Outlines v0.0.46

What's Changed

• Adding MLXLM, VLLM classes to LogitsGenerator type by @parkervg in #970
• Fix samplers documentation by @jrinder42 in #980
• Ensure regex matches valid JSON for "const" and "enum" with booleans, nulls, and strings by @mwootten in #972
• Add link to docs of Multimodal Structured Generation for CVPR 2nd MMFM Challenge by @leloykun in #960
• Fix Hugging Face Hub model ID in example code by @davanstrien in #988
• Allow escaped strings in json_schema.py by @lapp0 in #991
• Fix use of os.environ in documentation by @rlouf in #993
• fix pattern-string in json_schema.py by removing anchors by @lapp0 in #995
• Fix Incorrect Token Normalization Method for LlamaCppTokenizer by @lapp0 in #992

New Contributors

• @parkervg made their first contribution in #970
• @jrinder42 made their first contribution in #980
• @mwootten made their first contribution in #972
• @davanstrien made their first contribution in #988

Full Changelog: 0.0.45...0.0.46

Outlines v0.0.45

What's Changed

• Fix some dependency issues and remove obsolete try-except block by @fpgmaas in #967
• Update Modal refs from stub to app by @kstathou in #974
• Mask cache Performance Optimization for vllm by @paul-grundmann in #939
• update README.md by @silviachen46 in #968
• Pin Numpy: numpy<2.0.0, Prevent ModuleNotFoundError by @lapp0 in #977

New Contributors

• @fpgmaas made their first contribution in #967
• @kstathou made their first contribution in #974
• @paul-grundmann made their first contribution in #939
• @silviachen46 made their first contribution in #968

Full Changelog: 0.0.44...0.0.45

Outlines v0.0.44

What's Changed

• Fix null byte \x00 issue in byte level fsm resulting in KeyError in BetterFSM::FSMInfo by @lapp0 in #930
• Correct link for llamacpp library by @alonsosilvaallende in #949
• Add statement regarding OS vs closed models by @rlouf in #950
• Support min/max number of digits for numbers in JSON Schema by @smagnan in #932
• Fix/extend re replacement seq by @saattrupdan in #948
• Update docker ENTRYPOINT to ensure proper argument handling by @shashankmangla in #962
• Add cerebrium as deployment option in documentation by @rlouf in #963
• Add link to TGI documentation by @rlouf in #964
• Introduce outlines.models.mlxlm by @lapp0 in #956
• Update the documentation for OpenAI models by @rlouf in #951

New Contributors

• @alonsosilvaallende made their first contribution in #949
• @smagnan made their first contribution in #932
• @shashankmangla made their first contribution in #962

Full Changelog: 0.0.43...0.0.44

Outlines v0.0.43

What's Changed

• fix typo in docs by @eitanturok in #860
• fix code rendering by @eitanturok in #864
• Ignore errors caused by import warnings from huggingface_hub & pyairports by @leloykun in #866
• Fix format in the BentoML doc by @Sherlock113 in #867
• Hotfix for CFG Generation by @leloykun in #865
• Localize types by @rlouf in #868
• Add Email type by @eitanturok in #870
• Fix installation instructions by @eitanturok in #877
• Extract function name in get_schema_from_signature by @eitanturok in #878
• Remove broken final state loop by @br3no in #874
• Fixing stream stopping at wrong location by @isamu-isozaki in #898
• Prevent Illegal Look-Around for OneOf in JSONSchema by @lapp0 in #897
• Circumvent Broken llama.cpp Pre-Tokenizer by @lapp0 in #892
• Add args to Jinja filters by @eitanturok in #902
• Allow Parenthesis in STRING_INNER by @lapp0 in #899
• Allow Objects Which are Unconstrained (No additionalProperties) in JSON Schemas by @lapp0 in #907
• Use TQDM to track index compilation progress by @lapp0 in #915
• Update caching and add tokenizer to create_states_mapping by @brandonwillard in #911
• Use less problematic whitespace token by @lapp0 in #916
• Enable Tuples / prefixItems in build_regex_from_schema() by @lapp0 in #912
• Fix invalid regex in unconstrained arrays for json_schema.py by @lapp0 in #919
• Allow json schema of {}, resulting in unconstrained json value by @lapp0 in #914
• Fix llamacpp caching by making LlamaCppTokenizer an outlines Tokenizer by @lapp0 in #929
• Fix Missing pyproject.toml Deps, Breaking Release PyPi Workflow & Add Build Wheel / SDist Check to PR Workflow by @lapp0 in #938
• Introduce PR Benchmark Workflow by @lapp0 in #903
• Add Documentation on Outlines Versioning and Releases by @lapp0 in #940

