Getting Started Guide

Welcome to Nanonets!

Welcome to the complete guide to getting started with Nanonets. Learn how to capture data from any document, in any format and in any language in the world. Automate repetitive tasks, even reading data from the most complex documents, and make your team more productive!

Whether you're looking to start a car rental service, share benefits with your loyal customers, onboard more restaurants, verify data for employees you recruit or manage your Accounts Payable, Nanonets helps you effortlessly capture data from any document you can imagine, so that you can focus on what matters to you. You decide how you work, and build the perfect setup for your needs.

Unlike a traditional data extraction system, Nanonets gives you the power of an AI-enabled, template agnostic solution. It is super flexibleconnecting with your information, capturing only what you need, and structuring it as you need it—all in one place.

Who is this guide for?

Technical and non-technical folks, brand-new users to Nanonets, and anyone who just wants to brush up on their Nanonets knowledge.

Signing Up

First sign up on app.nanonets.com to access the Nanonets universe.
All you need to do is:
1. Enter your email address
2. Choose a password
3. Verify the link you receive on your email 

Once you first open up Nanonets, you'll see a panel on the left hand side and a bunch of colorful icons (More on these later).
The left hand side contains all your key account information -

  • My Models: All your models and their unique Model IDs in one place 
  • API Keys: Your API keys to access your model
  • Billing: Contains all your billing history and information
  • Team: Team members that have access to your models


Try Your First Model

When you first open up Nanonets, you'll see a bunch of colorful icons. The icons are different AI models that you can train or use right away. Here are the three ways: 

1. Build your own OCR Model
2. Build your Document Classification Model
3. Use a pre-made Nanonets Model



Building Your Own OCR Model

Let's take a fun fictitious example - Say you are starting a new restaurant business, and want to capture all monthly expenses in a CSV at the end of the month. 

Steps:

1. Upload some pages of your document type to teach the AI Model on the Upload Files screen.

We require a minimum of 10 images to train a custom model. 

How much training data is enough?

We recommend starting with 50 and adding files depending on the accuracy you see. The AI model significantly gets better in reading documents as you show it more data. For a complicated document type you might need 1000 or more files.


2. Specify the fields that you want the AI to capture from your document on the Specify Fields screen. 

In this case, you're labels will look something like this - 


Once you're ready, click on Start Training

Tip

If you already have XMLs to train the AI, click on 3. Train your model at the top of the screen to skip this step. Click on Upload XMLs to directly upload the XML files.

3. Show the AI Model where the fields are present on your pages. 

On the first page, create rectangular boxes around the text associated with each label. Enter the name of the label (or field) you want to associate the text with, and hit SaveThis process is called annotating


We need a minimum of 10 annotations per label to train a model. We recommend starting with 50 and adding more files depending on the accuracy you see. 

Tip

Click on All Files to see all your uploaded files in one place. You can also view the files by categories - All Files, Labelled, and Pending.

Hit Train Model. This kicks off several AI architectures in our backend that compete in a race to find the best accuracy for your model.

It takes about 40 minutes before you can see some magic. Watch your inbox - We'll send you an email once your model is ready!

Pro Tip

You can request us to annotate the data for you for free on the Pro Trial. Click on Upgrade Model to start your free Pro trial



Best Practices to Train the Model

Refer to an in-depth article here to train the best performance model for you: https://nanonets.com/help/ocr/best-practices-for-high-accuracy-models



Pre-made Nanonets Model 

You can quickly use a pre-made Nanonets model for these document types - Invoices, Receipts / Bills, US Driver's Licenses, Passports, Menu Cards. Simply upload your files on the Extract Data screen and review extracted data.

Each of these models is already trained on thousands and thousands of pages and work well out of the box for any language! What's more, that we can quickly enable these models for any additional language.


We frequently add new models to our Product Universe, if you can't find a model for your document type - drop an email to info@nanonets.com and we'll see if we can quickly build one for you. 



Testing your first model using the UI  

Your model is trained and you can see its accuracy on the "Model Metrics" section. You can also see AI machinery behind your model - the different Experiments, aka, AI Architectures contributing to the best model accuracy for your document.

Quick steps to see some AI magic on some unseen documents -

1. Click on the Extract Data screen.

2. Click on Add Files - you can import PDFs or images.


3. Click on the image when it's ready.


You can see the extracted information as bounding boxes on the original image on the left hand side. On the right hand side, you can see the extracted information as text under List View, and the response as returned by the API in the JSON format. 



Verifying extracted data  

Use the Verification feature to correct the fields before exporting your data. Watch this 3 min video to understand more



Improving AI model accuracy 

Not satisfied with the model results or accuracy? You can improve the model accuracy quickly and simply by showing the model more diversified data.

The model performance significantly improves if you add 50 < 100 < 500 more files. Follow Steps 1-3 under 
Build your own OCR Model to improve the model performance. This process is called as retraining

If you are still unsatisfied with the model performance, reach out to us at info@nanonets.com so that our Product Specialist can help you. 



Getting Code to Integrate API  

It is super easy to integrate the code to your codebase to consume the API, in no more than 15 minutes.  

Steps:

1. Find the code under Integrate tab in a programming language that you prefer.


2. Find your API keys under API Keys on the left hand panel.


3. Find your model ID under My Models section on the left hand panel.

4. Insert your API Key and model ID in the code from Integrate tab in your codebase. 



Exporting Data  

There are multiple ways to export the extracted data.

Steps:

1. Select the files for which you want to export data under Extract Data screen.

2. Click on Export To OR Bulk Actions and Export Extracted Data

Select files and click on ‘Bulk Actions’ OR ‘Export to’

Choose options from the Export to modal

3. Choose from the following:

A. CSV, XML, Excel 

Looking to extract data in a different template or format? We will customize this for you. Reach out to us at info@nanonets.com



B. Zapier 

We've launched our Zapier integration to leverage the platform's popularity among automation experts. Check out the integrations here: https://zapier.com/apps/nanonets-ocr/integrations



C. RPA 

We integrate with different RPA providers. Here is a quick video to integrate with UiPath.


Reach out to us at info@nanonets.com if you have a specific request. 

Tip

We wanted to quickly understand if these integrations would be valuable to you or your customers. We can in return offer you 1 month of free usage on Nanonets for sharing with us your knowledge.


Integrations Supported

We support several pre-built integrations ready right out of the box. 

  • ERP Systems such as Quickbooks, Freshbooks, Zohobooks
  • Document Management Systems such as Google Drive, One Drive, Drop Box, Sharepoint, Box
  • Accounting Softwares such as Foundation
  • RPA Systems such as UiPath, Automation Anywhere
  • Others such as Zapier, Bill.com, Gmail 


Didn't find what you were looking for? We also provide custom integrations. Drop an email to 
integrations@nanonets.com and we'll get back to you . 



Languages Supported

Our AI Models support 160+ languages across the world, including English, Spanish, German, French, Icelandic; Eastern European Languages such as Lithuanian, Hungarian, Romanian; South Asian Languages such as Korean, Japanese, Malaysian, Indonesian.

Any model can quickly be enabled for a new language. 



Billing 

View all your billing in one place. You can view all the invoices and their status under the Billing section on the left handside panel in your account. You can also clear your invoices by clicking on Pay



Monitoring Usage

To monitor the number of pages and fields you captured by month or by day for a particular model -

1. Click on
 My Models section in your account
2. Click on the Model for which you want to monitor usage
3. Click on
 Usage Stats once on the left handside panel. 
4. View the number of documents processed, number of fields processed and cost incurred. You can also download these reports. 



API Documentation

Check out our API documentation here: nanonets.com/documentation

Was this article helpful?