Unstructured
Open-source partitioning of PDFs and other documents into structured elements for LLM pipelines.
Jobs Extract
Operated by Unstructured Technologies, Inc.
Opens the vendor's own site.
Jobs covered
Open a task to see exactly what the vendor documentation supports.
Extract
Browse all extract toolsextracting structured content from documents with the open-source Unstructured library: partitioning PDFs, images, HTML, Word/Office, email, EPUB and other supported files into typed elements (Title, NarrativeText, ListItem, Table, etc.), with PDF/image strategies auto/fast/hi_res/ocr_only, optional table inference, coordinates/page breaks and OCR languages/backends, returning element data for downstream pipelines. The scope records local document partitioning/extraction only; it excludes searchable-PDF creation, PDF editing, redaction, signing, accessibility validation, hosted Transform/Pipelines/API use, inherited hosted data/compliance claims and any accuracy guarantee
Where your files are processed
Reported to stay on your device
Claimed by the vendor. Not yet independently verified. That is a property of the library itself: what an application built with it does with your file depends on that application, not on this.
The open-source library runs on the caller's own machine/container and partitions documents locally. Exceptions: the optional hosted API/Transform/Pipelines are separate services, and the library sends lightweight telemetry to packages.unstructured.io by default (package/platform/version, partition characteristics and aggregate counts; no document content) unless DO_NOT_TRACK or SCARF_NO_ANALYTICS is set.
'Local' describes document processing, not zero network traffic.
What it does
Unstructured turns a document into a list of typed elements - titles, narrative text, tables, list items - that a language-model pipeline can work with, across PDFs, images, HTML, Word and many other formats. The open-source library (currently 0.27.28, 16 October 2026, Python >=3.11,<3.14, Apache-2.0) runs locally in a container or virtual environment and offers PDF strategies such as auto, fast, hi_res and ocr_only, with optional table inference, coordinates and OCR backends (Tesseract/Paddle etc. installed separately).
It is the ingestion step: it reads documents and returns element data, not a searchable PDF, editor, redactor or accessibility validator. The same company sells hosted Transform API/Pipelines products (10,000 free pages then $0.015/page), which are separate services with their own terms and are not inherited into this local record.
The library sends lightweight telemetry by default; DO_NOT_TRACK or SCARF_NO_ANALYTICS disables it.
Best for
Anyone building a retrieval or model-training pipeline who needs one interface across many file types and does not want to write a parser per format. The open-source library is the reason to choose it over hosted competitors, and it is credible for PDFs specifically.
Worth knowing
The library sends telemetry by default: a library-load ping and a best-effort per-partition call to packages.unstructured.io, with package/platform/version, partition characteristics and aggregate element counts, but no document content. Set DO_NOT_TRACK or SCARF_NO_ANALYTICS before import to disable both.
Its PDF handling has fast/hi_res/ocr_only strategies; higher accuracy pulls in large deep-learning/OCR dependencies and models, so a production install is much heavier than the base package. Tesseract/Poppler/LibreOffice and optional OCR/ML backends are separate system dependencies with their own licences.
The hosted Transform API/Pipelines are commercial, per-page services (10,000 free pages then $0.015/page) and are not the open-source library; do not inherit their terms, data handling or service claims into this record. It partitions/returns elements (with optional tables/coordinates), but does not write searchable PDFs, edit/redact/sign PDFs, perform accessibility validation or guarantee extraction accuracy.
The local library has telemetry but does not upload document content by default.
Details, and where each comes from
Vendor statements, our own reading of their pages, and the things nobody has established yet, each answered separately. Where we have not confirmed something it says so rather than guessing, and a row nobody has established is greyed out.
- Versions covered
- Self-hosted · Linux · Windows · macOS
- Website
- github.com
- Requires an account
- Not applicable
- Free tier
- Yes
- Watermark on the free tier
- Not verified
- Maximum file size
- Not verified
- Batch processing
- Yes
- Data residency
- Not verified
- Open source
- Yes
- Self-hostable
- Yes
- Licence
-
Apache-2.0 for the open-source `unstructured` library.
Apache-2.0 for the open-source `unstructured` library. The hosted API/Transform and managed Pipelines are separate commercial products, not covered by this licence; no hosted terms are inherited into the local record.
System tooling (python-magic/libmagic, poppler, tesseract, libreoffice) and optional OCR/ML backends keep their own licences.
- Redaction
- No redaction feature
- Programmatic access
- Embeddable library
- Last availability check
- Responded in 464 ms 21 October 2026
Checked automatically by our own runner, not reported by the vendor. 100% of our last 30 checks got a response.
What the redaction verdict rests on
From the vendor's own documentation, read 22 September 2026. Not tested by us.
“The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. The use cases of unstructured revolve around streamlining and optimizing the data processing workflow for LLMs.”
What that does not establish
Recorded as `none` because partitioning is a read-only operation: the library converts a document into elements and does not write a PDF back, so there is no redaction feature and no output file in which hidden content could survive. The basis is the library's own description of its purpose, quoted above, so this is absence from a feature set rather than a test.
What it does not establish: that elements returned by the library are an anonymised view of the document. Text extracted from a document carries whatever was in it, so a partitioning step is not a sanitising step and should not be used as one.
What the vendor says
Claims are labelled rather than repeated as fact. Where we have checked something ourselves, it says so and shows when. Checked means we read the vendor's own page and it says what we recorded - not that we tested the behaviour, unless the note says we did.
-
“Unstructured sends lightweight analytics to GET https://packages.unstructured.io/python-telemetry by default: one library-load ping when it is imported and one best-effort local attempt for each top-level public partition call.”
Checked by us - the source says this Read 16 October 2026
Confirmed. The quoted text appears in the rendered page as read on 2026-10-01.
This claim was carried as reported rather than checked until this read.
Standing: Not re-read against the live source
Check it yourself: the source, the SHA-256, and how we checked
- From
- the text a browser renders
- SHA-256
- 0dc1c4b4bc2bc78544047eb787b2c3972ee95ccc3fd3f14f07842df4def8181f
How we checked
Read as rendered text in headless Chrome on 2026-10-01 and saved to the evidence archive, so the read can be repeated against the same file. Comparison ignores case, punctuation and hyphenation, which is why "open-source" on the record matches "open source" on the page.
-
“Start processing your data with 10,000 free pages.”
Checked by us - the source says this Read 16 October 2026
Confirmed. The quoted text appears in the rendered page as read on 2026-10-01.
This claim was carried as reported rather than checked until this read.
Standing: Not re-read against the live source
Check it yourself: the source, the SHA-256, and how we checked
- From
- the text a browser renders
- SHA-256
- 6bafbb0705e3593f82e113fd08b9cbd6248798baa2c64214c91af3e42fa02939
How we checked
Read as rendered text in headless Chrome on 2026-10-01 and saved to the evidence archive, so the read can be repeated against the same file. Comparison ignores case, punctuation and hyphenation, which is why "open-source" on the record matches "open source" on the page.
Each claim is quoted from the vendor's own pages. This section describes what we have and have not checked - it is not a judgement about anyone.
Sponsorship is distribution, not an endorsement or a promise of search rankings, AI citations, traffic, or sales. This listing is a free entry, compiled from published sources.
Related reading
- Open source PDF tools, and what their licences require - what open source does and does not tell you.