Alternatives and similar repositories for benchmarks

Users that are interested in benchmarks are comparing it to the libraries listed below

• pypdfium2-team / pypdfium2
  Python bindings to PDFium, reasonably cross-platform.
  ☆656Updated this week
• Unstructured-IO / unstructured-inference
  ☆194Updated last week
• datalab-to / pdftext
  Extract structured text from pdfs quickly
  ☆613Updated 4 months ago
• docling-project / docling-parse
  Simple package to extract text with coordinates from programmatic PDFs
  ☆205Updated this week
• isaacus-dev / semchunk
  A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.
  ☆390Updated 2 months ago
• poloclub / unitable
  UniTable: Towards a Unified Table Foundation Model
  ☆509Updated last year
• docling-project / docling-core
  A python library to define and validate data types in Docling.
  ☆194Updated this week
• docling-project / docling-ibm-models
  ☆156Updated this week
• explosion / spacy-layout
  📚 Process PDFs, Word documents and more with spaCy
  ☆778Updated 7 months ago
• xhluca / bm25s
  Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy
  ☆1,358Updated last month
• MinishLab / semhash
  Fast Semantic Text Deduplication & Filtering
  ☆816Updated 2 weeks ago
• adobe / pdfservices-python-sdk-samples
  Adobe PDFServices python SDK Samples
  ☆159Updated 3 months ago
• conjuncts / gmft
  Lightweight, performant, deep table extraction
  ☆514Updated 2 months ago
• DS4SD / DocLayNet
  DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis
  ☆393Updated 2 years ago
• lfoppiano / streamlit-pdf-viewer
  Streamlit PDF viewer
  ☆181Updated last month
• getomni-ai / benchmark
  OCR Benchmark
  ☆583Updated 4 months ago
• ShayHill / docx2python
  Extract docx headers, footers, (formatted) text, footnotes, endnotes, properties, and images.
  ☆192Updated last week
• IBM / fastfit
  FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes
  ☆212Updated last month
• AmenRa / retriv
  A Python Search Engine for Humans 🥸
  ☆237Updated last year
• PrithivirajDamodaran / FlashRank
  Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cro…
  ☆872Updated last month
• AmenRa / ranx
  ⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍
  ☆601Updated 2 months ago
• pymupdf / PyMuPDF-Utilities
  Demos, examples and utilities using PyMuPDF
  ☆685Updated last year
• zafercavdar / fasttext-langdetect
  80x faster and 95% accurate language identification with Fasttext
  ☆161Updated last year
• lightonai / pylate
  Late Interaction Models Training & Retrieval
  ☆626Updated this week
• pymupdf / pymupdf4llm
  PyMuPDF4LLM
  ☆1,078Updated 3 weeks ago
• houfu / redlines
  Show the differences between two strings/text as a compact text, in markdown/HTML, in the terminal and more.
  ☆144Updated last week
• stephenleo / llm-structured-output-benchmarks
  Benchmark various LLM Structured Output frameworks: Instructor, Mirascope, Langchain, LlamaIndex, Fructose, Marvin, Outlines, etc on task…
  ☆179Updated last year
• philschmid / document-ai-transformers
  ☆385Updated last year
• vespa-engine / pyvespa
  Python API for https://vespa.ai, the open big data serving engine
  ☆145Updated last week
• allenai / pawls
  Software that makes labeling PDFs easy.
  ☆420Updated last year