Welcome to Reducto! We help AI teams and companies take unstructured data like PDFs, images, and spreadsheets and turn them into structured data to enhance products, gather insights, and create LLM pipelines.
This guide provides an overview of our flexible toolkit of API endpoints, example use cases, configuration best practices, and answers frequently asked questions. For more code specific information on our endpoints, refer to our API reference.
If you have any questions unanswered, feel free to reach out to our team at support@reducto.ai.
These API endpoints are the building blocks for all your document ingestion needs. You can use them individually, or in conjunction to make powerful end-to-end pipelines. Read more about each below, and check out our customizable configurations that can suit your every need.
Upload a local file to Reducto for downstream processing.
Parse all content in a document and handle post-processing steps like chunking.
Perform structured JSON extraction to pull out specific fields according to your schema.
Split a document into multiple subsections, essentially inferring a table of contents.
Across all industries, unstructured data is rampant. There are infintely many great use-cases we’ve seen amongst our customers, utilizing Reducto’s APIs to build knowledge graphs, RAG-based pipelines, and even industry specific AI agents. Here are some of the documents we can process:
If you’re looking for types of files we can support, read here.
For beginners, we show you the easiest way to call our APIs.
See visual examples of how Reducto works and test out your own sample documents and schemas!
Learn about new features, practical tips, and company announcements.
The best place to stay up to date on all things Reducto!
If you’re interested in building with us, we’re always looking to meet talented people!
Welcome to Reducto! We help AI teams and companies take unstructured data like PDFs, images, and spreadsheets and turn them into structured data to enhance products, gather insights, and create LLM pipelines.
This guide provides an overview of our flexible toolkit of API endpoints, example use cases, configuration best practices, and answers frequently asked questions. For more code specific information on our endpoints, refer to our API reference.
If you have any questions unanswered, feel free to reach out to our team at support@reducto.ai.
These API endpoints are the building blocks for all your document ingestion needs. You can use them individually, or in conjunction to make powerful end-to-end pipelines. Read more about each below, and check out our customizable configurations that can suit your every need.
Upload a local file to Reducto for downstream processing.
Parse all content in a document and handle post-processing steps like chunking.
Perform structured JSON extraction to pull out specific fields according to your schema.
Split a document into multiple subsections, essentially inferring a table of contents.
Across all industries, unstructured data is rampant. There are infintely many great use-cases we’ve seen amongst our customers, utilizing Reducto’s APIs to build knowledge graphs, RAG-based pipelines, and even industry specific AI agents. Here are some of the documents we can process:
If you’re looking for types of files we can support, read here.
For beginners, we show you the easiest way to call our APIs.
See visual examples of how Reducto works and test out your own sample documents and schemas!
Learn about new features, practical tips, and company announcements.
The best place to stay up to date on all things Reducto!
If you’re interested in building with us, we’re always looking to meet talented people!