Search results for document extraction

High-performance document intelligence library

Go to Download

Metadata and content analysis service - This extension detects and extracts metadata (EXIF / IPTC / XMP / ...) from potentially thousand different file types (such as MS Word/Powerpoint/Excel documents, PDF and images) and bring them automatically and natively to TYPO3 when uploading assets. Works with built-in PHP functions but takes advantage of Apache Tika and other external tools for enhanced metadata extraction.

Go to Download

A lightweight PHP library to convert PDF documents into clean, structured Markdown. Supports text extraction, headings, lists, tables, diagrams and code blocks for easier content reuse and publishing.

Go to Download

Laravel AI Document Intelligence & OCR package for Laravel 12 AI SDK. Convert PDF to JSON, extract tables, image to text, Ask PDF with AI, audio transcription and multi-language support using GPT-5.2, Claude and Gemini.

Go to Download

PHP 8.2+ library for PDF text extraction with automatic reader selection. Supports embedded text and scanned documents via OCR.

Go to Download

Laravel OCR package — extract text from images, PDFs, invoices, receipts using Tesseract, Claude Vision, OpenAI GPT-4o. Supports barcode, QR code, table extraction, multi-language OCR, AI cleanup, and document templates. Zero Guzzle dependency.

Go to Download

Core document processing services for OCR, classification, extraction, and normalization.

Go to Download

High-performance German document OCR - Local & Cloud API

Go to Download

A Laravel PDF text extraction package with multiple strategies (PdfParser, XObject, AWS Textract, Tesseract OCR). Handles Canva-generated PDFs, scanned documents, and other edge cases with automatic fallback.

Go to Download

High-performance document intelligence for PHP. Extract text, metadata, and structured information from PDFs, Office documents, images, and 75 formats. Powered by Rust core for 10-50x speed improvements.

Go to Download

Official PHP SDK for the DocXtract document extraction API

Go to Download

A powerful library for manipulating and converting PDF files.

Go to Download

Core of ai-kit: document ingestion, chunking, extraction, vector retrieval (sqlite-vec + pgvector), and RAG agents built on the official Laravel AI SDK.

Go to Download

PHP FFI bindings for LiteParse, fast local PDF and document parsing with spatial text extraction

Go to Download

Laravel-native document text and schema extraction with provenance and AI cost tracking.

Go to Download