How to Extract Data from Images in Airtable using AI

This tutorial shows you how to extract data from images directly into Airtable using OpenAI and Data Fetcher. You'll extract specific fields (like names, emails, and job titles) from business card images and automatically populate your Airtable fields. The same approach works for parsing any structured data from images into your database.

Set Up Your Business Cards Table

We'll begin by uploading our image files and setting up a filtered view with all the records that need data:

1. Create a table called "Business Cards" or use an existing table.

2. Create a new field called "Business Card" with the type Attachment. You can use your existing attachment field if you have one.

3. Upload business card images to the "Business Card" field. OpenAI can parse different card layouts and designs, so they don't need to be from the same template or format.

4. Create a new Grid view called Needs data and add the following filters:

• Name - is empty
• Business Card - is not empty

This view will allow us to avoid processing the same images twice, and save API credits.

Now that the table is set up, let's grab an OpenAI API key.

Create an OpenAI API Key

1. Sign up for an OpenAI API account, or log in to your existing account.

2. Add a payment method in your OpenAI API billing panel.

3. Create an API key in your OpenAI account. Save this API key - you'll need it in the next steps.

Note: OpenAI API accounts and billing are separate from ChatGPT subscriptions. You will still need to go through these steps even if you have a subscription to ChatGPT.

API costs are typically $0.001-0.005 per image, depending on size and complexity.

Add Data Fetcher

We'll create a request in Data Fetcher that will allow us to send images to OpenAI to parse the information from the business cards.

1. Add the Data Fetcher extension to your Airtable base.

2. Once you've added the extension, sign in to Data Fetcher or sign up if you don't have an account.

3. Once you're logged in to Data Fetcher, click Create your first request.

Extract Data from Images in Airtable using AI

Follow these steps to configure the request:

1. Select OpenAI under Application.

2. Rename the request to "Extract image data".

3. Copy and paste your OpenAI API key under Authorization.

4. Under Endpoint, select Create a model response.

5. Click Save and Continue in the bottom right corner.

Configure Image Data Extraction

After following the previous steps, you'll be taken to a new section where you'll configure how OpenAI processes the images.

1. For this tutorial, we'll use the gpt-5 model, which provides excellent vision capabilities at lower cost.

2. Copy and paste the following under Input. The prompt below tells OpenAI exactly which fields to extract from your business cards and how to structure them. Modify this template to match the data you need:

Extract data from the following business card image. Return JSON data. If you cannot find a field, return null.
Output format:
{
"name": "John Smith",
"jobTitle": "Senior Developer",
"contactEmail": "[email protected]",
"phone": "+1-555-0100",
"company": "Tech Corp"
}

Note: To extract additional fields (like address, website, or social media), add them to the JSON template above.

Now we'll reference the image files in the table.

3. Click the + button on the right-hand side of Input to add a field reference.

4. In the dialog that opens:

• Ensure Business Cards is selected for Table
• Select Business Card under Field
• Under Run for every record in view, select Needs data

5. Click Confirm to save and close the dialog.

The message sent to OpenAI will now include each business card image when the integration runs.

6. Click Save and Run in the bottom right corner to proceed to the next step.

Map Image Parsing Results to Airtable Fields

After completing the previous steps, Data Fetcher will take you to Response Field Mapping. This is where you'll configure how the extracted image results are imported into your Airtable fields.

Data Fetcher returns several fields from the OpenAI response, but we only need the business card data fields we specified in our output format. You can ignore the "Json" prefix in the field names - Data Fetcher automatically adds this because we configured our image extractor to return JSON-formatted data.

Follow these steps to map the fields:

1. Click the selected Message field to deselect it (we don't need the raw message text).

2. Map the extracted image fields to your Airtable columns:

• Json name → Existing field Name
• Json job title → New field Job Title
• Json contact email → New field Contact Email
• Json phone → New field Phone
• Json company → New field Company

3. Click Save and Run in the bottom right corner to run the image extraction.

Return to the default "Grid view" in your Business Cards table, and you will see the extracted data populated automatically from your business card images through the OpenAI image parsing process.

Automate Image Extraction

Currently, whenever you add new images to your table, you'll have to manually run the request. To save time, you can use Data Fetcher's Trigger feature to run the request automatically.

The Trigger feature is only available on our paid plans, so you can follow these steps to upgrade:

1. Open the request in Data Fetcher, scroll down to the Schedule / Trigger / Webhook URL tabs, then select Upgrade under Trigger.

2. Select a paid plan and complete the payment process.

3. Click + Authorize to give Data Fetcher access to your Airtable base.

4. Click I understand, let's Authorize.

A new window will open, asking you to grant Data Fetcher access to your Airtable base.

5. Click Add a base, then select + Add resources so you won't have to authorize Data Fetcher anytime you want to use it on an additional Airtable base.

6. Click Grant access.

Now that you've authorized Data Fetcher, you can create a trigger to run the request when you add a new image to the table:

1. Select Record created.

2. Select Business Cards under Table and Needs data under View.

3. Finally, click Save at the bottom of the screen.

Your image to Airtable automation is now active. When you upload new business card images to your Business Cards table, Data Fetcher automatically extracts the names, job titles, emails, and other contact information into your Airtable fields.

Use Cases: Extract Data from Business Cards, Receipts, and Documents

This image extraction workflow saves hours of manual data entry while ensuring consistent, accurate data capture. Here are practical applications for different types of visual data:

• Business Card Management: Extract contact details from networking events directly into your CRM. Process hundreds of cards from conferences without manual typing.
• Receipt Processing: Pull vendor names, dates, amounts, and tax information from expense receipts. Build automated expense tracking without manual entry.
• Product Label Data: Extract ingredients, nutritional information, and barcodes from product packaging. Create product databases from photos of items.
• Form and Survey Processing: Convert handwritten forms or printed surveys into structured data. Digitize paper-based workflows from field teams.
• ID and Document Verification: Extract names, dates, and ID numbers from driver's licenses or passports. Speed up customer onboarding and verification processes.
• Screenshot Data Capture: Pull text, numbers, and tables from screenshots of reports or dashboards. Convert visual reports into analyzable data.

The combination of OpenAI's vision capabilities and Airtable's database features means you can transform any manual image-based process into an automated data extraction system.