Docling
Docling is an easy-to-use, self-contained, MIT-licensed open source toolkit for converting messy documents into structured data and simplifying downstream document and AI processing. It can parse many popular document formats into a unified and richly structured Docling Document, including PDF, DOCX, PPTX, XLSX, HTML, Markdown, AsciiDoc, CSV, images, audio, and scanned pages through an OCR engine of the user’s choice. Docling detects tables, formulas, reading order, chunks, bounding boxes, page headers and footers, pictures, captions, code, list items, paragraphs, cells, and document structure, making extracted content easier to process, search, and ingest into AI, RAG, and agentic systems. It can export parsed documents to JSON, text, Markdown, HTML, and Doctags, giving developers flexible outputs for pipelines and applications. Docling stores and traverses components according to reading order, partitions documents into bite-sized contiguous text chunks.
Learn more about Docling
OpenText Capture Center
OpenText Capture Center (formerly DOKuStar Capture Suite) uses the most advanced document and character recognition capabilities available to turn documents into machine-readable information. Capture Center captures the data “stored” in scanned images and faxes and interprets it using OCR, ICR, IDR, adaptive reading and other technologies. Capture Center reduces manual keying and paper handling, accelerates business processing, improves data quality, and saves you money. Reduce errors and improve the quality of data entering your ECM or ERP systems through rule-based classification, extraction and verification. One-click and manual exception handling further improves accuracy. Pulling from sources such as high-end scanning devices, Multifunction Peripherals (MFPs), file system folders, email servers, Microsoft® SharePoint® servers and FTP sites, OpenText Capture Center quickly and efficiently captures and digitizes documents, forms and faxes.
Learn more about OpenText Capture Center
T-NEX Document AI
T-NEX Document AI is a configurable document-processing solution for organizations moving information from business documents into downstream workflows. T-NEX scopes projects around document types, required fields, sample documents, target data structures and review rules. The workflow can classify documents, extract specified values, link them to their sources, and flag unclear or missing information for human review. Approved data can be handed off in an agreed format, such as a file or project-specific API connection. Evaluation uses representative documents and varied layouts to assess recognition results and correction effort for selected fields. It is intended for SMEs, startups and industrial or other business teams handling documents such as order confirmations and reports. The solution is delivered as a custom project, with integrations and direct posting scoped individually.
Learn more about T-NEX Document AI
Tungsten Express
High-speed scanning with real-time image display, indexing, and barcode detection. Improve business processes, reduce costs and reliance on paper, improve records management and compliance with Tungsten Express. Anyone can quickly scan, index, and export documents for fast retrieval. Execute commands with a single click for faster adoption and greater productivity. Multiple scan and image processing functions can run simultaneously to provide the highest throughput possible. Index, classify, and deliver documents and data into more than 100 different back-end systems for easy and fast retrieval. Express supports direct integration with Tungsten Capture and provides an API for advanced exports. Utilize SmoothView technology to manipulate document images. Integrated Tungsten VirtualReScan (VRS) technology ensures images will look better than their paper originals without pre-scan document preparation.
Learn more about Tungsten Express