v5.3.3

Full Changelog: v5.3.2...v5.3.3

v5.4.0

What's Changed

• Renamed to PQASession type by @whitead in #653
• Lock file maintenance by @renovate in #657
• Ability to zero-shot gen_answer by @jamesbraza in #658
• Lock file maintenance by @renovate in #659
• Moving to uv dependency groups by @jamesbraza in #660
• Lock file maintenance by @renovate in #664
• Convert citation to formatted_citation usage where necessary by @mskarlin in #666
• Catch edge case where externalIds field is None by @mskarlin in #668
• Made o1 temperature issue a warning, instead of valueerror by @whitead in #669
• Added train and eval splits' questions and DOIs by @jamesbraza in #662
• fake agent allowing timeouts or exceptions, by @jamesbraza in #672
• Optional AnswerSetting.max_answer_attempts to allow a new unsure branch by @jamesbraza in #673
• Made it so you do not die on invalid tool by @whitead in #670
• Allowing latest pydantic-settings and regenerated cassettes by @jamesbraza in #674
• Empty tool calls leading to done condition by @jamesbraza in #671
• Changed it to be debug for source quality by @whitead in #675

Full Changelog: v5.3.2...v5.4.0

v5.3.2

What's Changed

• Printing the text in a failed llm_parse_json by @jamesbraza in #629
• Change S2 client logic to use arxiv doi if it's defined by @mskarlin in #632
• Increased retry count for ClientConnectorDNSError errors by @jamesbraza in #639
• Make string similarity case insensitive by default by @mskarlin in #640
• Pulling in latest fhaviary, mypy, ruff by @jamesbraza in #647
• Add an after model validator ensuring temp=1 for o1 models by @dakoner in #649
• Fixing crash due to None author by @jamesbraza in #650
• Fixing flaky test test_minimal_fields_filtering by @jamesbraza in #651
• Fixing flaky tests test_code and test_minimal_fields_filtering by @jamesbraza in #652
• Lock file maintenance by @renovate in #648

New Contributors

• @dakoner made their first contribution in #649

Full Changelog: v5.3.1...v5.3.2

v5.3.1

What's Changed

• Exposed LDPRolloutCallback and on_agent_action_callback for fake agent by @jamesbraza in #612
• Fixed NumpyVectorStore.__eq__'s NotImplemented case by @jamesbraza in #613
• Implemented __deepcopy__ on all Environments by @jamesbraza in #614
• Made embedding default by @whitead in #615
• Lock file maintenance by @renovate in #617
• Pulled in latest PyMuPDF for set_messages by @jamesbraza in #618
• Fixed crash due to DOI being a list by @jamesbraza in #619
• Added configuration to adjust how contexts are displayed by @whitead in #620
• Fixing CI by regenerating test_pdf_reader_match_doc_details cassette by @jamesbraza in #625
• Retrying flaky test test_propagate_options by @jamesbraza in #626
• Regression protection in embedding_model_factory by @jamesbraza in #622
• Added writer.wait_merging_threads call by @jamesbraza in #628
• Caching opened tantivy.Indexes in the package by @jamesbraza in #627

Full Changelog: v5.3.0...v5.3.1

v5.3.0

What's Changed

• Add callback support in settings and tools by @nadolskit in #590
• Moved validate_sources to include all sources not found by @jamesbraza in #595
• Cleaning up citations by @jamesbraza in #598
• Validating sources with case insensitive DOI matching by @jamesbraza in #600
• Added sentence transformers embedding model by @whitead in #604
• Cleaned and clarified deferred embeddings code by @jamesbraza in #597
• Fixed NumpyVectorStore.clear from not clearing text_hashes by @jamesbraza in #608
• Moved Pydantic model_config to top of each class by @jamesbraza in #607
• Testing we can use ~ as paper_directory by @jamesbraza in #610
• Increased testing of NumpyVectorStore and defer_embeddings by @jamesbraza in #606
• Expose env class to run_agent functions by @mskarlin in #611

Full Changelog: v5.2.1...v5.3.0

v5.2.1

What's Changed

• Fixing Settings propagation and always configuring LiteLLM retrying by @jamesbraza in #575
• Fixing the ability to resume index builds by @jamesbraza in #577
• Fixed GLOBAL_RATE_LIMITER_TIMEOUT env var typo by @jamesbraza in #578
• Lock file maintenance by @renovate in #583
• Unsilencing manifest read failure when no CSV header is present by @jamesbraza in #587
• Added typeguard to confirm type hints by @jamesbraza in #585
• Renovate once/month, removing stale LiteLLM disables by @jamesbraza in #589
• Fixed a few minor SearchIndex bugs and documented SearchIndex by @jamesbraza in #588
• Confirming LitQA sources are in a manifest/index by @jamesbraza in #579
• Limiting parsed page size to 1.28 million chars by @jamesbraza in #592
• Stripping DOI URL prefix for sources by @jamesbraza in #593
• Fix sequential client query clobbering by @mskarlin in #594

Full Changelog: v5.2.0...v5.2.1

v5.2.0: OpenAlex

Highlights

Added a new metadata provider OpenAlex for scholarly work, researchers, institutions, journals, and research topics.

