Skip to content

Start building

Integration · Docs and data

AI agents for Nanonets

Extract data from invoices, receipts, purchase orders, IDs and other documents with your Nanonets OCR models.

Actions
5
Read
3
Write
2

Actions

What your agents can do in Nanonets

Extract data from invoices, receipts, purchase orders, IDs and other documents with your Nanonets OCR models: send a document's web address and get back each field and table the model finds, look up past results, and remove files from a model.

Read 3

Look things up. Nothing changes.

  • Get a file's result

    Returns the result for one file sent earlier, by its request_file_id.

  • List results between two dates

    Returns every file the model processed between two dates (UTC) with its results, split into moderated_images.

  • Get the model

    Returns the model's details: model_id, model_type, state and categories (the fields it extracts, each with how many training examples it has).

Write 2

Create, change or send.

  • Extract data from a document

    Sends a document by its public web address (or as base64) to a Nanonets OCR model and returns what it read.

  • Delete a fileDeletes data

    Removes a processed file and its results from the model, by the file's ID (the id of its page entry or its request_file_id).

A person can approve first

Any write action can be set to wait for a person's approval before it runs, so an agent asks before it changes anything. Actions that delete data ask first by default.

Connection

How it connects

Connect it once in the console, then give it to the agents and workflows that need it.

Username and key

Enter the API credentials from your Nanonets account.

What you enter

  • API key

Settings

  • Model ID

Kept safe

  • Credentials are stored encrypted with your organization's own keys.
  • They are opened only by the process that makes the call, at the moment it runs, and never go into a prompt or the browser.
  • Calls go only to the tool's own servers.

How we protect your data

Ideas

Ideas to start with

Starting points made only from the actions above. Mix them with any other tool your agents can use.

  • 01

    Ask about your Nanonets data

    Ask a question in plain words. The agent can get a file's result, list results between two dates or get the model in Nanonets, then answers with what it found.

  • 02

    Let an agent update Nanonets

    Have the agent extract data from a document or delete a file in Nanonets as part of a larger task. Turn on approval and a person signs off on each change first.

  • 03

    Share what it finds in Slack

    Give one agent Nanonets and Slack: it can get a file's result in Nanonets and post a summary to a Slack channel in the same run.

FAQ

Nanonets and MyDeepAgents

Can MyDeepAgents connect to Nanonets?

Yes. The Nanonets connector has 5 actions: 3 read and 2 make changes. Your agents can call them as tools, and your workflows can run them as steps.

How do I connect Nanonets?

Enter the API credentials from your Nanonets account. You'll need: API key. The connection also asks for: Model ID. Credentials are stored encrypted with your organization's own keys and are opened only at the moment of a call.

Can an agent change data in Nanonets without asking?

Only if you let it. Each of the 2 actions that change data can be set to wait for a person's approval before it runs, and the one that deletes data asks first by default.

Can I use Nanonets in workflows as well as agents?

Yes. Every Nanonets action also works as a step in a workflow, and the same connection serves your agents and your workflows.

Early access

Put Nanonets to work

Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.