kreuzberg

🥇Gold

Kreuzberg is a versatile document intelligence framework built on a Rust core, enabling extraction of text, metadata, and structured information from a wide array of formats including PDFs and Office documents. It supports multiple programming languages and can be accessed via CLI or REST API, making it ideal for developers seeking strong document processing solutions.

7,5032230Updated Today

Intermediate15 minutes to implementdevelopment

Saves ~150 min per use

Quick InstallView Source

claude install kreuzberg-dev/kreuzberg

Works with:

GitHub Copilot

Overview

About This Skill

How to Use

["1. **Install Kreuzberg**: Follow the installation instructions on the official Kreuzberg documentation to set up the framework on your local machine or server.","2. **Prepare Your Document**: Ensure the document you want to process is in one of the supported formats (PDF, DOCX, etc.) and is accessible from your system.","3. **Run the Extraction Command**: Use the Kreuzberg CLI or REST API to run the extraction command. For example, if using the CLI, you might run: `kreuzberg extract --input Q3_Financial_Report.pdf --output results.json`.","4. **Review the Output**: Check the output file (e.g., `results.json`) to verify that the extracted data is accurate and complete. Adjust the command parameters if necessary to refine the results.","5. **Integrate into Your Workflow**: Once satisfied with the extraction, integrate the Kreuzberg command into your existing document processing workflow to automate the extraction of metadata and text content."]

Use Cases

Extracting data from invoices for financial analysis and reporting.

Automating document processing workflows in CRM systems to improve efficiency.

Generating structured reports from unstructured text to facilitate data analysis.

Enhancing search capabilities in document repositories for faster information retrieval.

Best For

GrowthRevOps

Setup & Installation

Quick Install

Terminal

claude install kreuzberg-dev/kreuzberg

Alternative Install (Git Clone)

git clone https://github.com/kreuzberg-dev/kreuzberg

Requirements

Claude Code or compatible AI agent
Works with: GitHub Copilot

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Extract the key metadata and text content from the document '[DOCUMENT_NAME]' in [FORMAT]. Identify the main topics discussed, any important dates mentioned, and the author's name if available. Return the results in JSON format with separate fields for metadata, topics, dates, and author.

Example Output

```json
{
  "metadata": {
    "document_name": "Q3_Financial_Report.pdf",
    "format": "PDF",
    "page_count": 28,
    "creation_date": "2023-10-15",
    "last_modified": "2023-10-20"
  },
  "topics": [
    "Quarterly Financial Performance",
    "Market Trends",
    "Future Outlook",
    "Risk Assessment"
  ],
  "dates": [
    "2023-07-01",
    "2023-09-30",
    "2023-10-15"
  ],
  "author": "Jane Doe, CFO"
}
```

The document 'Q3_Financial_Report.pdf' is a 28-page PDF that was created on October 15, 2023, and last modified on October 20, 2023. The main topics covered in the report include the company's quarterly financial performance, current market trends, future outlook, and risk assessment. Key dates mentioned are July 1, 2023, September 30, 2023, and October 15, 2023. The report was authored by Jane Doe, the Chief Financial Officer.