Nanonets provides an AI-driven Intelligent Document Processing API that transforms unstructured documents into structured data, enabling efficient data extraction and workflow automation.
Nanonets provides an AI-driven Intelligent Document Processing API that transforms unstructured documents into structured data, enabling efficient data extraction and workflow automation. On Nagent, Nanonets is exposed as a fully-configurable ai document extraction integration that any agent can call — 11 actions, and API key authentication. No code is required to wire Nanonets into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Nanonets 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 Nanonets 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 Nanonets, with input parameters and output schema. Drop these into any step of an agent built in Helix.
NANO_NETS_CREATE_MODELTool to create a new image classification or OCR model. Use when you need to initialize a model before uploading training images. Provide a list of categories/classes that the model should learn to identify or extract.
Input parameters
List of category/class names for the model to identify. For image classification, provide labels like \['cat', 'dog'\]. For OCR extraction, provide field names to extract like \['invoice_number', 'date', 'total'\].
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
NANO_NETS_DELETE_MODELPermanently deletes an OCR model from Nanonets. Use this action when you need to remove a trained model that is no longer needed. This action is irreversible - once deleted, the model and all its training data cannot be recovered. Prerequisites: Obtain the model_id from the 'Get all OCR models' action first.
Input parameters
The unique identifier (UUID) of the OCR model to delete. Get this from the 'Get all OCR models' action.
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
NANO_NETS_GET_ALL_MODELSRetrieves all models (OCR and Image Classification) in the user's NanoNets account. Returns model details including ID, type, status, accuracy, and extractable fields/categories. Use to discover available models before performing predictions or training operations.
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
NANO_NETS_GET_ALL_PREDICTION_FILESRetrieve all prediction files (OCR results) for a NanoNets model. Use this tool to: - List all documents/images that have been processed by an OCR model - Get prediction results including extracted text and field values - Access file URLs and processing status for each prediction The response includes prediction labels with extracted text, confidence scores, and bounding box coordinates for each processed file.
Input parameters
Page number for pagination (must be >= 1)
Unique identifier of the NanoNets OCR model to fetch prediction files from
Number of prediction files per page (1-500)
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
NANO_NETS_GET_MODEL_DETAILSTool to retrieve details of an OCR model. Use when you need full metadata of a model by its ID.
Input parameters
Unique identifier of the OCR model to retrieve details.
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
NANO_NETS_GET_TRAINING_IMAGESTool to retrieve training images for an OCR model. Use when you need to page through images associated with a model before training or analysis.
Input parameters
Page number for pagination (1-indexed). Defaults to 1.
Unique identifier (UUID) of the OCR model. Obtain this from the GET_ALL_MODELS action or model creation response.
Number of images to return per page. Defaults to 50.
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
NANO_NETS_GET_WORKFLOWSTool to retrieve a list of all workflows in your Nanonets account. Use when you need to inventory or inspect all configured workflows.
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
NANO_NETS_LIST_DOCUMENTSRetrieve a paginated list of documents processed by a NanoNets workflow. Returns document metadata including processing status, upload timestamp, verification status, and page details. Use this to monitor document processing progress or access extracted data from previously uploaded documents.
Input parameters
Page number for pagination (1-indexed). Defaults to 1 if not specified.
Number of documents per page. Defaults to 50 if not specified.
The unique identifier (UUID) for the NanoNets workflow. Obtain this from the GET_WORKFLOWS action or from the NanoNets dashboard.
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
NANO_NETS_UPDATE_MODELUpdate AI Agent guidelines for an OCR model. Sets instructions for how the AI should handle field and table predictions. Only works for Instant Learning models. Use this to customize extraction behavior for specific document types.
Input parameters
Unique identifier of the OCR model to update AI guidelines for.
Instructions for the AI model to follow during field predictions. Provide guidance on how to extract and validate field data.
Instructions for the AI model to follow during table predictions. Provide guidance on how to identify and extract tabular data.
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
NANO_NETS_UPLOAD_TRAINING_IMAGES_BY_FILETool to upload a training image file to a specified OCR model. Use when adding a local image file to train the model. Supported file formats include PNG, JPEG, and PDF.
Input parameters
The image file to upload for training. Supported formats: PNG, JPEG, PDF.
Unique identifier of the OCR model to which the image will be uploaded.
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
NANO_NETS_UPLOAD_TRAINING_IMAGES_BY_URLTool to upload training images by URL to a specified OCR model. Use when adding URLs of images to a model for training purposes.
Input parameters
List of publicly accessible image URLs to upload for training.
Unique identifier of the OCR model to which the images will be uploaded.
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 99 agents privately built on Nagent that already use Nanonets.
Build on Nagent
Connect Nanonets 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 Nanonets, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Nanonets is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Nanonets is connected, you configure its 11 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Nanonets 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 Nanonets event fires, the agent kicks off automatically.
Every Nanonets 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 Nanonets ships with 11 pre-built ai document extraction actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Nanonets together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Nanonets-based workflows tailored to your business.