For UnstructuredAI Platform

Tables And Layout

Unstructured (API + Platform) · Unstructured

Document ETL for LLMs — Unstructured (API + Platform)

Unstructured evals — Tables & Layout (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	Agent expects table HTML in metadata.text_as_html but did not set infer_table_structure=true, so Table elements have only flat text.	Set infer_table_structure=true so Table elements carry metadata.text_as_html with row/column structure. Without it, tables degrade to unstructured text. Verify text_as_html is present before relying on table structure downstream.	Pass / FailAi Platformhigh
02	Operator needs to highlight source regions in a viewer using metadata.coordinates, but the elements were produced with strategy=fast and have no coordinates.	Coordinates (bounding boxes + coordinate system) are produced by the layout model (hi_res). To support source highlighting, run hi_res and read metadata.coordinates.points with its coordinate_system; do not fabricate boxes when they are absent.	Pass / FailAi Platformmedium
03	A Table element carries metadata.text_as_html. The agent strips the HTML to plain text before indexing, collapsing the grid.	Preserve text_as_html (or parse it into structured rows/cells) so column/row relationships survive. For RAG, embed a structured or markdown rendering of the table rather than a row-joined blob that loses cell alignment.	Pass / FailAi Platformhigh
Use this eval