Outlines v0.1.5

What's Changed

• Turn off guide caching by @torymur in #1278

New Contributors

• @torymur made their first contribution in #1278

Full Changelog: 0.1.4...0.1.5

Outlines v0.1.4

What's Changed

• Bump to outlines-core=0.1.17 for python 3.12-3.13 support by @mgoin in #1273

New Contributors

• @mgoin made their first contribution in #1273

Full Changelog: 0.1.3...0.1.4

Outlines v0.1.3

What's Changed

• Add PDF cookbook by @cpfiffer in #1256
• Add earnings reports to cookbook index by @cpfiffer in #1255
• Add a receipt processing cookbook by @cpfiffer in #1249
• Update README.md by @scampion in #1258

New Contributors

• @scampion made their first contribution in #1258

Full Changelog: 0.1.2...0.1.3

Outlines v0.1.2

What's Changed

• Doc corrections by @cpfiffer in #1213
• Add transformers vision cookbook with atomic caption flow by @fearnworks in #1216
• docs: update llamacpp.md by @eltociear in #1231
• Earnings report cookbook by @cpfiffer in #1235

New Contributors

• @fearnworks made their first contribution in #1216

Full Changelog: 0.1.1...0.1.2

Outlines v0.1.1

The 0.1.0 included a version of outlines-core for which wheels where not available, causing many errors for users who don't have a Rust compiler installed. We fixed this in outlines-core, but changes to the interface where pushed in the meantime so we have to account for these before cutting this new release.

What's Changed

• Logits processors: Update inplace, with batch operation by @lapp0 in #1192
• Fix Broken Docs Links by @lapp0 in #1195
• use dottxt-ai/outlines not outlines-dev/outlines in mkdocs by @lapp0 in #1194
• Add docs on serving with LM Studio by @cpfiffer in #1205
• Compatibility updates for next outlines-core release by @lapp0 in #1204

Full Changelog: 0.1.0...0.1.1

Outlines v0.1.0

⚡ Performance Improvements

• Outlines Core: Enjoy faster FSM index construction with a new implementation (#1175).
• 98% Reduction in Runtime Overhead: Reduced overhead by storing FSM-token-mask as tensors. (#1013)

🚀 New Features

• Transformers Vision Models: Apply structured generation with vision + text inputs (#1052)
• OpenAI-Compatible API Support: Use models.openai with any OpenAI-like API (e.g. vLLM, ChatGPT), including structured generation with generate.json and generate.choice (#1142).

💡 Enhancements

• Unified Logits Processors: All models now use shared outlines.processors, completed by adding the following to the integration: llama-cpp, vLLM and ExLlamaV2).
• Custom Regex Parsers: Simplify the implementation of custom Guide classes with Regex Parser support (#1039).
• Qwen-style Byte Tokenizer Support: Now compatible with Qwen-style byte tokenizers (#1153).

🐛 Bug Fixes

• CFG Beta: Fixed large number of bugs to enable beta version grammar-based generation using Lark (#1067)
• Fixed incorrect argument order breaking some models in models.transformers_vision (#1077).
• Resolved OpenAI fallback tokenizer issue (#1046).
• Option to disable tqdm bars during inference with vLLM (#1004).
• models.llamacpp no longer includes implicit max_tokens (#996).
• Fixed whitespace handling for models.mlxlm (#1003).
• models.mamba now working, and supporting structured generation (#1040).
• Resolved pad_token_id reset issue in TransformerTokenizer (#1068).
• Fixed outlines.generate generator reuse causing runtime errors (#1160).

