Nanonets updates
Nanonets updates

Faster date parsing in post processing




The Extract date from text post processing should now be significantly faster and save upto 1-2 seconds in API response time if set on your model

Fuzzy matching on databases




The Derive field from database post processing and the Match databases validation have both been updated to also support fuzzy matching. The fuzzy matching runs a LIKE query on your database

For eg: Let's say the data extracted from your document was Apple and the Vendor name on your invoice was Apple Inc, Nanonets would now be able to match these data points and associate them.

Screenshot 2021-10-05 at 9.28.37 PM.png

Auto-fill fields from your database






Now derive a new field from your database, based on a field extracted from your image.

Set up post-processing on any field on your document using the Operation 'Derive field from database'. Specify the table and columns to match from and choose which column to derive the field from.


Powerful Table Structure and Custom Table Training!






Now capture tables of any type and only extract the cells you want. The tables can have dynamic structures and the model will learn the data you want to extract. It will learn to extract only the data you need and ignore all the others.

Multiple cells can be extracted from the same row or column leading to more flexibility creating the most powerful table extraction tool in the world.

Op-10(Fast, small).gif

It's super easy to annotate and train for the data you want to extract. Draw boxes around any text of interest even if it has no clearly defined boundaries and Nanonets will learn to extract that information

Easier Field Type Setup





Now access your field type setup more easily!


From the Build Section

Screen Shot 2021-04-26 at 3.53.42 PM.png


From the Extract Section

Screen Shot 2021-04-26 at 4.02.29 PM.png


Edit Directly in Place from the Build Section

Screen Shot 2021-04-26 at 3.53.56 PM.png

More Integrations! - Postgresql and Mariadb





You can now export all your data to Postgresql and Mariadb on a successful prediction from Nanonets or on verifying data.

Screen Shot 2021-04-26 at 3.50.24 PM.png

New Integrations for Export





You can now write data directly from Nanonets into a business application like your MySQL database, Salesforce CRM or Quickbooks accounting software. So any document processed can be directly added to the next step of your business process. You can also set it up to only add data once the files have been verified.

Screen Shot 2021-03-25 at 7.33.08 PM.png

To get started with this go to your model and click on Auto Export.

Screen Shot 2021-03-25 at 7.36.26 PM.png

Validations, Field Types and Postprocessing





We are introducing new Validations, Field Types and Postprocessing to allow for additional rules on top of the predictions made by the AI. This gives users greater control on making sure the data is returned exactly in the format they are looking for

Validation Feedback on the test screen:

Screen Shot 2021-02-12 at 3.30.11 PM.png

Specify 3 types of rules for each field:

  1. Postprocessing - makes changes to data predicted by Machine Learning
  2. Formatting - make formatting changes to output data in the format you want
  3. Validations - checks if a field matches specified rules

Screen Shot 2021-02-12 at 3.29.41 PM.png

Every File and Prediction now has a Url





We have enabled deep linking within our app such that every image and associated prediction or annotation on Nanonets has a unique Url. This makes it easier to share and collaborate.

New Urls look like:

Share this with your team so they know exactly what you are talking about.

You can easily generate a link for this by clicking Generate Sharable Link from inside each file.

Nanonets on your own Website!





You can now white-label and embed Nanonets into your app or server it through your own domain. Follow this article to get setup. Process files and give your users the best experience without ever leaving your app or website.