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

Outlines v0.0.16

What's Changed

• Define end-to-end applications by @rlouf in #413
• Create a new AsyncOpenai client for each request by @rlouf in #434

Full Changelog: 0.0.15...0.0.16

Outlines v0.0.15

What's Changed

• Add models playing chess example by @rlouf in #394
• Documentation prompting by @rlouf in #426
• Fix vectorize signature and caching in OpenAI integration by @rlouf in #430

Full Changelog: 0.0.14...0.0.15

Outlines v0.0.14

What's Changed

• anyOf and oneOf implementation of the JSON Schema spec are incorrect by @BruParis in #399
• Update the documentation styling and Home Page by @rlouf in #408
• Track usage, add system prompt and timeout by @HerrIvan in #388
• Change line spacing and index code width by @rlouf in #409
• Fix the width of the code example on index by @rlouf in #410
• Improve Getting Started section of the documentation by @rlouf in #411
• Update README.md by @rlouf in #412
• Remove unused FSM code by @brandonwillard in #414
• Refactor the sequence generation by @rlouf in #366
• Add Mamba models by @rlouf in #403

New Contributors

• @BruParis made their first contribution in #399

Full Changelog: 0.0.13...0.0.14

Outlines v0.0.13

What's Changed

• step by step prompting and colons in prompts by @MeDott29 in #390
• Correct auto-gpt name in exception by @amrrs in #392
• Add Chain of Density prompting example by @rlouf in #389
• fixes generate.json() not working with json schema strings by @bettybas in #395

New Contributors

• @MeDott29 made their first contribution in #390
• @amrrs made their first contribution in #392

Full Changelog: 0.0.12...0.0.13

Outlines v0.0.12

What's Changed

• Fix a typo in the documentation by @rlouf in #369
• Modify the openai model to conform to the new openai sdk v1.0.0 by @RobinPicard in #364
• Add "was this page helpful?" widget by @rlouf in #372
• Remove unused arguments from openai generate functions. by @HerrIvan in #376
• "Optimistic" is_in generation for openai. by @HerrIvan in #378
• Add hiring ad on Outlines by @rlouf in #384
• Refactor the OpenAI integration by @rlouf in #381
• Remove unnecessary comment in OpenAI integration by @rlouf in #385
• Mention in README datasets requirement by @rlouf in #386
• Add integration for AutoGPTQ and AutoAWQ by @rlouf in #343

New Contributors

• @RobinPicard made their first contribution in #364

Full Changelog: 0.0.11...0.0.12

Outlines v0.0.11

What's Changed

• Add optional api_key parameter by @bettybas in #362
• Build a JSON schema from a function's signature by @rlouf in #355
• Implement text.generate.format constrained generation by @rlouf in #358
• Remove top-level imports of transformers and datasets by @rlouf in #367

New Contributors

• @bettybas made their first contribution in #362

Full Changelog: 0.0.10...0.0.11