v5.11.0

What's Changed

• Fixed type problems from llmclient by @maykcaldas in #770
• Clinical trials docs and bugfixes by @mskarlin in #819
• Fixing flaky test test_cli_can_build_and_search_index by retrying by @jamesbraza in #816
• Allowing more general types in Settings by @jamesbraza in #818
• Documenting citation style by @jamesbraza in #817
• Updated badges in README by @maykcaldas in #821
• Pulling in latest ldp for bulk_evaluate_consensus by @jamesbraza in #826
• Updated CITATION.cff to include more info by @jamesbraza in #824
• chore(deps): lock file maintenance by @renovate in #825

Full Changelog: v5.10.2...v5.11.0

v5.10.2

What's Changed

• Ensure fields are lists before combining in DocDetails class by @harryvu-futurehouse in #801
• Pulling in latest fh-llm-client for CommonLLMNames by @jamesbraza in #810
• chore(deps): lock file maintenance by @renovate in #811
• Fixing gather_evidence and complete response messages by @jamesbraza in #812

New Contributors

• @harryvu-futurehouse made their first contribution in #801

Full Changelog: v5.10.1...v5.10.2

v5.10.1

What's Changed

• Fixing tool failures crashing runners in failover answer by @jamesbraza in #808
• Fixing evidence counted in gather_evidence's response message by @jamesbraza in #809

Full Changelog: v5.10.0...v5.10.1

v5.10.0

What's Changed

• Expose more contexts as output from gather_evidence tool by @mskarlin in #793
• Settings lookup table and improved Settings descriptions by @jamesbraza in #795
• Fixing incorrect seeding argument due to Pydantic extra="ignore" by @jamesbraza in #797
• Loosened input types to allow more MultipleChoiceQuestion by @jamesbraza in #798
• Added aviary-paper-data as LitQA v2 test split by @jamesbraza in #800
• Added LitQAv2TaskSplit.get_index convenience by @jamesbraza in #802
• Refactor to remove QueryRequest entity by @jamesbraza in #799
• Latest tooling by @jamesbraza in #804
• chore(deps): update astral-sh/setup-uv action to v5 by @renovate in #806
• chore(deps): lock file maintenance by @renovate in #807

Full Changelog: v5.9.2...v5.10.0

v5.9.2

Note to self: run unit tests (and not just mypy) in downstream repos before cutting the release.

What's Changed

• Fixing not using set_llm_session_ids from fh-llm-client by @jamesbraza in #792

Full Changelog: v5.9.1...v5.9.2

v5.9.1

What's Changed

• Pinning min version of fh-llm-client by @jamesbraza in #790
• Fixed Record import from Qdrant not being in TYPE_CHECKING block by @jamesbraza in #791

Full Changelog: v5.9.0...v5.9.1

v5.9.0

What's Changed

• feat: Qdrant support by @Anush008 in #730
• Made it possible to get answers from litqa evaluations by @whitead in #760
• Added answer an ideal to gradeable environments by @whitead in #762
• Pinned lower bound on aiohttp for aiohttp.ClientConnectionResetError by @jamesbraza in #763
• Added llmclient dependency by @maykcaldas in #757
• Propagating citation count in flaky test_pdf_reader_match_doc_details by @jamesbraza in #766
• Renovate lockFileMaintenance respecting schedule, 2-week stability period, no openai pinning by @jamesbraza in #767
• chore(deps): lock file maintenance by @renovate in #765
• Added test split's source DOIs and question IDs by @jamesbraza in #771
• Consolidated LDP imports into ldp_shims module by @jamesbraza in #772
• Missing None failovers in LDP shims by @jamesbraza in #774
• Dropping refurb in favor of its ruff port by @jamesbraza in #773
• Converting add_texts_and_embeddings to async by @ThomasRochefortB in #778
• Add clinical trials search tool by @mskarlin in #777
• chore(deps): lock file maintenance by @renovate in #769
• Replace raise_for_status return None with Mock() in clinical trials test by @mskarlin in #785
• Docs around embeddings and agentic usage by @jamesbraza in #780
• Moved to MultipleChoiceQuestion/MultipleChoiceEvaluation from aviary by @jamesbraza in #768
• Feat/qdrant docs reconstruct by @ThomasRochefortB in #776
• Removed dead test cassettes by @jamesbraza in #788

New Contributors

• @Anush008 made their first contribution in #730
• @ThomasRochefortB made their first contribution in #778

Full Changelog: v5.8.0...v5.9.0

v5.6.1

Full Changelog: v5.6.0...v5.6.1

v5.8.0

What's Changed

• Update all non-major dependencies by @renovate in #745
• Created dev extra for convenience by @jamesbraza in #750
• Update all non-major dependencies by @renovate in #754
• Populated LICENSE by @jamesbraza in #756
• Add partitioning func capabilities to allow doc-types-based embedding ranking by @mskarlin in #752
• Exposed seeding of LitQA2 read and shuffling by @jamesbraza in #758

Full Changelog: v5.7.0...v5.8.0

v5.7.0

What's Changed

• Moved README to use session over answer by @jamesbraza in #741
• Moved Docs.aadd to support str | os.PathLike by @jamesbraza in #742
• Cleared up 'Adding Documents Manually' docs by @jamesbraza in #740
• Support env states with custom status functions by @mskarlin in #743
• Update astral-sh/setup-uv action to v4 by @renovate in #746
• Moved JSON summary prompt to mention score is an integer by @jamesbraza in #748

Full Changelog: v5.6.0...v5.7.0