Optimize graphrag again (#6513)

### What problem does this PR solve?

Removed set_entity and set_relation to avoid accessing doc engine during
graph computation.
Introduced GraphChange to avoid writing unchanged chunks.

### Type of change

- [x] Performance Improvement
This commit is contained in:
Zhichang Yu
2025-03-26 15:34:42 +08:00
committed by GitHub
parent 7a677cb095
commit 6bf26e2a81
19 changed files with 466 additions and 530 deletions

View File

@ -8,7 +8,7 @@
"docnm_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace"},
"title_tks": {"type": "varchar", "default": "", "analyzer": "whitespace"},
"title_sm_tks": {"type": "varchar", "default": "", "analyzer": "whitespace"},
"name_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace"},
"name_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"important_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"tag_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"important_tks": {"type": "varchar", "default": "", "analyzer": "whitespace"},
@ -27,16 +27,16 @@
"rank_int": {"type": "integer", "default": 0},
"rank_flt": {"type": "float", "default": 0},
"available_int": {"type": "integer", "default": 1},
"knowledge_graph_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace"},
"knowledge_graph_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"entities_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"pagerank_fea": {"type": "integer", "default": 0},
"tag_feas": {"type": "varchar", "default": ""},
"from_entity_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace"},
"to_entity_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace"},
"entity_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace"},
"entity_type_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace"},
"source_id": {"type": "varchar", "default": ""},
"from_entity_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"to_entity_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"entity_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"entity_type_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"source_id": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"n_hop_with_weight": {"type": "varchar", "default": ""},
"removed_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace"}
"removed_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"}
}