Outlines v0.0.26

What's Changed

• Update index.md - fix model by @7flash in #601
• Fix typo in prompt example by @ShukantPal in #603
• Reset lark package in test_parsing.py by @lapp0 in #596
• introduce WHITESPACE regex constant by @jc-louis in #599
• Make json array generation more flexible by @posionus in #608
• Update self_consistency.py - print actual answer by @7flash in #602
• Bump vLLM version to 0.3.0 by @lapp0 in #579

New Contributors

• @7flash made their first contribution in #601
• @ShukantPal made their first contribution in #603
• @jc-louis made their first contribution in #599
• @posionus made their first contribution in #608

Full Changelog: 0.0.25...0.0.26

v0.0.25

What's Changed

• Fix bug in the treatment of the anyOf keywork in JSON schema by @RobinPicard in #552
• Improvements to documentation and README by @rlouf in #547
• Added subclass of OpenAI class to support custom endpoints by @shannonsands in #560
• Update pydantic install instructions for vLLM by @rlouf in #564
• Pin transformers version to 4.36.2 by @lapp0 in #569
• Clear cache upon version upgrade by @lapp0 in #566
• Implement JSON schema field constraints by @aschwa in #567
• Fix incompleteness of regex and cfg guided generation by @benlipkin in #544
• Add benchmark suite by @lapp0 in #542
• Fix Bug Issue Template - Command Doesn't Produce Version, Isn't Copyable by @lapp0 in #578
• Bugfix: Fixes dtype issue described in #583 by @dnhkng in #584
• Make OpenAI models compatible with the main API by @rlouf in #574
• Add grammars module by @lapp0 in #562

New Contributors

• @shannonsands made their first contribution in #560
• @lapp0 made their first contribution in #569
• @aschwa made their first contribution in #567
• @dnhkng made their first contribution in #584

Full Changelog: 0.0.24...0.0.25

Outlines v0.0.24

What's Changed

• Add roadmap blog post by @rlouf in #519
• Remove draft status of roadmap post by @rlouf in #525
• Cache creation of states_token_mapping in the init of RegexFSM by @RobinPicard in #492
• Remove the AutoAWQ and AutoGPTQ integrations by @rlouf in #527
• Fix typos by @pitmonticone in #530
• Add CFG to vllm serving by @mory91 in #517
• Revert "Add CFG to vllm serving" by @rlouf in #537

New Contributors

• @pitmonticone made their first contribution in #530
• @mory91 made their first contribution in #517

Full Changelog: 0.0.23...0.0.24

Outlines v0.0.23

What's Changed

• Support required keyword in JSON Schema by @RobinPicard in #495
• Use the OpenAI API to check that a model exists by @rlouf in #518
• Updates chess cookbook example with Phi-2 and adds omitted code. by @kgourgou in #521
• Patch nest_asyncio in notebooks only by @dzhulgakov in #520
• Support Azure OpenAI by @joeddav in #522

New Contributors

• @kgourgou made their first contribution in #521
• @dzhulgakov made their first contribution in #520
• @joeddav made their first contribution in #522

Full Changelog: 0.0.22...0.0.23

Outlines v0.0.22

What's Changed

• Remove idx arg from FSM interface by @benlipkin in #510
• Add LlamaCpp integration by @dtiarks in #486

New Contributors

• @dtiarks made their first contribution in #486

Full Changelog: 0.0.21...0.0.22

Outlines v0.0.21

What's Changed

• Do not import transformers at top level in Exllama2 integration by @rlouf in #490

Full Changelog: 0.0.20...0.0.21

Outlines v0.0.20

What's Changed

• Change argument name in logits_bias by @rlouf in #464
• Edit quickstart and community sections of the documentation by @rlouf in #457
• Expand "reach out" section by @rlouf in #466
• Simplify the README by @rlouf in #468
• Change order of features and styling in documentation by @rlouf in #470
• Update pip install outlines in documentation by @jqueguiner in #467
• Add classification and NER examples to the documentation by @rlouf in #471
• Document the vLLM integration by @rlouf in #473
• Add integration for ExllamaV2 by @kimjaewon96 in #462
• Add validation for model_name parameter by @smwitkowski in #476
• Restore the ability to stop when a specified string has been generated by @RobinPicard in #451
• Fix typo in caching.py by @eltociear in #482
• update vllm patch to v0.2.6 and add regex support for /generate by @tscholak in #481

New Contributors

• @kimjaewon96 made their first contribution in #462
• @smwitkowski made their first contribution in #476
• @tscholak made their first contribution in #481

Full Changelog: 0.0.19...0.0.20

Outlines v0.0.19

What's Changed

• Update README.md by @jqueguiner in #446
• Update README to point to latest function of LLM text by @immortal3 in #447
• Add grammar-guided generation to the README by @rlouf in #454
• Fix typo in CFG example by @rlouf in #455
• Simplify logit biasing logic by @Infrared1029 in #458
• Serve JSON with vLLM using FastAPI and Uvicorn by @rlouf in #453

New Contributors

• @immortal3 made their first contribution in #447
• @Infrared1029 made their first contribution in #458

Full Changelog: 0.0.18...0.0.19

Outlines v0.0.18

What's Changed

• Add CFG-guided generation by @benlipkin in #391

New Contributors

• @benlipkin made their first contribution in #391

Full Changelog: 0.0.17...0.0.18

Outlines v0.0.17

What's Changed

• Update README by @jqueguiner in #436
• fix(README): mistralai/Mistral-7B-v0.1 by @jqueguiner in #437
• Fix prompt removal logic and update test case by @venondev in #439
• Add example of integration with vLLM by @rlouf in #435
• Vllm integration by @rlouf in #442
• Update the vLLM example to work with batch requests by @rlouf in #444
• Add JSON Schema example in README by @rlouf in #445

New Contributors

• @jqueguiner made their first contribution in #436
• @venondev made their first contribution in #439

Full Changelog: 0.0.16...0.0.17