- Add support for metadata that contains lists of supported types (#2877)
- Simplify pydoc configs (#2855)
- Replacing each
DocumentStorespecific tests and used the generalised ones fromhaystack.testing.document_store(#2812) - Chroma - remove tests for invalid Settings (now ignored) (#2935)
- Remove unused allow-direct-references (#2866)
- Standardize author mentions (#2897)
- Fixing curly brackets (#2824)
- Add metadata query operations to ChromaDocumentStore (#2819)
- Add
client_settingstoChromaDocumentStore(#2651)
- Fix: doc links (#2662)
- Make fmt command more forgiving (#2671)
- [breaking] Chroma - drop Python 3.9 and use X|Y typing (#2701)
- Fix: Fix doc links (#2661)
- Adding
delete_by_filter()andupdate_by_filter()toChromaDocumentStore(#2649)
- Change pytest command (#2475)
- Remove Readme API CI workflow and configs (#2573)
- Adopt PEP 585 type hinting (part 1) (#2509)
- Adding delete_all_docs to ChromaDB document store (#2399)
- Add pydoc configurations for Docusaurus (#2411)
- Install dependencies in the
testenvironment when testing with lowest direct dependencies and Haystack main (#2418)
- Update md files for new hatch scripts (#1911)
- Remove black (#1985)
- Standardize readmes - part 1 (#2202)
- Chroma - fix typing + ship types by adding py.typed files (#1910)
- Add async support for Chroma + improve typing (#1697)
- Align core-integrations Hatch scripts (#1898)
- Update test and unpin chroma (#1618)
- Make chroma backwards compatible (#1619)
- Review testing workflows (#1541)
- Fix: Pin chroma (#1608)
- Use Haystack logging across integrations (#1484)
- Fix: Chroma - relax dataframe/blob test (#1404)
- Pin haystack and remove dataframe checks (#1501)
- Better handle discarded fields (#1373)
- Inherit from
FilterDocumentsTestWithDataframein Document Stores (#1290)
- Fix: Chroma - make
filter_documentsmethod return embeddings (#1361)
- Fix linting/isort (#1215)
- Chroma - pin
tokenizers(#1223)
- Unpin tokenizers (#1233)
- Fix: updates for Chroma 0.6.0 (#1270)
- Fixing Chroma tests due
chromadbupdate behaviour change (#1148) - Adapt our implementation to breaking changes in Chroma 0.5.17 (#1165)
- Adopt uv as installer (#1142)
- Empty filters should behave as no filters (#1117)
- Chroma - allow remote HTTP connection (#1094)
- Chroma - defer the DB connection (#1107)
- Refactor: fix chroma linting; do not use numpy (#1063)
- Filters in chroma integration (#1072)
- Do not retry tests in
hatch run testcommand (#954)
- Chroma - ruff update, don't ruff tests (#983)
- Update ruff linting scripts and settings (#1105)
- Chore: ChromaDocumentStore lint fix (#1065)
ChromaDocumentStore- discardmetaitems when the type of their value is not supported in Chroma (#907)
- Add metadata parameter to ChromaDocumentStore. (#906)
- Added distance_function property to ChromadocumentStore (#817)
- Add filter_policy to chroma integration (#826)
- Allow search in ChromaDocumentStore without metadata (#863)
Chroma- Fallback to default filter policy when deserializing retrievers without the init parameter (#897)
- Retry tests to reduce flakyness (#836)
- Update ruff invocation to include check parameter (#853)
- Ci: install
pytest-rerunfailureswhere needed; add retry config totest-covscript (#845) - Chore: Minor retriever pydoc fix (#884)
- Chore: pin chromadb>=0.5.0 (#777)
- Chore: change the pydoc renderer class (#718)
- Implement filters for chromaQueryTextRetriever via existing haystack filters logic (#705)
- Small consistency improvements (#536)
- Disable-class-def (#556)
- Make tests show coverage (#566)
- Refactor tests (#574)
- Remove references to Python 3.7 (#601)
- Make Document Stores initially skip
SparseEmbedding(#606) - Pin databind-core (#619)
- Chore: add license classifiers (#680)
- Feature/bump chromadb dep to 0.5.0 (#700)
- Release chroma on python 3.8 (#512)
- Fix order of API docs (#447)
- Serialize the path to the local db (#506)
- Update category slug (#442)
- Review chroma integration (#501)
- Small improvements (#443)
- Fix: make write_documents compatible with the DocumentStore protocol (#505)
- Chroma: rename retriever (#407)
- Generate API docs (#262)
- Add typing_extensions pin to Chroma integration (#295)
- Allows filters and persistent document stores for Chroma (#342)
- Chroma DocumentStore creation for pre-existing collection name (#157)
- Mount chroma integration under
haystack_integrations.*(#193) - Remove ChromaSingleQueryRetriever (#240)
- Fix project URLs (#96)
- Use
hatch_vcsto manage integrations versioning (#103)
- Chore: pin chroma version (#104)
- Fix: update to the latest Document format (#127)
- Document Stores: fix protocol import (#77)
- Fix license headers
- Reorganize repository (#62)
- Update import paths (#64)
- Patch chroma filters tests (#67)
- Remove Document Store decorator (#76)