Metadata-Version: 2.1
Name: parserllm
Version: 0.0.1
Summary: Force LLMs to use a specific context-free grammar in completions
License: MIT
Keywords: llm,ai,prompt,large language models,gpt-3,chatgpt
Author: Matt Rickard
Author-email: pypi@matt-rickard.com
Maintainer: Matt Rickard
Maintainer-email: pypi@matt-rickard.com
Requires-Python: >=3.11,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Requires-Dist: lark (>=1.1.5,<2.0.0)
Requires-Dist: regex (>=2023.5.5,<2024.0.0)
Requires-Dist: rellm (==0.0.5)
Requires-Dist: transformers (>=4.28.1,<5.0.0)
Project-URL: repository, https://github.com/r2d4/parserllm
Description-Content-Type: text/markdown

# parserLLM

Use a context-free grammar and a parser generator to determine valid next tokens for an LLM generation. See [examples/example.py](examples/example.py) for an example of how to use this library. Run it with `python examples/example.py`.
