
ETL library that turns documents into clean data for LLMs
Do you work on Unstructured Technologies?
This listing is unclaimed. Claim it for free to edit the details, add screenshots and reply to reviews.
Unstructured is a document preprocessing tool for teams building retrieval and RAG pipelines. It reads PDFs, HTML, Word, PowerPoint and many other file types, then splits them into clean, structured elements ready for an LLM. It began as an open source library and also offers a hosted service for connectors and larger jobs. AI engineers use it to feed messy company documents into vector databases and models. A free tier is available.
From people who have used it. One review per person, checked by a human.
No reviews yet. Be the first to say something useful.