PyPI page
Home page
Author:
tianleG
Summary:
Structure-aware Markdown, HTML, and DOCX lumber pipeline for RAG preprocessing
Latest version:
0.7.0
Required dependencies:
markdown-it-py
|
openpyxl
|
python-docx
|
pyyaml
|
tomli
Optional dependencies:
aspose-email-foss
|
cachetools
|
fastapi
|
haystack-ai
|
langchain-core
|
langchain-text-splitters
|
llama-index-core
|
markitdown
|
python-multipart
|
python-pptx
|
starlette
|
tiktoken
|
transformers
|
tree-sitter
|
tree-sitter-bash
|
tree-sitter-c
|
tree-sitter-c-sharp
|
tree-sitter-cpp
|
tree-sitter-go
|
tree-sitter-java
|
tree-sitter-javascript
|
tree-sitter-kotlin
|
tree-sitter-lua
|
tree-sitter-php
|
tree-sitter-python
|
tree-sitter-ruby
|
tree-sitter-rust
|
tree-sitter-swift
|
tree-sitter-typescript
|
tree-sitter-zig
|
uvicorn
Downloads last day:
6
Downloads last week:
224
Downloads last month:
148
7-day smoothing