Extract text, tables, metadata, and images from 91+ document formats.
npx skills add https://github.com/vaayne/agent-kit --skill kreuzberg-vaayne
Please help me install this Agent Skill. Skill: kreuzberg Source: https://github.com/vaayne/agent-kit/tree/main/skills/kreuzberg Command: npx skills add https://github.com/vaayne/agent-kit --skill kreuzberg-vaayne
Kreuzberg automates the extraction of text, tables, metadata, and images from 91+ document formats, enabling rapid digitization and analysis of diverse files.
Run Kreuzberg on a sample document to extract text, tables, metadata, and images.
High-intent search queries and answers about installing and using this skill.
To extract text and tables from multiple document formats for batch processing, this tool automates ingestion across 91+ formats including PDFs, Office documents, HTML, and emails. It handles batch extraction efficiently and outputs structured data ready for analytics pipelines.
The best way to prepare document extractions for semantic search and embeddings is to use a tool that outputs structured, chunked text. This extraction Skill provides configurable chunking options and embeddings-ready outputs directly from 91+ document formats.
Yes, you can use OCR to extract text from scanned PDFs and images. This extraction tool supports OCR backends to capture text from image-heavy files, ensuring accurate digitization and metadata retrieval for analytics.
Yes, this document extraction tool supports archives and email formats. It extracts text, tables, metadata, and embedded images from a wide range of 91+ formats including HTML, emails, and Office documents.
You can configure chunking and output formats for extracted document data using configurable CLI options. The tool allows you to specify output formats and chunking parameters to tailor the extraction results for server use or analytics ingestion.
Monjyu1101Extract text from PDFs and scanned documents using pymupdf and marker-pdf.
zainhasGenerate text embeddings via the Together AI embeddings API.
MSamiulHasnatIndex embeddings and perform context-aware similarity queries for document retrieval.
devMoezExtract text and structured content from PDFs and scanned documents into Markdown.
