Feat: Add knowledge compilation workflows (#16515)

## Summary
- Add knowledge compilation template APIs, services, and builtin
template seed data
- Add advanced knowledge compile structure/artifact/RAPTOR workflow
support
- Update parsing, dataset/document APIs, and supporting services for
compilation workflows
This commit is contained in:
Kevin Hu
2026-07-02 23:22:07 +08:00
committed by GitHub
parent 7d64a78f83
commit 62f94cd59b
57 changed files with 14587 additions and 3094 deletions

View File

@@ -40,5 +40,37 @@
"toc_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"raptor_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"raptor_layer_int": {"type": "integer", "default": 0},
"extra": {"type": "varchar", "default": ""}
"extra": {"type": "varchar", "default": ""},
"compile_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"source_chunk_ids": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"source_doc_ids": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"compilation_template_ids": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"compilation_template_kind_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"chunk_hash_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"input_hash_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"artifact_slug_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"md_with_weight": {"type": "varchar", "default": ""},
"summary_with_weight": {"type": "varchar", "default": ""},
"skill_with_weight": {"type": "varchar", "default": ""},
"skill_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"children_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"doc_ids_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"slug_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"title_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"page_type_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"entity_names_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"outlinks_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"related_kb_pages_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"type_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"from_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"to_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"rechunk_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"rechunked_from_template_id": {"type": "varchar", "default": ""},
"rechunked_from_chunk_ids": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
"superseded_by_chunk_id": {"type": "varchar", "default": ""},
"doc_count_int": {"type": "integer", "default": 0},
"depth_int": {"type": "integer", "default": 0},
"outlinks_int": {"type": "integer", "default": 0},
"token_num": {"type": "integer", "default": 0}
}