Unstructured.io
Unstructured · Data analysis · US · www.unstructured.io
services/unstructured-io.yamlVendor data-handling terms
Unstructured parses documents for RAG pipelines; the policy does not say whether processed documents improve its models.
“The Service's use and transfer to any other app of information received from Google APIs, including Google Drive data from a Google account connected to the Service, will adhere to the Google API Services User Data Policy , including the Limited Use requirements .In particular, we do not transfer, sell, or use user data obtained through the Google Worksp”
“We retain personal information for as long as necessary to fulfill the purposes for which we collected it, including for the purposes of satisfying any legal, accounting, or reporting requirements, to establish or defend legal claims, or for the compliance and protection purposes described above.”
“We are headquartered in the United States and may use service providers that operate in the United States and other countries.”
Domains and endpoints
observed means seen in Unseen deployments; vendor-documented means listed by the vendor. Vendors do not publish complete lists.
| Host | Role | Source |
|---|---|---|
| api.unstructured.io | api | observed |
Assessment
Reasoning: A document-parsing API used to feed internal documents into RAG systems. The hosted API sees whole documents; the policy covers Google data well but not training on processed content or region. The open-source library runs locally.
Flags: Training-use of processed documents not stated · US processing · Assessed 2026-09-16. The assessment is Unseen's; the terms above are the vendor's.
Changelog
- 2026-09-16Documented. Google API, retention and location terms verified against the Unstructured privacy policy.
- 2026-09-15Listed from the Unseen catalogue with observed domains.
Corrections
Pull request on GitHub, or the form below. Changes are reviewed and recorded in the changelog.