AI & Machine Learning
Connect Nanonets to Your AI Agents
Let your Wkil agents run and train image/document extraction models through Nanonets.
Authentication: Basic auth
What you can do
- Run OCR/ML predictions on images and documents
- Train custom extraction models
Available capabilities may vary by authentication and workspace configuration.
Actions supported by the connector
12 verified tools
Prediction for Image File
Run a trained model's prediction on an uploaded image file.
Prediction for Image URL
Run a trained model's prediction on an image at a given URL.
Async Prediction for Image File
Queue an asynchronous prediction job for an uploaded image.
Train Model
Start training a model on the uploaded dataset.
Upload training images by File
Upload labeled training images directly as files.
Get All Prediction Files
List all files that have been run through prediction.
View all verified tools (search)
Get Prediction File By Page IDGet All Prediction FilesGet Prediction File By File IDPrediction for Image FileAsync Prediction for Image FilePrediction for Image URLAsync Prediction for Image URLUpload training images by UrlUpload training images by FileTrain ModelPrediction for image URLsPrediction for image File
Practical agent use cases
- An agent extracts structured data from an uploaded invoice image automatically.
- An agent trains a new extraction model as fresh labeled samples arrive.
How it works with Wkil
- 1Choose the integrationAdd Nanonets to your agent from inside the Wkil platform.
- 2Grant the permissions it needsDefine precisely what the agent can access and perform.
- 3Test, then run itTest actions before they go live, with human approval where needed.
Permissions always stay in your control — you can scope access and require human approval before any sensitive action.
Related integrations
FAQ
Do I need my own Nanonets account?
Yes — access is scoped to your Nanonets account credentials.