Releases: instructor-ai/instructor
Releases · instructor-ai/instructor
1.4.0
What's Changed
- Fix debug log exception in retry_async by @mattheath in #884
- Formatted Docs by @ivanleomk in #864
- Anthropic IncompleteOutputException was never triggered for tools and JSON modes by @palako in #848
- Fix for Flaky Test Issue #853 by @DonovanAD in #891
- revise prompt design docs [zero-shot] by @shreya-51 in #865
- Corrected some typos. by @atbradley in #905
- Pyright Errors by @ivanleomk in #900
- Update 4-validation.ipynb by @ashkanrdn in #932
- Fix typo in handle_response_model (anthropic system message): responsd -> respond by @timlod in #904
- Remove Async Validation in process async by @ivanleomk in #933
- Adding support for structured outputs by @ivanleomk in #938
- Update vertexai.md fix typo by @lawrencecchen in #943
- Resolve duplicate test function name by @noxan in #894
New Contributors
- @mattheath made their first contribution in #884
- @palako made their first contribution in #848
- @DonovanAD made their first contribution in #891
- @atbradley made their first contribution in #905
- @ashkanrdn made their first contribution in #932
- @timlod made their first contribution in #904
- @lawrencecchen made their first contribution in #943
Full Changelog: 1.3.7...1.4.0
1.3.7
1.3.5
What's Changed
- prompting docs by @shreya-51 in #786
- Fixed up an example for RAR and RE2 by @ivanleomk in #790
- Added an index page by @ivanleomk in #791
- fix: async from_litellm by @adrienbrault in #783
- Update maybe.md by @r41ng3l in #781
- Update usage.md 'constructor usage list' command documentation by @r41ng3l in #770
- Add prompting docs tests by @jxnl in #794
- docs: typo fix by @rishabgit in #795
- Add explicit check for jsonref dep in vertexai client import guard by @lemontheme in #797
- Fixed up Self-Ask Example by @ivanleomk in #792
- Added some new prompt techniques by @ivanleomk in #809
- prompt docs by @shreya-51 in #793
- Validate anthropic_tool function args as json by @woodbridge in #779
- Fix: Resolve create_model() TypeError in Partial class by @slavakurilyak in #801
- add client parameter to instructor.Intructions by @bhomass in #814
- Added new techniques by @ivanleomk in #810
- prompt docs by @shreya-51 in #813
- render gpt4o url by @rshah713 in #826
- skeleton of thought prompting doc by @shreya-51 in #824
- Bugfix: enable anthropic streaming support with partials by @ssonal in #825
- docs(examples, navigation): add local classification tutorial and update navigation by @jxnl in #830
- sg_icl prompting doc by @shreya-51 in #829
- Synthetic Data Notebook by @ivanleomk in #839
- feat: add blog post and example script for extracting YouTube video chapters using OpenAI models by @jxnl in #831
- Added COSP by @ivanleomk in #823
- Fixed up Max Mutual information example by @ivanleomk in #842
- Added support for Anthropic system parameter by @ivanleomk in #833
- knn prompting doc by @shreya-51 in #845
- Fixed up additional functionality for the batch job article by @ivanleomk in #843
- Fixed up new pydantic version by @ivanleomk in #847
- Bump Tenacity Version by @ivanleomk in #851
New Contributors
- @adrienbrault made their first contribution in #783
- @r41ng3l made their first contribution in #781
- @woodbridge made their first contribution in #779
- @slavakurilyak made their first contribution in #801
- @bhomass made their first contribution in #814
- @rshah713 made their first contribution in #826
Full Changelog: 1.3.4...1.3.5
1.3.4
What's Changed
- typo fix and rephrasing suggestion by @lukaskf in #756
- Fix the link to use the cloudflare docs by @ivanleomk in #753
- Updated the Documentation by @ivanleomk in #751
- Fixed Cohere retries by @ionflow in #761
- Added Vertex AI JSON Mode by @ajac-zero in #750
- Fix heading indentation in the getting started section of the docs by @RensDimmendaal in #744
- Anthropic client. Prevent empty generator when streaming by @lemontheme in #728
- Add Gemini via OpenAI Client Support Documentation by @bllchmbrs in #736
- rename batch to bulk/async, to avoid confusion with OpenAI's batch APIs by @avyfain in #765
- Disabling Pydantic Error by @ivanleomk in #757
- feat: add support for typeddicts by @ivanleomk in #758
- feat: prompt engineering cookbooks by @shreya-51 in #764
- feat: new cli for batch jobs by @ivanleomk in #754
- zero-shot prompting docs by @shreya-51 in #780
New Contributors
- @lukaskf made their first contribution in #756
- @RensDimmendaal made their first contribution in #744
- @avyfain made their first contribution in #765
Full Changelog: 1.3.3...1.3.4
What's Changed
- typo fix and rephrasing suggestion by @lukaskf in #756
- Fix the link to use the cloudflare docs by @ivanleomk in #753
- Updated the Documentation by @ivanleomk in #751
- Fixed Cohere retries by @ionflow in #761
- Added Vertex AI JSON Mode by @ajac-zero in #750
- Fix heading indentation in the getting started section of the docs by @RensDimmendaal in #744
- Anthropic client. Prevent empty generator when streaming by @lemontheme in #728
- Add Gemini via OpenAI Client Support Documentation by @bllchmbrs in #736
- rename batch to bulk/async, to avoid confusion with OpenAI's batch APIs by @avyfain in #765
