Vibe Coding Discover

RAG

docling-java

View on GitHub

A Java API for Docling

★ 13930 forksJavaMITdocling-project

Docling Java is the official Java API for IBM's Docling document processing stack. It parses PDFs, Office files, images and audio into a unified DoclingDocument, exporting Markdown, HTML, DocTags or JSON for RAG and GenAI pipelines.

Use Cases

Parse PDFs, DOCX, PPTX, XLSX and HTML into structured documents for RAG ingestionConvert documents to Markdown, HTML, DocTags or lossless JSONOCR scanned PDFs and imagesExtract page layout, reading order and table structureTranscribe audio (WAV, MP3, VTT) with ASR modelsCall a remote Docling Serve backend from Java appsRun Docling in Docker via Testcontainers for integration testsFeed parsed documents into LangChain4j pipelinesAir-gapped/local document processing for sensitive data

Built With

Language
Java
Frameworks
LangChain4j · Jackson · Testcontainers · Gradle · JUnit · Java HttpClient

Tags

docling · document-parsing · pdf · ocr · rag · java · document-conversion · markdown · langchain4j · testcontainers · docling-serve · vlm · asr · table-extraction · knowledge-pipeline · doclingdocument