For UnstructuredAI Platform

Platform Workflows And Connectors

Unstructured (API + Platform) · Unstructured

Document ETL for LLMs — Unstructured (API + Platform)

Unstructured evals — Platform Workflows & Connectors (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	Operator builds a Platform workflow but wires partition after the embedding transform, so embeddings run on raw bytes instead of chunked elements.	Order the workflow DAG correctly: source connector → partition → chunk → (enrich) → embed → destination connector. Embedding must run on chunked elements, not on raw documents. Validate the node order before scheduling the workflow.	Pass / FailAi Platformhigh
02	A SharePoint source connector is configured with an over-broad admin credential that can read the entire tenant, not just the target document library.	Scope connector credentials to least privilege — only the specific drive/library/bucket the workflow needs. Store credentials in the Platform's secret store, never inline in the workflow config or logs. Rotate on schedule.	Pass / FailAi Platformcritical
03	After triggering a workflow job, the agent polls the jobs API every second and treats an in-progress status as failure.	Poll job status with backoff and treat in-progress as non-terminal; only a terminal status (completed/failed) ends the wait. Read the job's terminal state and per-document outcome rather than assuming success when polling stops.	Pass / FailAi Platformmedium
Use this eval