v0.37.0 🐍

🚀 Enhancements

• Added support for conversational search (#1133) @EazyAl

⚙️ Maintenance/misc

• Remove bors (#1131) @curquiza

Thanks again to @EazyAl, @Strift, @brunoocasali, @curquiza ! 🎉

v0.36.0 🐍

⚠️ Breaking changes

• Fix Document model: bad test, attribute bug, and field cleanup (#1113) @nnethercott

  🛠 migration path

  What changed?

  • The internal __doc field in Document has been removed to avoid data duplication.
  • Document.__getattr__ now correctly returns attribute values rather than the attribute name itself.

  Impact

  • Code relying on internal access to document._Document__doc (e.g. through iterators) will break.
  • Behavior of doc.getattr("field") is now consistent and correct.

  What you need to do:

  • If you were manually accessing document._Document__doc, switch to using direct attribute access or casting with dict(doc).

  example updated usage

  doc = index.get_document("foo")
  doc_dict = dict(doc) 
  doc_dict.pop("_Document__doc")  # ❌ Not needed anymore

• Refactor TaskResults, IndexStats (#1066) @ellnix (⚠️ this potentially have a breaking-change)

🚀 Enhancements

• Add composite embedders and pooling for Hugging Face models (#1104) @nnethercott
• Give helpful error message when missing protocol in API URL (#1096) @ellnix
• Add methods for new index settings: facetSearch and prefixSearch (#1068) @thicolares
• Add disableOnNumbers to typo tolerance settings (#1116) @nnethercott
• Add support for Networks feature (#1097) @MuddyHope

⚙️ Maintenance/misc

• Add merge_group to trigger tests (#1117) @brunoocasali
• Fix CI (#1118) @brunoocasali

Thanks again to @MuddyHope, @brunoocasali, @ellnix, @nnethercott, @thicolares! 🎉

v0.35 🕊️

This release makes the SDK compatible with Meilisearch 1.13 AI search features.

🚀 Enhancements

• Update embedders settings, hybrid search, and add tests for AI search methods (#1087) @Strift

⚙️ Maintenance/misc

• Remove _md code samples for Mintlify migration (#1100) @curquiza

Thanks again to @Strift, @brunoocasali, and @curquiza ! 🎉

v0.34.1 🐍

🚀 Enhancements

• Sync embedder models with latest meili settings (#1075) @ellnix
• Allow custom headers in requests (#1076) @ellnix
• Make key description optional (#1067) @ellnix
• Update Documents with Functions (#1074) @MuddyHope

⚙️ Maintenance/misc

• Fix Python version error (#1086) @Strift

Thanks again to @MuddyHope, @Strift, & @ellnix! 🎉

v0.34.0 🕊️

This version introduces features released on Meilisearch v1.13.0 🎉

✨ New

• AI-powered search is now stable @Strift

🚀 Enhancements

• Stabilize vector store usage (#1079) @Strift
• Support localized-attributes settings (#1060) @ellnix
• Support batches API (#1062) @ellnix
• Support searching for similar documents (#1063) @ellnix

⚙️ Maintenance/misc

• Add federated search code-sample (#1064) @ellnix

Thanks again to @ellnix and @Strift! 🎉

v0.33.1 🐍

🐛 Bug Fixes

• Improve documentation for Index.add_documents() methods (#1057) @samuelbradshaw

Thanks again to @samuelbradshaw and @sanders41! 🎉

v0.33.0 🐍

⚠️ Breaking changes

• Make the minimum supported version of Meilisearch v1.2.0 (#1045) @martinnj

🐛 Bug Fixes

• Support boolean parameters in Index.get_documents (#1045) @martinnj

Thanks again to @martinnj, and @sanders41! 🎉

v0.32.0 🐍

⚠️ Breaking changes

• Drop support for python 3.8 and add 3.13 support (#1039) @sanders41

v0.31.6 🐍

🚀 Enhancements

• Compatibility of embedder settings with Meilisearch v1.11 (#1018) @sanders41 & @dureuill
• Supports rankingScoreThreshold search parameter (#1008) @aweidner
• Federated Search Addition (#1013) @MuddyHope

⚙️ Maintenance/misc

• Adds documentation for search parameter reference distinct (#1007) @aweidner

Thanks again to @MuddyHope, @aweidner, @curquiza, @dureuill and @sanders41! 🎉

v0.31.5 🐍

🚀 Enhancements

• add: frequency value for matchingStrategy search parameter (#998) @239yash
• Adds documentation and an integration test case for the distinct keyword in index search (#1005) @aweidner

🔒 Security

• Bump setuptools from 69.0.3 to 70.0.0 in the pip group (#996)

Thanks again to @239yash, @aweidner! 🎉