NagentArtefacts
Dev & Technology
Enterprise and White Glove
Company
Nanonets connects to a Nagent workspace with an API key. Once it is connected, agents can call 11 Nanonets actions, such as "Create Model", "Get All Models" and "Get All Prediction Files". Nothing is enabled on connect: each action is allowed one at a time, and an action with side effects runs or waits for a person according to the agent's level.
Every operation an agent can call against Nanonets, with input parameters and output schema.
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
Agents can call 11 Nanonets actions on Nagent, including "Create Model", "Get All Models" and "Get All Prediction Files". Create Model: Create a new image classification or OCR model. Each action is listed on this page with its input parameters and its output.
Nanonets connects with an API key, under your workspace's own connection. Nothing is enabled on connect: each action is allowed one at a time and can be scoped to the agents that need it.
Create Model takes 1 required input: categories. It returns data, error and successful.