CREDO23 8d413ea5c2 refactor(indexing): expose chunk_markdown and embed_batch helpers ... Split _compute so the incremental edit path can reuse the exact same chunker selection and embedding entry points (and their test patch targets) without going through the doc-level cache.		2026-06-12 18:52:57 +02:00
..
adapters	feat(backend): Remove LLM summaries from document indexing	2026-06-04 00:50:19 +05:30
cache	refactor(indexing): expose chunk_markdown and embed_batch helpers	2026-06-12 18:52:57 +02:00
__init__.py	test: add ConnectorDocument unit tests and factory fixture	2026-02-24 22:20:08 +02:00
chunk_reconciler.py	feat(indexing): add pure chunk reconciler for content-addressed diffs	2026-06-12 18:52:46 +02:00
connector_document.py	feat(backend): Remove LLM summaries from document indexing	2026-06-04 00:50:19 +05:30
document_chunker.py	feat(chunker): add table-aware chunk_text_hybrid to prevent mid-row table splits	2026-05-05 12:48:04 +08:00
document_embedder.py	feat: re-export embed_texts from document_embedder	2026-03-09 15:54:02 +02:00
document_hashing.py	feat: made agent file sytem optimized	2026-03-28 16:39:46 -07:00
document_persistence.py	fix(indexing): log and recover session in rollback_and_persist_failure	2026-06-10 00:10:25 +02:00
exceptions.py	style: simplify LLM model terminology in UI	2026-04-02 10:11:35 +05:30
indexing_pipeline_service.py	feat(index-cache): serve chunk embeddings from cache during indexing	2026-06-12 16:48:18 +02:00
pipeline_logger.py	feat: enhance performance logging and caching in various components	2026-02-26 13:00:31 -08:00