Home Unstructured
Unstructured
Unstructured is an open-source ETL solution that converts complex documents into structured data for language models, featuring enterprise-grade capabilities like workflow orchestration, document partitioning, enrichment, chunking, and embedding.
Language
HTML
Latest Release
0.18.22
License
Apache License 2.0
Key Features
- Transforms unstructured documents into structured data
- Enterprise-grade workflow automation
- Supports partitioning, enrichment, and embedding
- Optimized for extracting data for language models
- Open-source and production ready
Alternative Tools
Resources
Community
Stars
13.4k
Open Issues
233
Forks
1.1k