⚠️ Breaking Changes

• outlines.integrations is now deprecated: #1061

Full Changeset

• Add contributors, creation and update date by @rlouf in #1000
• Add SimToM prompt recipe by @kstathou in #1002
• Ensure models.llamacpp Doesn't Have Implicit max_tokens by @lapp0 in #996
• fix models.mlxlm whitespace prefix handling by @lapp0 in #1003
• Adding the option to avoid displaying tqdm bars at inference with vllm by @BIMM99 in #1004
• Update pyproject.toml, enable mlx-lm requirement only on darwin, disable vllm requirement on darwin by @lapp0 in #1005
• Add asknews example by @robcaulk in #1008
• Improve outlines.processors, add integration tests to test_generate.py by @lapp0 in #998
• Abridged version of the .txt article on Coding For Structured Generat… by @willkurt in #1012
• RegexFSM: Cache Legal-Token Mask as torch.Tensor to Improve Performance by @lapp0 in #1013
• JSON response format fix by @rshah713 in #1029
• Fix broken link in README.md regarding Serving with vLLM by @shinohara-rin in #1030
• Major bug & fix: Fix bug in batched multi sample generation by @JulesGM in #1025
• Update file contributors style for docs by @gtsiolis in #1034
• fix: ocd missing blank space by @talboren in #1036
• Adds support for custom regex parsers (for multimodal structured generation) by @leloykun in #1039
• Update models.transformers to use SequenceGeneratorAdapter and OutlinesLogitsProcessors by @lapp0 in #966
• Use outlines.processors for models.llamacpp by @lapp0 in #997
• Add QA with Citations example to the Cookbook by @alonsosilvaallende in #1042
• Fix mamba integration by making it a variant of outlines.models.transformers by @lapp0 in #1040
• fix PyPI name for autoawq by @davanstrien in #1045
• add fallback tokenizer by @JerryKwan in #1046
• Update cerebrium instructions by @milo157 in #1047
• Add Knowledge Graph Extraction example to the Cookbook by @alonsosilvaallende in #1049
• Correct link and add llama-cpp-python installation instructions by @alonsosilvaallende in #1051
• Introduce outlines.models.transformers_vision by @lapp0 in #1052
• Use outlines.processors and SequenceGeneratorAdapter for outlines.models.vllm by @lapp0 in #1053
• Modal documentation: fix deprecated memory= parameter by @Perdu in #1057
• Documentation: Fix failing Modal example by @Perdu in #1058
• Add links to the two examples by @alonsosilvaallende in #1062
• Add link to Multimodal Structured Generation (MMSG) library to docs by @leloykun in #1064
• Correct the documentation to disable caching by @alonsosilvaallende in #1069
• Fix TransformerTokenizer pad_token_id reset by @ispobock in #1068
• Fix link to mamba model reference by @rlouf in #1072
• More detailed mlxlm documentation by @lapp0 in #1074
• Add chain of thought example by @alonsosilvaallende in #1087
• Fix coverage exclude_lines setting for ellipsis by @brandonwillard in #1089
• Add ReAct agent example by @alonsosilvaallende in #1090
• Include SPDX license info in project metadata by @tiran in #1094
• Update Documentation by @lapp0 in #1063
• Make model_class required arg, default processor_class to AutoProcessor by @parkervg in #1077
• Fix details in the documentation by @rlouf in #1096
• Change cookbook examples: Download model weights in the hub cache folder by @alonsosilvaallende in #1097
• Correct variable name in chain-of-thought example by @cpfiffer in #1101
• Remove deprecated outlines.integrations by @rlouf in #1061
• Use relative coverage source paths by @brandonwillard in #1113
• Add missing CI matrix step by @brandonwillard in #1124
• Update modal example by @cpfiffer in #1111
• docs: fix typo by @billmetangmo in #1120
• Pass text and images as kwargs to VLM processor by @lapp0 in #1126
• Update CFGGuide to use outlines.fsm.parsing. Enable generate.cfg by @lapp0 in #1067
• Include hidden files in coverage CI upload by @brandonwillard in #1136
• Add documentation request issue template by @cpfiffer in #1138
• Set the tokenizer versions in test_create_fsm_index_tokenizer by @brandonwillard in #1139
• Change Outlines' logo by @rlouf in #1143
• Update logo size in documentation by @rlouf in #1144
• Improve sampler docs by @cpfiffer in #1141
• Update vllm.md by @americanthinker in #1137
• Correct pathways, update site color, front page fixes by @cpfiffer in #1146
• Change the color of the logo by @rlouf in #1155
• Remove Broken pyairports Package, Replace with airportsdata by @lapp0 in #1156
• Enable Tokenizers with Byte Tokens by @lapp0 in #1153
• Integrate OpenAI API Structured Generation by @lapp0 in #1142
• Remove link to Outlines twitter account by @rlouf in #1168
• Don't re-use logits processors in SequenceGeneratorAdapter, copy them by @lapp0 in #1160
• Fix benchmark workflow triggers by @brandonwillard in #1170
• Reuse jinja environment for a prompt by @jantrienes in #1162
• Use Faster FSM by @lapp0 in #1175
• Pin outlines-core version by @brandonwillard in #1187
• add missing comma in llamacpp docs by @cpfiffer in https://github.com/dottxt-ai/outl...

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