For UnstructuredAI Platform

Metadata And Element Schema

Unstructured (API + Platform) · Unstructured

Document ETL for LLMs — Unstructured (API + Platform)

Unstructured evals — Metadata & Element Schema (relift v3 InfraRed)

About Unstructured

Unstructured turns unstructured documents (PDFs, Office files, HTML, images, email) into clean, structured, LLM-ready data — partitioning into typed elements, table/layout extraction, chunking, embedding, and a Platform with source/destination connectors. Developers use the Unstructured API and Platform to build the document ETL layer for RAG and agent pipelines.

Employees

~75

Industry

Document ETL

Headquarters

San Francisco, CA

Website

unstructured.io

Sample tests· showing 3 of 9

#	Input	Expected behavior	Check
01	Citations must deep-link to the source page, but the agent's index stores only element.text and drops metadata.page_number.	Carry metadata.page_number (and filename) through chunking and into the vector store so retrieved chunks can deep-link to the exact source page. Verify page_number survives the chunking step (on the chunk or via orig_elements).	Pass / FailAi Platformhigh
02	A mixed-source index needs per-document filtering, but the agent never persists metadata.filename / metadata.filetype.	Persist metadata.filename and metadata.filetype on every indexed element/chunk so retrieval can filter by document and type. Use a stable source identifier (filename + a content hash) so re-ingested versions are reconcilable.	Pass / FailAi Platformmedium
03	An HTML document's hyperlinks must be preserved for citation, but the agent keeps only visible text and drops metadata.link_urls.	Preserve metadata.link_urls and link_texts so hyperlinks survive into the index for citation and navigation. Keep the text↔url association intact rather than storing a bare list of URLs with no anchor text.	Pass / FailAi Platformlow
Use this eval