New Contributors

• @eitanturok made their first contribution in #860
• @leloykun made their first contribution in #866
• @Sherlock113 made their first contribution in #867
• @br3no made their first contribution in #874

Full Changelog: 0.0.42...0.0.43

Outlines v0.0.42

What's Changed

• Add cookbook to run Outlines on the cloud with BentoML by @larme in #848
• Add Gigax project to community by @rlouf in #850
• Add HF evaluation article by @rlouf in #851
• Remove the need to copy all tokens during basic generation by @brandonwillard in #852
• Add article with HF in README and documentation by @rlouf in #854
• Add more custom types by @rlouf in #857

New Contributors

• @larme made their first contribution in #848

Full Changelog: 0.0.41...0.0.42

Outlines v0.0.41

What's Changed

• Fix typo in llama.cpp documentation by @rlouf in #835
• Add azure_openai to models init.py by @lassiraa in #840
• Add phone number and zip code custom types by @rlouf in #849

New Contributors

• @lassiraa made their first contribution in #840

Full Changelog: 0.0.40...0.0.41

Outlines v0.0.40

What's Changed

• Exclude escape character in JSON string fields by @rlouf in #829
• Add tweets about Outlines by @rlouf in #830
• Add model_name as an optional parameter for azure_openai by @HerrIvan in #825
• Force dates, uuid, datetimes, times to be between quotes by @rlouf in #831

Full Changelog: 0.0.39...0.0.40

Outlines v0.0.39

What's Changed

• Add page with projects from the community by @rlouf in #816
• Add documentation vLLM for multiple GPUs by @rlouf in #817
• Add torch dependency in installation instructions by @rlouf in #818
• Add DirectMerge article by @rlouf in #819
• Add cookbook to run Outlines on the cloud with Modal by @rlouf in #803
• Fix torch optional import by @rlouf in #821

Full Changelog: 0.0.38...0.0.39

Outlines v0.0.38

What's Changed

• Improve documentation of generation methods by @rlouf in #769
• Small typo fix in cookbook example by @mkretsch327 in #775
• allow json ints to be negative by @posionus in #777
• Add vLLM integration by @rlouf in #772
• Add nvidia to list of companies using Outlines by @rlouf in #783
• Add nvidia logo by @rlouf in #784
• Add SGLang as a user of outlines by @merrymercy in #786
• Fix missing text module from json documentation by @ibndias in #791
• Change white space pattern in llama.cpp test by @rlouf in #793
• Update the llama.cpp integration by @rlouf in #782
• Switched order of AzureAsyncOpenAI to AsyncAzureOpenAI by @gfade in #798
• Add downloads badge by @rlouf in #801
• Add a small grammar guide by @rlouf in #802
• Remove unused dependencies by @rlouf in #804
• Update the README with articles on structured generation by @rlouf in #805
• Make torch and transformers imports optional by @rlouf in #815

New Contributors

• @mkretsch327 made their first contribution in #775
• @merrymercy made their first contribution in #786
• @ibndias made their first contribution in #791
• @gfade made their first contribution in #798

Full Changelog: 0.0.37...0.0.38

Outlines v0.0.37

What's Changed

• Refactored exl2 method to add LoRA, 8bit cache, and other features supported by exllama by @psych0v0yager in #729
• Update the docstring of exl2 by @rlouf in #742
• Added model_kwargs by @isamu-isozaki in #744
• Fix generation of multi-token unicode characters by @ai-and-i in #738
• Make model_kwargs dictionary by default by @rlouf in #747
• Check if the given token is a string by @silverriver in #745
• Add BibteX citation by @rlouf in #755
• fixed parsing token vocabularies for gemma and gpt-sw3 models by @ai-and-i in #763
• fix: Do not reset RegexLogitsProcessor._fsm_state by @saattrupdan in #760

New Contributors

• @psych0v0yager made their first contribution in #729
• @ai-and-i made their first contribution in #738
• @silverriver made their first contribution in #745

Full Changelog: 0.0.36...0.0.37