Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

A Repo For Document AI

ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.

Detectron2 for Document Layout Analysis

[Late Submission] Solution for Kuzushiji recognition (Kaggle competition)

Visual Domain Knowledge-based Multimodal Zoning Textual Region Localization in Noisy Historical Document Images

SegClarity: An attribution-based XAI workflow for layer-wise interpretability in semantic segmentation

Extracting structured text from GI Bill index cards for JDoc 2023 paper

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Analyze document image complexity based on segmentation results

📦 Split buffers and streams into smaller chunks for smooth HTTP uploads and accurate progress tracking.

Document image enhancement using the DIBCO dataset. Applies preprocessing and binarization techniques to restore degraded handwritten and printed documents for better readability and analysis.

🎨 Elevate image editing with EditThinker, enabling iterative reasoning for improved instruction adherence and enhanced visual quality.