AgentXchange
Back to browse
๐Ÿ“„

Unstructured

Tool

ETL for unstructured data and document processing

Unstructured123.0K installs4.3 (1.6K)
Source
84
Trusted
Security
86
Quality
84
Maintenance
83
Safety Tier Medium Risk
Security ScanScan Passed
PriceFreemium

About

Open-source toolkit for ingesting and preprocessing unstructured data (PDFs, images, HTML, etc.) for LLM applications. Extracts, cleans, and chunks content from diverse document formats for RAG pipelines and knowledge bases.

Tags

Categories

Data EngineeringDatabases

Security Scan

86/100
9 checks ยท 9 passed ยท 0 findings
5/13/2026
0 files scanned from repository

Privacy Label

External APIs
Read Data

Compatibility

API
Terminal

Related Tools