Kreuzberg Cloud
Extracts structured content from 101 file formats, parses source code in 371 languages, enriches with LLMs, and provides retrieval and RAG capabilities.
A document intelligence and RAG platform that extracts structured, machine-readable content from documents and feeds it into AI pipelines. It solves the problem of ingesting and processing diverse file formats for AI applications. The platform targets developers and data teams in B2B settings, offering open-source primitives and a managed backend. It is positioned as a self-hostable, open-source solution with support for 101 file formats, 371 programming languages, and 165 LLM providers.
Key features
- Extract from 101 file formats
- Parse 371 programming languages
- Enrich via 165 LLM providers
- Native SDKs for 15 languages
- Web crawling and ingestion
- Hybrid retrieval and reranking
- Structured extraction and OCR
- Code-aware retrieval and search
- No social media activity within the last 30 days
GTM channels
- Partner program
- Community
- API
ICP
- Software developers
- Data analytics teams
- Engineering teams