AI Block

This article explains the Get Data from AI block that can be used to design an app. This block can analyse both typed input and uploaded files from your app using field variables. For example, it can review text entered by users, interpret images uploaded through the Camera, image & files block, or read PDF documents, all based on the instructions you provide.

‍Use Case Examples

1. Quality assurance
2. Cleanliness audits
3. Safety gear analysis
4. Inventory identification without scanning codes
5. Crop Health Detector

Help Video

Editing the Block

Click on the block and start editing on the panel that appears on the right side.

‍

Label

This is what appears as the label for the dropdown that shows the list of the items from the master app. Usually people provide labels such as "Display the item", "Calculate total score", etc.

Select LLM

Select the AI provider you want to use. Currently available options include OpenAI, Claude, and Gemini.

Each provider has its own strengths, and you may need to experiment with different ones to get the output that best suits your use case.

AI Model

Once an LLM is selected, this dropdown shows the corresponding list of available models. Choose a model from the list to power your AI interaction. The different models available allow you to experiment and find the one that provides the most accurate or relevant responses for your task.

Note: The output may vary slightly depending on the model chosen, even if the instructions are the same. If needed, test your instructions on the provider’s platform before using them in the app to reduce unnecessary AI calls.

Description

Description is positioned below the Input block which explains to the end user about the data that will be generated once they click on the AI button.

Description is positioned below the Input block which explains to the end user about the data that will be generated once they click on the Get Data from AI.

Description is an optional field.‍

NOTE - Since the Get Data from AI block is an Auto-Generated feature, it doesn’t require the user to enter any data into the block.

Instructions

Configure the AI block by typing in the exact instructions to display the data that is needed.

For example, to fetch data from external sites, detect and display details in uploaded images or even perform calculations on uploaded files and images. 

You can also use field variable names to make the AI analyse inputs from different app fields present.

Note: Tweak your instructions to get the required results before distributing the app to users.

File Handling

The AI block can also process uploaded files such as PDFs and images.

PDF documents or images can be analysed for information extraction, summaries, or other tasks.

Note: When using Claude, the AI block can process up to 100 pages in a PDF document. Only document-type files are supported currently. Once additional formats are supported by the underlying models, they may be available here as well.

Example 1: To calculate the total score in a checklist uploaded using the Camera, Images & Files block.

Blocks used: Camera, Images & Files block, Get Data from AI block.

Instructions: Check the scores in {upload_sc} under the score coloumn and calculate the total score. Display only the final value out of 100.

LLM: OpenAI

AI Model: gpt-4o

‍

‍

Example 2: Detect cleanliness of a room.

Blocks used: Camera, Images & Files block, Get Data from AI block.

Instructions: Check if the room in {upload_ima} is clean or not. Display only yes or no.

LLM: OpenAI

AI Model: gpt-4o

‍

‍

Example 3: Detect the distance traveled by a vehicle by checking the odometer.

In cases where the value is in between changing to the next increment, some OCR may not be able to detect it accurately. But the Get data from AI will be able to detect it accurately.

Blocks used: Camera, Images & Files block, Get Data from AI block.

Instructions: In {upload_ima}, check the trip distance traveled in the odometer and only display the distance. If it is about to change, display that distance instead.

LLM: OpenAI

AI Model: gpt-4o

‍

Here, the distance, in the image, is about to change from 144.2km to 144.3km .

‍

Required

Enable this option to tell the user that it is a compulsory field. Without generating the output of this block, users will not be able to make a submission if enabled.

Advanced Options

Display this field if

Enable this option to show/hide the Get Data from AI block in relation with another Input block. It accepts the standard Clappia Formulae, similar to conditional sections.

Allow value to be changed after initial submission

Enable this to allow the field value to be changed after submission

‍

Usage Limits and Add-on

The AI block has a limited number of included calls. If usage exceeds the limit, you can opt for additional AI calls as part of an add-on.

To increase AI usage, you can go to Workplace Settings > Billings tab and select the add on. Your AI usage can also be seen in the Billings tab.

Note

This is a beta version of the AI service available as an optional add-on. It is not included in any plan.The block uses APIs to interact with external LLMs. Use of this feature implies agreement with the terms and conditions of the selected model provider.