Document Summary Agent

A simple document summary agent built with Java 21, Spring Boot, LangChain4j, and Anthropic.

Features

• Upload .pdf, .txt, or .md documents.
• Extract text from the document.
• Chunk large documents.
• Generate a consolidated markdown summary using Anthropic.
• REST API endpoint for summarization.

Tech Stack

• Java 21
• Spring Boot 3.5.0
• LangChain4j
• Anthropic API
• Apache PDFBox

Configuration

Set your Anthropic API key:

export ANTHROPIC_API_KEY=your_key_here

Run

./mvnw spring-boot:run

or

mvn spring-boot:run

API

POST /api/documents/summarize

Multipart form field:

• file: PDF, TXT, or Markdown file

Example:

curl -X POST http://localhost:8080/api/documents/summarize \
  -H "Content-Type: multipart/form-data" \
  -F "file=@sample.pdf"

Notes

• Large documents are chunked and summarized in stages.
• The final response returns markdown summary text.