text-extraction

OCR It is a Chrome extension that extracts text from un-copyable documents using local OCR, designed to help users prepare content for LLMs like Claude or ChatGPT.

The Firecrawl team open-sourced pdf-inspector, a fast Rust library that automatically determines whether a PDF is text-based or scanned, directly extracts text and converts it to Markdown, avoiding unnecessary OCR, supports table and multi-column layout detection, and provides Python/Node.js/Rust/WASM interfaces.

The author describes building a test suite for their CV PDF to ensure it is parseable by applicant tracking systems, and experimentally checks whether disabling ligatures affects pdftotext output.

Introducing the open-source project ai-knowledge-graph, which can automatically split long documents into chunks, extract triples, and generate an interactive knowledge graph as HTML. It's compatible with the OpenAI API as well as local models, making it useful for research and document organization.

The author explains why a customer's PDF bank statement showed all amounts as negative: the PDF encodes invisible trailing minus signs in a gray level matching the background, which the extraction code reads as visible text. They discuss solutions like OCR or stripping non-black text.

Modelence Mobile App Builder launches on ProductHunt, enabling users to create a document management web app with a mobile app that uses the phone camera to scan and extract text.

This article presents a technique to embed hidden markdown structure inside PDFs using the PDF spec's replacement text property, enabling LLMs to extract clean, structured data while humans see the same visual document.

pdf-inspector is an open-source Rust library for intelligently classifying PDF types (text or scanned), extracting text, and converting to Markdown, avoiding unnecessary OCR to improve speed and save costs.

Jerry Liu discusses challenges with using Vision Language Models for PDF parsing, particularly around ensuring text correctness and maintaining proper reading order while avoiding hallucinations.

Firecrawl unveils pdf-inspector, a fast Rust library for PDF classification and text extraction that converts text-based PDFs to Markdown without OCR, with bindings for Python, Node.js, and WebAssembly.

abiruyt/text-extract-ocr is an open-source OCR model available on Replicate, running on CPU with low cost and fast inference.