yobix-ai/

extractous

GitHub

Extractous is a Rust-based core for fast unstructured data extraction with Python bindings. It focuses on text and metadata extraction across many formats, using native Rust and optional Tika-backed formats.

1.8kstars

97forks

33issues

Apache-2.0license

2024since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

huggingface/

transformers

▲ 266/wk

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

163k34kPython

rasbt/

LLMs-from-scratch

▲ 487/wk

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

101k15kJupyter Notebook

hiyouga/

LlamaFactory

▲ 162/wk

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

74k9.0kPython

rohitg00/

ai-engineering-from-scratch

▲ 1.3k/wk

Learn it. Build it. Ship it for others.

46k7.9kPython

google/

langextract

▲ 54/wk

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

38k2.6kPython

PaddlePaddle/

PaddleOCR

▲ 532/wk

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

87k11kPython

Compareextractous vs transformers extractous vs LLMs-from-scratch extractous vs LlamaFactory

Reviewgenerated from repository data · Aug 5, 2026

What it is

Extractous is a Rust core for high-performance unstructured data extraction with bindings for Python and planned bindings for other languages. It targets fast text and metadata extraction from multiple document formats, including those supported by Apache Tika, and supports OCR via tesseract-ocr.

How it works

The project combines a Rust core with language bindings (Python currently) and uses GraalVM ahead-of-time compiled native shared libraries for non-natively supported formats via Apache Tika, enabling in-process parsing without external services. It includes OCR for images and scanned documents via tesseract-ocr. The README provides usage patterns for Python and Rust, showing a consuming builder pattern to configure extraction, and methods to extract to strings or streams.

Getting started

Examples are provided for Python:

from extractous import Extractor
extractor = Extractor()
extractor = extractor.set_extract_string_max_length(1000)
result, metadata = extractor.extract_file_to_string("README.md")

from extractous import Extractor
reader, metadata = extractor.extract_file("tests/quarkus.pdf")

And for OCR:

from extractous import Extractor, TesseractOcrConfig
extractor = Extractor().set_ocr_config(TesseractOcrConfig().set_language("deu"))

Rust usage shows the corresponding API with Extractor::new() and methods like set_extract_string_max_length, set_xml_output, extract_file_to_string, and extracting via streams.

Recent releases

The latest release section shows: - none

Traction

The repository has 1769 stars and 97 forks; open issues are 33.

Behind the repo

Label indicates yobix-ai as the author; no startup/company link is provided beyond the project scope.

Caveats

License is Apache-2.0. Created 2024-06-04; last push 2024-12-21. The README notes OCR requirements (Tesseract) and dependencies on GraalVM for Tika-backed formats.

SharePost on X LinkedIn