it will be parsed by a JSON parser, do not add any extra content in output
|
| 240 |
- The JSON should have two keys:
|
| 241 |
- "high_level_keywords" for overarching concepts or themes
|
| 242 |
- "low_level_keywords" for specific entities or details
|