yangdx b5c230abdd optimize: avoid duplicate embedding calls in _build_query_context ...

Reduces API costs and improves query performance while maintaining backward compatibility.

2025-08-21 16:49:24 +08:00

..

api

Update documentation with LLM selection guidelines and API improvements

2025-08-21 13:59:14 +08:00

kg

Fix logging level usage in Redis retry decorator

2025-08-20 05:21:15 +08:00

llm

feat: Add extra_body parameter support for OpenRouter/vLLM compatibility

2025-08-21 13:06:28 +08:00

tools

…

__init__.py

…

base.py

feat: KG related chunks selection by vector similarity

2025-08-13 18:16:42 +08:00

constants.py

Set default TIMEOUT value to 150, and gunicorn timeout to TIMEOUT+30

2025-08-20 22:04:32 +08:00

exceptions.py

…

lightrag.py

Rename MAX_TOKENS to SUMMARY_MAX_TOKENS for clarity

2025-08-21 10:15:20 +08:00

llm.py

…

namespace.py

Refac: Add workspace infomation to all logger output for all storage type

2025-08-12 01:19:09 +08:00

operate.py

optimize: avoid duplicate embedding calls in _build_query_context

2025-08-21 16:49:24 +08:00

prompt.py

Refactor keyword extraction rules and remove overlap constraint

2025-08-19 15:07:40 +08:00

rerank.py

…

types.py

…

utils_graph.py

…

utils.py

optimize: avoid duplicate embedding calls in _build_query_context

2025-08-21 16:49:24 +08:00