> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Nanonets

> Nanonets provides an AI-driven Intelligent Document Processing API that transforms unstructured documents into structured data, enabling efficient data extraction and workflow automation.

![Nanonets logo](https://mintcdn.com/composio-preview/9YPuzjEU4UlMnwGq/images/toolkits/nano_nets.svg?fit=max\&auto=format\&n=9YPuzjEU4UlMnwGq\&q=85\&s=93008f82e403525b6e842ea5abf59897)

* **Category:** ai document extraction
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 11
* **Triggers:** 0
* **Slug:** `NANO_NETS`
* **Version:** 20261101\_00

## Tools

> [accordion] Create Model
>
> **Slug:** `NANO_NETS_CREATE_MODEL`
>
> Create a new OCR model with a list of categories or fields to extract, before uploading training images.
>
> #### Input Parameters
>
> **categories** `array` *required*
>
> 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** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete OCR Model
>
> **Slug:** `NANO_NETS_DELETE_MODEL`
>
> Permanently 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
>
> **model\_id** `string` *required*
>
> The unique identifier (UUID) of the OCR model to delete. Get this from the 'Get all OCR models' action.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get All Models
>
> **Slug:** `NANO_NETS_GET_ALL_MODELS`
>
> Retrieve image classification models in the user's NanoNets account, including available model details and categories.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get All Prediction Files
>
> **Slug:** `NANO_NETS_GET_ALL_PREDICTION_FILES`
>
> Retrieve a page of OCR prediction files for a Nanonets model, with available prediction details such as extracted text and field values. Choose a page and page size from 1 to 500; a 404 response is presented as an empty result.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number for pagination (must be >= 1)
>
> **model\_id** `string` *required*
>
> Unique identifier of the NanoNets OCR model to fetch prediction files from
>
> **page\_size** `integer`
>
> Number of prediction files per page (1-500)
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get OCR Model Details
>
> **Slug:** `NANO_NETS_GET_MODEL_DETAILS`
>
> Tool to retrieve details of an OCR model. Use when you need full metadata of a model by its ID.
>
> #### Input Parameters
>
> **model\_id** `string` *required*
>
> Unique identifier of the OCR model to retrieve details.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get OCR Training Images
>
> **Slug:** `NANO_NETS_GET_TRAINING_IMAGES`
>
> Retrieve a page of training images associated with an OCR model for inspection before training or analysis. Specify the page and page size; a 404 response is presented as an empty result.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number for pagination (1-indexed). Defaults to 1.
>
> **model\_id** `string` *required*
>
> Unique identifier (UUID) of the OCR model. Obtain this from the GET\_ALL\_MODELS action or model creation response.
>
> **page\_size** `integer`
>
> Number of images to return per page. Defaults to 50.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Workflows
>
> **Slug:** `NANO_NETS_GET_WORKFLOWS`
>
> Retrieve the workflows in a Nanonets account to inventory or inspect their configurations.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Workflow Documents
>
> **Slug:** `NANO_NETS_LIST_DOCUMENTS`
>
> Retrieve a paginated list of documents processed by a NanoNets workflow, with basic metadata, processing status, verification status, and page information.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number for pagination (1-indexed). Defaults to 1 if not specified.
>
> **limit** `integer`
>
> Number of documents per page. Defaults to 50 if not specified.
>
> **workflow\_id** `string` *required*
>
> The unique identifier (UUID) for the NanoNets workflow. Obtain this from the GET\_WORKFLOWS action or from the NanoNets dashboard.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Model AI Guidelines
>
> **Slug:** `NANO_NETS_UPDATE_MODEL`
>
> Update 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
>
> **model\_id** `string` *required*
>
> Unique identifier of the OCR model to update AI guidelines for.
>
> **field\_instructions** `string` *required*
>
> Instructions for the AI model to follow during field predictions. Provide guidance on how to extract and validate field data.
>
> **table\_instructions** `string` *required*
>
> Instructions for the AI model to follow during table predictions. Provide guidance on how to identify and extract tabular data.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Upload Training Images by File
>
> **Slug:** `NANO_NETS_UPLOAD_TRAINING_IMAGES_BY_FILE`
>
> Tool 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
>
> **file** `object` *required*
>
> The image file to upload for training. Supported formats: PNG, JPEG, PDF.
>
> **model\_id** `string` *required*
>
> Unique identifier of the OCR model to which the image will be uploaded.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Upload Training Images by URL
>
> **Slug:** `NANO_NETS_UPLOAD_TRAINING_IMAGES_BY_URL`
>
> Upload one or more publicly accessible image URLs to a specified Nanonets OCR model for training.
>
> #### Input Parameters
>
> **urls** `array` *required*
>
> List of publicly accessible image URLs to upload for training.
>
> **model\_id** `string` *required*
>
> Unique identifier of the OCR model to which the images will be uploaded.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