- Disabling Pydantic Error by @ivanleomk in #757
- feat: add support for typeddicts by @ivanleomk in #758
- feat: prompt engineering cookbooks by @shreya-51 in #764
- feat: new cli for batch jobs by @ivanleomk in #754
- zero-shot prompting docs by @shreya-51 in #780
- Updated Pyproject.toml to publish a new version of Instructor by @ivanleomk in #785
New Contributors
- @lukaskf made their first contribution in #756
- @RensDimmendaal made their first contribution in #744
- @avyfain made their first contribution in #765
Full Changelog: 1.3.3...1.3.4
1.3.3
What's Changed
- refactor(simple_type, ModelAdapter): update type checking and refactor model creation by @jxnl in #710
- Fix response UnboundError when request fails and custom
tenacity.Retrying
is used by @lazyhope in #713 - [fixes #721] Switch away from Anthropic beta interface for tools. by @lemontheme in #723
- Add Support for VertexAI Gemini by @ajac-zero in #711
- async gemini support by @Cruppelt in #719
- fix: parallel unions by @vinchg in #734
- typo fix document_segmentation.md by @NicolaiLolansen in #730
- Sync
pyproject.toml
andpoetry.lock
files by @jlondonobo in #729 - Added Jiter Support by @ivanleomk in #745
- Iterable Workaround by @ivanleomk in #737
New Contributors
- @lemontheme made their first contribution in #723
- @ajac-zero made their first contribution in #711
- @vinchg made their first contribution in #734
- @NicolaiLolansen made their first contribution in #730
Full Changelog: 1.3.2...1.3.3
1.3.2
What's Changed
- Adding gpt4o vision example by @karbon0x in #702
- Fixed incorrect/missing arguments by @Elektra58 in #708
- Fixed incorrect argument by @Elektra58 in #707
- Fixed a typo by @yasoob in #705
- restore async groq functionality by @cmishra in #704
- Improve gemini model robustness by @ssonal in #701
New Contributors
- @karbon0x made their first contribution in #702
- @Elektra58 made their first contribution in #708
- @yasoob made their first contribution in #705
- @cmishra made their first contribution in #704
Full Changelog: 1.3.1...1.3.2
1.3.1
What's Changed
- Fix typos in README.md by @AmgadHasan in #699
- Fix failure checking for "google.generativeai' import spec by @dbmikus in #698
New Contributors
- @AmgadHasan made their first contribution in #699
- @dbmikus made their first contribution in #698
Full Changelog: 1.3.0...1.3.1
1.3.0
What's Changed
- Update groq.md by @frankbaele in #651
- Added gpt-4o to model costs and model names by @st4r0 in #671
- Update Groq documentation and examples to use preferred patching method by @NasonZ in #663
- anthropic force tool by @Cruppelt in #681
- maybe results typo fix by @rbraddev in #686
- Parea Blogpost by @joschkabraun in #673
- Fix typo in philosophy.md by @deeplook in #677
- Update mode.py to warn in
Mode.FUNCTIONS
access vs. in__new__
by @boydgreenfield in #678 - Fix handling of snapshot_ids ("gpt-4-turbo-2024-04-09" and "gpt-4o-2024-05-13") and alias "gpt-4-turbo". by @st4r0 in #672
- Update ollama.md by @MeDott29 in #635
- Fixed up discord link by @ivanleomk in #690
- Enrich IncompleteOutputException with completion context by @lukszamarcin in #683
- Anthropic streaming support by @ssonal in #682
- results rename by @rbraddev in #692
- Updates to Parea blog by @joschkabraun in #695
- Fix typo in blog by @joschkabraun in #696
- Update
Mode.MD_JSON
and addProvider.DATABRICKS
by @arcaputo3 in #691 - Add basic support for gemini models by @ssonal in #684
New Contributors
- @frankbaele made their first contribution in #651
- @st4r0 made their first contribution in #671
- @NasonZ made their first contribution in #663
- @rbraddev made their first contribution in #686
- @deeplook made their first contribution in #677
- @lukszamarcin made their first contribution in #683
- @ssonal made their first contribution in #682
- @arcaputo3 made their first contribution in #691
Full Changelog: 1.2.6...1.3.0
1.2.6
What's Changed
- Import typing related imports only when type checking by @noxan in #645
- New Logfire Article ( Fixes #640 ) by @ivanleomk in #647
- Updated the Logfire and Fastapi article by @ivanleomk in #648
- [docs] index watsonx example by @h0rv in #642
- doc: Update self_critique.md by @sgrimee in #652
- fix: Update llama-cpp-python examples to use
patch
instead offrom_openai
by @abetlen in #656
New Contributors
- @noxan made their first contribution in #645
- @sgrimee made their first contribution in #652
- @abetlen made their first contribution in #656
Full Changelog: 1.2.5...1.2.6
1.2.5
What's Changed
- feat: add watsonx support by @h0rv in #620
- Implement Pyright for Type-Checking by @max-muoto in #630
- Enable PyUpgrade Ruff Rule-Set by @max-muoto in #633
- Avoid deprecated class property stacking by @max-muoto in #637
- Instructor with Logfire by @ivanleomk in #639
- ANTHROPIC_JSON: allow control characters in JSON strings if strict=False by @voberoi in #644
- Allow newer Pydantic patch versions by @bencrouse in #643
New Contributors
- @h0rv made their first contribution in #620
- @max-muoto made their first contribution in #630
- @voberoi made their first contribution in #644
- @bencrouse made their first contribution in #643
Full Changelog: 1.2.4...1.2.5