Kreuzberg

What it is

Kreuzberg is a high-performance document extraction library with a Rust core, supporting over 62 formats including PDF, Office documents, images with OCR, HTML, email, and archives. It's ideal for developers needing to extract text and metadata from various file types efficiently.

Kreuzberg stands out with its high-performance Rust core and support for over 62 document formats, making it an ideal choice for developers needing efficient extraction capabilities in various file types without the need for cloud services.

When it fits — and when it doesn’t

Known weaknesses

Each one links to the public issue, changelog or docs page it came from, where we have one.

1. 01

   Limited direct support for non-Rust languages

   Primary language is Rust, and while there are community-maintained SDKs for other languages like TypeScript, they may not be as robust or up-to-date.

2. 02

   Complex setup process

   Setting up Kreuzberg requires a deep understanding of Rust package management and dependencies which can be challenging for developers unfamiliar with the ecosystem.

3. 03

   Documentation lacks examples for advanced use cases

   While there is extensive documentation, it tends to focus more on basic usage rather than complex scenarios or edge cases that some users might encounter.

What it does well

• Supports over 62 document formats including PDF, Office documents, images with OCR, HTML, email, and archives.

• High-performance extraction using Rust core.

• Extensive documentation and community support.

Pricing

Free tier

YesOpen source — free to use

Paid from

$0

Model

Flat rate

Enterprise plan

No

Pricing not independently confirmed — check the vendor’s page.