ragflow/graphrag/general
f0 fb1bedbd3c
fix(_handle_entity_relation_summary): correctly calculate the descriptions_list (#10534)
### What problem does this PR solve?

Since `description_list` was a tuple containing a single element (which
was the actual list of descriptions), `len(description_list)` was always
**1**.

The subsequent check:
`if len(description_list) <= 12:` always evaluated to `True` (since $1
\le 12$), even if the inner list contained more than 12 descriptions.
This prevented the necessary summarization logic from running for long
lists.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-10-15 15:30:06 +08:00
..
__init__.py Light GraphRAG (#4585) 2025-01-22 19:43:14 +08:00
community_report_prompt.py Optimize graphrag again (#6513) 2025-03-26 15:34:42 +08:00
community_reports_extractor.py Fix: meta data filter with AND logic operations. (#9687) 2025-08-25 18:29:24 +08:00
entity_embedding.py code cleans. (#9916) 2025-09-05 09:59:27 +08:00
extractor.py fix(_handle_entity_relation_summary): correctly calculate the descriptions_list (#10534) 2025-10-15 15:30:06 +08:00
graph_extractor.py Refa: remove temperature since some LLMs fail to support. (#8981) 2025-07-23 10:17:04 +08:00
graph_prompt.py perf: Optimize GraphRAG’s LOOP_PROMPT (#7356) 2025-04-28 13:31:04 +08:00
index.py Fix typos: retrievaler -> retriever (#10372) 2025-10-10 09:17:36 +08:00
leiden.py Optimize graphrag again (#6513) 2025-03-26 15:34:42 +08:00
mind_map_extractor.py Refa: remove temperature since some LLMs fail to support. (#8981) 2025-07-23 10:17:04 +08:00
mind_map_prompt.py Light GraphRAG (#4585) 2025-01-22 19:43:14 +08:00
smoke.py Fix typos: retrievaler -> retriever (#10372) 2025-10-10 09:17:36 +08:00