Extend

Parse API

The Parse API converts unstructured documents into structured context for agents, enabling them to understand and process the content effectively. This feature allows users to handle various document types and layouts, ensuring accurate data extraction and processing.

Extract API

The Extract API enables users to extract structured data from documents into any predefined schema. This feature is crucial for organizations that need to convert raw document data into usable formats for analysis or integration into other systems.

Split API

The Split API segments multi-document files into individual subdocuments, allowing users to manage and process documents more efficiently. This feature is particularly useful for handling large files that contain multiple documents in a single submission.

Classify API

The Classify API categorizes documents into predefined categories, streamlining the organization and retrieval of information. This feature helps users quickly identify the type of document they are dealing with, enhancing workflow efficiency.

Edit API

The Edit API detects form fields and fills them programmatically, automating data entry processes. This feature reduces manual effort and increases accuracy by ensuring that data is entered consistently and correctly.

Agentic OCR

Agentic OCR is a feature that allows for the recognition of text within images and scanned documents, enabling users to extract information from non-digital sources. This capability enhances the versatility of document processing by incorporating various input types.

Workflows

Workflows provide end-to-end orchestration for complex document processing pipelines. Users can build multi-step workflows that parse, split, extract, validate, and route documents, ensuring a streamlined and efficient processing experience.

Studio and Evals

Studio and Evals empower users to iterate on schemas, run evaluations, and catch regressions in a user-friendly interface. This feature simplifies the process of refining document processing models and ensures high-quality outputs.

Composer & Review Agent

The Composer & Review Agent feature allows users to optimize document processing by automatically identifying issues and refining schemas based on uploaded examples. This capability enhances accuracy and reduces manual intervention.

Multiple performance modes

This feature allows users to toggle between performance modes optimized for speed, cost, or accuracy. By selecting the appropriate mode, users can tailor the processing to meet their specific needs and constraints.

Fast mode

Fast mode is designed for low-latency processing, making it ideal for real-time use cases. Users can switch to this mode to ensure quick responses and efficient handling of urgent document processing tasks.

Self-hosted deployments

Self-hosted deployments allow organizations to run the document processing solution entirely on their infrastructure. This feature is essential for companies that need to keep sensitive documents in-house while maintaining speed and accuracy.

HIPAA Compliance and BAA add-on

This feature ensures that the document processing solution meets HIPAA compliance standards, providing an additional layer of security for sensitive healthcare data. Organizations can opt for this add-on to safeguard their data handling practices.

Advanced RBAC, SSO, & SAML

Advanced Role-Based Access Control (RBAC), Single Sign-On (SSO), and Security Assertion Markup Language (SAML) features enhance security by providing robust user authentication and access management. This is crucial for organizations that require strict control over user permissions.