Aryn is an AI-powered platform for document parsing, data extraction, and analytics, enabling users to process and query unstructured documents at scale.
Aryn is an AI-powered platform for document parsing, data extraction, and analytics, enabling users to process and query unstructured documents at scale. On Nagent, Aryn is exposed as a fully-configurable ai document extraction integration that any agent can call — 9 actions, and API key authentication. No code is required to wire Aryn into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Aryn to automate the kinds of tasks ai document extraction teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Aryn into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Aryn, with input parameters and output schema. Drop these into any step of an agent built in Helix.
ARYN_CREATE_DOCSETTool to create a new DocSet. Use when you need to allocate a storage container before adding documents.
Input parameters
String name for the DocSet
Optional schema object defining document properties
Optional dictionary of prompts for the DocSet
Optional dictionary of additional properties
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ARYN_DELETE_DOCSETTool to delete a DocSet and all its documents. Use after confirming the DocSet ID, when you need to permanently remove a DocSet and its contents.
Input parameters
The unique identifier of the DocSet to delete. Format is typically 'aryn:ds-xxxxx' where xxxxx is an alphanumeric string.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ARYN_GENERATE_PLANTool to generate a query plan without executing it. Use when you need to review the logical plan before running your query (e.g., "Generate a plan for revenue breakdown by region").
Input parameters
Natural language query string to generate a plan for. The query will be converted into a logical execution plan with operators.
If true, the query will generate only a RAG (Retrieval Augmented Generation) query plan instead of a full analytics plan.
The unique identifier of the DocSet to query. Format: 'aryn:ds-{id}'. Find DocSet IDs in the Aryn UI or via the list docsets API.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ARYN_GET_DOC_SETTool to retrieve metadata for a specific DocSet by its ID. Use when you need to check DocSet details like name, creation time, properties, or prompts.
Input parameters
Unique identifier of the DocSet to retrieve. Format: 'aryn:ds-<alphanumeric>'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ARYN_GET_DOCUMENTRetrieve a document by ID from Aryn DocParse storage. Returns the document's parsed elements (text, tables, sections with embeddings), custom properties, and optionally the original binary content. Use this after obtaining a docset_id and doc_id from other Aryn actions (e.g., list_docs or add_doc).
Input parameters
The unique identifier of the document to retrieve. Format: 'aryn:f-xxxxxxxxxxxxxxxxxxxx'.
The unique identifier of the DocSet containing the document. Format: 'aryn:ds-xxxxxxxxxxxxxxxxxxxx'.
When true, includes the base64-encoded original document binary data. Set to true only if you need the raw file content.
When true, includes parsed document elements (sections, tables, text blocks, etc.) with their embeddings and text representations. Set to false if you only need document metadata.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ARYN_GET_DOCUMENT_BINARYDownload the original binary content (e.g., PDF, image) of a document from an Aryn DocSet. This action retrieves the raw binary file that was originally uploaded to the DocSet. Use this when you need to access the original document file rather than the parsed elements or extracted text.
Input parameters
The unique identifier of the DocSet containing the document. Format: 'aryn:ds-<alphanumeric_id>' (e.g., 'aryn:ds-n1uckj87hwf2d95kwr5gsh1').
The unique identifier of the document to download. Format: 'aryn:f-<alphanumeric_id>' (e.g., 'aryn:f-8dkwobf4oihjlhz7koqlqfr').
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ARYN_LIST_ASYNC_TASKSTool to list all outstanding asynchronous tasks for the account. Use when you need to check pending or running tasks.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ARYN_PARTITION_DOCUMENTPartition a document using Aryn DocParse to extract and structure its content elements including text, tables, and images. Supports file upload or URL input with extensive processing options for chunking, OCR, table extraction, image extraction, and multiple output formats. Use when you need to extract structured content from PDFs or other document formats.
Input parameters
File to partition. Either file or file_url must be provided.
Comprehensive options for document partitioning
URL of the file to partition. Either file or file_url must be provided.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ARYN_SUBMIT_ASYNC_ADD_DOCTool to submit a document for asynchronous addition to a DocSet. Returns a task ID to track the operation. Use when you need to add documents to an existing DocSet and want to track the processing status.
Input parameters
The file to upload to the Aryn platform. Either 'file' or 'file_url' must be provided, but not both.
DocParse options to use during partitioning, provided as a JSON string.
URL of the file to add to the Aryn platform. Either 'file' or 'file_url' must be provided, but not both.
The unique identifier of the docset to which to add the document. Format: 'aryn:ds-<alphanumeric>'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 32 agents privately built on Nagent that already use Aryn.
Build on Nagent
Connect Aryn to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Aryn, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Aryn is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Aryn is connected, you configure its 9 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Aryn steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Aryn event fires, the agent kicks off automatically.
Every Aryn action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Aryn ships with 9 pre-built ai document extraction actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Aryn together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Aryn-based workflows tailored to your business.