Apache Tika Document Extractor

Wraps Apache Tika Server REST API for extracting structured text from PDFs, DOCX, PPTX, and 1,200+ file formats. Outputs clean markdown with metadata preservation using Tika /rmeta/text endpoint and recursive parsing mode.

Installation

Requirements and caveats from upstream:

• N.B. Docker is used for tests in tika-integration-tests. If Docker is not installed, those tests are skipped.

Basic usage or getting-started notes:

• ===========

• Parse a file in Java:

• java

• Source: https://github.com/apache/tika

• Extracted from upstream docs: https://raw.githubusercontent.com/apache/tika/HEAD/README.md

Source

• Agent Skill Exchange