This pull request includes several updates to the DOCS.md documentation, as well as significant changes to the SemanticChunker and SDPMChunker classes to simplify and improve their functionality. Additionally, there are updates to the pyproject.toml file to reflect the current development status and dependencies.
Documentation Updates:
Improved the tone and clarity of the DOCS.md file, including capitalization and formatting corrections. [1][2]
Added a new FAQ section to the documentation.
Codebase Simplification:
Removed sentence_mode and spacy_model parameters from the SemanticChunker and SDPMChunker classes, focusing on a more streamlined approach. [1][2][3][4][5][6][7]
Updated the sentence splitting method in SemanticChunker to use enhanced regex patterns instead of spaCy.
Dependency and Configuration Updates:
Updated the pyproject.toml to change the development status from "Production/Stable" to "Beta" and adjusted dependencies accordingly. [1][2]
Minor Code Cleanup:
Removed unused imports and parameters in the SentenceChunker class. [1][2]
This pull request includes several updates to the
DOCS.mddocumentation, as well as significant changes to theSemanticChunkerandSDPMChunkerclasses to simplify and improve their functionality. Additionally, there are updates to thepyproject.tomlfile to reflect the current development status and dependencies.Documentation Updates:
DOCS.mdfile, including capitalization and formatting corrections. [1] [2]Codebase Simplification:
sentence_modeandspacy_modelparameters from theSemanticChunkerandSDPMChunkerclasses, focusing on a more streamlined approach. [1] [2] [3] [4] [5] [6] [7]SemanticChunkerto use enhanced regex patterns instead of spaCy.Dependency and Configuration Updates:
pyproject.tomlto change the development status from "Production/Stable" to "Beta" and adjusted dependencies accordingly. [1] [2]Minor Code Cleanup:
SentenceChunkerclass. [1] [2]