• Responses can include open access information and raw pdf locations.
• Doesn't require authentication, but does prioritize requests with an email in the mailto URL parameter, exposed as an environment variable OPENALEX_MAILTO

Implemented an opt-in bypass around the litellm.Router for LLM completions (see #563)

What's Changed

• Fixed pickle-ability of LiteLLMModel by @jamesbraza in #560
• Refactoring LiteLLMModel before removing Router by @jamesbraza in #561
• Adds openalex client as a default client by @nadolskit in #555
• Moving to setup-uv and hynek/build-and-inspect-python-package in CI by @jamesbraza in #564
• Ability to bypass usage of litellm.Router by @jamesbraza in #563
• Propagating hynek/build-and-inspect-python-package's output location to pypa/gh-action-pypi-publish by @jamesbraza in #565
• Downloading Package artifact for pypa/gh-action-pypi-publish by @jamesbraza in #566

Full Changelog: v5.1.1...v5.2.0

v5.1.1

What's Changed

• Lock file maintenance by @renovate in #545
• Validating for broken index by @jamesbraza in #544
• Added example how to use ollama hosted models by @grg-ffb in #536
• Making parsing resistant to failed inference of citations by @whitead in #551
• Exposed log verbosity configuration function by @jamesbraza in #552
• Cleaned up log verbosity code by @jamesbraza in #554

New Contributors

• @grg-ffb made their first contribution in #536

Full Changelog: v5.1.0...v5.1.1

v5.1.0: rate limits, refactored settings

Highlights

In-housed rate limits management

• Centers on a moving window algorithm with either a Redis or in-memory state
• Supports dynamically defined rates for different models or providers.
• New bundled configurations for different OpenAI rate limit tiers
• Accomplished using new third party dependencies coredis and limits

Refactored Settings to allow for increased flexibility

• Indexing
  • Indexes can use relative paths, enabling sharing across machines
  • Paper search now no longer rebuilds the index every invocation
  • Index parameter now are grouped in IndexSettings
    • This release begins a deprecation cycle for the original hyperparameters
  • Index builds now have a rich.Progress bar
• Parsing
  • Chunking and embedding can now be deferred to inference time
• Agents
  • Agents now have a max_timesteps parameter to upper-bound trajectory length
  • Default agent is now a simple tool calling agent (ToolSelector), instead of a deterministic sequence of tool calls ("fake" agent)

Several bug fixes centered on retry-able errors:

• Flaky Semantic Scholar and Crossref SSL errors and connection reset errors
• LLM completions and text embeddings

What's Changed

• Cleaning up #489's implementation by @jamesbraza in #503
• chore(deps): lock file maintenance by @renovate in #504
• chore(deps): lock file maintenance by @renovate in #506
• chore(deps): update all non-major dependencies by @renovate in #505
• Filtering two more DeprecationWarnings by @jamesbraza in #509
• Refactor to create settings.agent.index grouping by @jamesbraza in #510
• Removed extra save_index calls, and added missing changed by @jamesbraza in #513
• Not rebuilding SearchIndex every paper_search by @jamesbraza in #512
• Updated citation to arxiv preprint by @whitead in #514
• Aviary agent max_timesteps and fixed test_gather_evidence_rejects_empty_docs by @jamesbraza in #515
• Moved reset_log_levels to usefixtures by @jamesbraza in #517
• Decomposing Answer.could_not_answer by @jamesbraza in #516
• Fixing IndexSettings.use_absolute_paper_directory leading to relative index file paths by @jamesbraza in #518
• Moving run_ldp_agent to center on RolloutManager by @jamesbraza in #519
• Retrying on known Semantic Scholar flaky SSL error in get_s2_doc_details_from_doi by @jamesbraza in #522
• Converted PyMuPDF message to warning logs by @jamesbraza in #523
• rich.Progress bar for monitoring index builds by @jamesbraza in #521
• Better descriptions and log messages by @jamesbraza in #524
• Made it possible to skip chunking by @whitead in #526
• Retrying on aiohttp.ClientConnectionResetError by @jamesbraza in #529
• Add rate limits for LLMs and Embedding Models by @mskarlin in #520
• Disallowing confusing None from IndexSettings.index_directory, and IndexSettings.get_named_index_directory by @jamesbraza in #531
• Add router_kwargs in separate control flow step by @mskarlin in #532
• Propagating AgentSettings.agent_type default for synchrony by @jamesbraza in #533
• Adding retrying of aembedding if it fails by @jamesbraza in #535
• Add limits+coredis to mypy by @mskarlin in #537
• Lock file maintenance by @renovate in #534
• Controlling for pymupdf version in test_pdf_reader_match_doc_details VCR by @jamesbraza in #538
• Lock file maintenance by @renovate in #539
• Fixed yet another api.semanticscholar.org:443 ssl:default error via retrying by @jamesbraza in #540

Full Changelog: v5.0.10...v5.1.0

v5.0.10

What's Changed

• Discovered Renovate :automergeMinor and preventing openai version bumps by @jamesbraza in #493
• Fixing LitQATaskDataset deserialization from config by @jamesbraza in #494
• chore(deps): update all non-major dependencies by @renovate in #498
• Broken reader ut by @nadolskit in #497
• Fixing LitQATaskDatasetcompute_trajectory_metrics crash with bad status extraction by @jamesbraza in #500
• For autogenerated Router kwargs, specifying timeout of 60-sec by @jamesbraza in #501

Full Changelog: v5.0.9...v5.0.10