62 dependents
| Package | Description | Downloads/month |
|---|---|---|
| Democratizing AI scientists with ToolUniverse | 126K | |
| "Document AI repo for data science" | 10K | |
| Resolved the issue of incorrect quantity extraction in OCR text caused by a wate... | 4K | |
| This repository contains a Python program designed to extract Optical Character ... | 1K | |
| FREDtools repository | 1K | |
| A libary for office operator | 728 | |
| Open source Python CLI toolkit for conversion, manipulation, Analysis of files (... | 576 | |
| PDF2TEXT LIBRARY : Update extract condition (image/no image) | 467 | |
| 统一的异步工具库，支持文件、数据库、时间、日志等多种操作 | 407 | |
| A custom Flask package with PDF processing tools | 309 | |
| 289 | ||
| Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-pro... | 257 | |
| 220 | ||
| Package to save CSV as PNG | 213 | |
| 182 | ||
| Extracts images from PDFs, stores them in S3, and retrieves based on keyword sea... | 171 | |
| 153 | ||
| Topik-aware semantic search untuk dokumen hukum berbasis vectorstore, dan pembua... | 143 | |
| A Python package to compare files (PDF, docx, images) and generate reports in tx... | 137 | |
| 133 | ||
| A microservice using FastAPI, PostgreSQL, OpenSearch, and LangChain. | 132 | |
| Image converter and resizer for research publication. | 132 | |
| 128 | ||
| 128 | ||
| 125 | ||
| 123 | ||
| Proteus data extractor File | 122 | |
| 121 | ||
| 119 | ||
| 118 | ||
| 113 | ||
| 113 | ||
| 113 | ||
| A library for converting PDF to HTML and vice versa | 109 | |
| 103 | ||
| 102 | ||
| 102 | ||
| 100 | ||
| 99 | ||
| 96 | ||
| 94 | ||
| 92 | ||
| 91 | ||
| 84 | ||
| Convert PDF files to Markdown with OCR support | 82 | |
| Topik-aware semantic search untuk dokumen hukum berbasis vectorstore, dan pembua... | 82 | |
| 81 | ||
| 70 | ||
| Tired of main_fixed.py? File summarizer and context manager for AI agents. / 告别m... | 70 | |
| 66 |
