create_model
Create Model
Create a new AI model in Nanonets. Supports OCR document extraction, image classification, and object detection model types. Define the categories or fields you want the model to recognize.
Supported Tools
list_processed_files
List Processed Files
List all files that have been processed by a Nanonets model within a date range. Returns both moderated (reviewed) and unmoderated files with their extraction results and review status.
extract_document_data
Extract Document Data
Upload a document to a Nanonets OCR model and extract structured data. Supports processing documents via URL. Returns extracted fields, tables, bounding boxes, and confidence scores. Use synchronous mode for small documents (≤3 pages) and async mode for larger files.
upload_training_data
Upload Training Data
Upload training images via URL to a Nanonets model. Supports OCR, image classification, and object detection models. For classification models, images must be associated with a category. For OCR and object detection, annotations with bounding boxes can be provided.
get_prediction_results
Get Prediction Results
Retrieve extraction/prediction results for a previously processed document. Use this to check the status of async predictions or to retrieve detailed results by file ID or page ID.
review_file
Review File
Approve or unapprove a processed file in a Nanonets model. Approval marks the file's extracted data as verified. Unapproval reverts an approved file back to the unreviewed state.
retry_file_processing
Retry File Processing
Retry predictions or exports for previously processed files. Use this when files failed to process correctly or when exports need to be re-triggered.
get_model
Get Model
Retrieve details about a Nanonets model including its current state, configured categories, and training status. Works for OCR, image classification, and object detection models.
extract_full_text
Extract Full Text
Extract the complete raw text from documents or images using Nanonets OCR. Unlike structured extraction, this returns all text found in the document without field mapping. Useful for getting the raw content of PDFs, scanned documents, and images.
detect_objects
Detect Objects
Detect and locate objects within images using a trained Nanonets object detection model. Returns bounding box coordinates and confidence scores for each detected object.
classify_image
Classify Image
Classify images into predefined categories using a trained Nanonets image classification model. Provide one or more image URLs and receive category labels with probability scores.
train_model
Train Model
Initiate training for a Nanonets model. Supports OCR, image classification, and object detection models. Training data must be uploaded before training can start.
More integrations teams use with Nanonets
Linear
Create, read, update, and delete issues across teams with support for priorities, labels, assignees, due dates, and workflow states. Manage projects that group related issues, and organize work into time-boxed cycles (sprints). Create and manage documents, comments, and file attachments. Search issues using vector similarity or rich filters. Configure teams, workflow states, and labels. Track customers and link them to issues. Subscribe to real-time webhooks for changes to issues, projects, cycles, comments, documents, and more.
GitHub
Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.
Sharepoint
Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Subscribe to webhooks for list and library change notifications. Retrieve site properties and search for sites across Microsoft 365.
Salesforce
Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Subscribe to real-time change events via Change Data Capture and Platform Events. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.
Microsoft Outlook
Send, read, reply to, forward, and manage email messages in user mailboxes. Organize messages into folders, apply categories, flags, and importance levels. Manage file and item attachments. Create, update, delete, and respond to calendar events and meetings. Find available meeting times, manage attendees, handle recurrence, and work with shared or delegated calendars. Create, read, update, and delete contacts, organize them into contact folders, and manage contact photos. Manage tasks and task lists via Microsoft To Do, including due dates, reminders, recurrence, and checklist items. Subscribe to webhook notifications for changes to messages, calendar events, and contacts. Support for Focused Inbox, @-mentions, mail tips, send-on-behalf, and send-as capabilities.
Airtable
Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.
Technical notes for Nanonets
Extract structured data from unstructured documents using AI-powered OCR and deep learning. Create and manage document processing workflows to extract fields and tables from invoices, receipts, forms, purchase orders, bank statements, and other document types. Upload documents as files or URLs for synchronous or asynchronous processing, receiving extracted data with confidence scores and bounding boxes. Train custom image classification and object detection models with labeled data. Manage human-in-the-loop review processes including approving, rejecting, and moderating extracted predictions. Apply post-processing transformations such as date formatting, currency detection, regex matching, lookup enrichment, and custom Python scripts. Import documents from email, Dropbox, Google Drive, OneDrive, and SharePoint. Export processed data to Google Sheets, QuickBooks, Xero, Salesforce, databases (PostgreSQL, MySQL, MSSQL), and other platforms. Receive webhook notifications on document processing, approval, rejection, and assignment events.
Frequently asked questions
Common questions about connecting Nanonets to AI agents with Metorial.
Can Metorial connect Nanonets to AI agents?
Yes. Metorial connects AI agents to Nanonets through a governed integration layer, so teams can use the provider while keeping access controlled and observable.Does the Nanonets integration work with MCP?
Metorial is MCP compatible and lets teams expose approved provider tools to MCP-capable agents and clients through a controlled access layer.How does Metorial control access to Nanonets?
Metorial applies policies across users, groups, providers, agents, and individual tools, then records the context around every agent interaction.Can teams trace Nanonets activity from agents?
Yes. Metorial records provider activity so teams can inspect tool calls, troubleshoot integrations, and give security teams the visibility they need.