CREDO23 f82dedf712 feat(indexing): add pure chunk reconciler for content-addressed diffs ... Greedy multiset match on chunk text decides which rows keep their embeddings, which texts need embedding, and which rows are deleted. No DB, no embeddings; fully unit-tested (reuse, head insert, middle edit, deletion, duplicates, reorder, full rewrite).		2026-06-12 18:52:46 +02:00
..
cache	refactor(embedding-cache): rename index cache to embedding cache	2026-06-12 17:00:01 +02:00
__init__.py	test: bootstrap pytest environment for backend	2026-02-24 18:19:56 +02:00
conftest.py	feat: enhance performance logging and caching in various components	2026-02-26 13:00:31 -08:00
test_chunk_reconciler.py	feat(indexing): add pure chunk reconciler for content-addressed diffs	2026-06-12 18:52:46 +02:00
test_connector_document.py	feat(tests): Update tests for summary-free indexing	2026-06-04 00:53:51 +05:30
test_create_placeholder_documents.py	feat: made agent file sytem optimized	2026-03-28 16:39:46 -07:00
test_document_chunker.py	add docstrings to all indexing pipeline tests	2026-02-25 20:30:31 +02:00
test_document_hashing.py	feat: enhance Google connectors indexing with content extraction and document migration	2026-03-25 18:33:44 +05:30
test_index_batch.py	refactor(tests): Update tests to remove summary references and adjust for embedding errors	2026-06-04 01:51:21 +05:30
test_index_batch_parallel.py	test(index-cache): add unit tests and repoint embed/chunk patch targets	2026-06-12 16:48:18 +02:00
test_migrate_legacy_docs.py	feat: add integration tests for indexing pipeline components	2026-03-25 18:34:02 +05:30
test_prepare_placeholder_dedup.py	feat: made agent file sytem optimized	2026-03-28 16:39:46 -07:00