7 Commits

Author SHA1 Message Date
yangdx
32af45ff46 refactor: improve JSON parsing reliability with json-repair library
Replace regex-based JSON extraction with json-repair for better handling of malformed LLM responses. Remove deprecated JSON parsing utilities and clean up keyword_extraction parameter across LLM providers.

- Remove locate_json_string_body_from_string() and convert_response_to_json()
- Use json-repair.loads() in extract_keywords_only() for robust parsing
- Clean up LLM interfaces and remove unused parameters
- Add json-repair dependency
2025-08-01 19:36:20 +08:00
yangdx
ac2b6af97e Eliminate tenacity from dynamic import 2025-05-14 10:57:05 +08:00
Mario Vignieri
f33bcbb32c fix hf_embed torch device use MPS or CPU when CUDA is not available -macos users 2025-03-20 09:40:56 +01:00
Konrad Wojciechowski
4f76b1c23e fix AttributeError: 'NoneType' object has no attribute 'dim' 2025-02-24 10:28:15 +01:00
Yannick Stephan
ea41d08b9f removed torch from requirement lightrag server 2025-02-18 20:05:51 +01:00
Saifeddine ALOUI
06c9e4e454 Fixed missing imports bug and fixed linting 2025-01-25 00:55:07 +01:00
Saifeddine ALOUI
34018cb1e0 Separated llms from the main llm.py file and fixed some deprication bugs 2025-01-25 00:11:00 +01:00