Skip to main content
All Collections🤖 Flowbot FeaturesAI OperationOCR
🤖 How to Set Up "Extract Text from Images/PDFs"

🤖 How to Set Up "Extract Text from Images/PDFs"

As of Aug 8, 2024

Yoom Customer Service avatar
Written by Yoom Customer Service
Updated over 3 weeks ago

📝 Overview

Yoom's AI-powered OCR feature allows you to extract text from images and PDFs.

You can extract from various file formats, such as invoices, business cards, and documents.

📌 Important Notes:

  • Each extraction action has different capabilities and task consumption.

  • The setup process is the same across all actions.


💡 Plans Available for Use

  • AI features (including OCR and summarization) are available in Business plans and above.

  • Free plan users can access a two-week free trial (once per plan).

  • Signing up for a Business or Enterprise plan trial grants access to AI features for a limited time.


🧾 Example Configuration: Extract Text from an Invoice (5 tasks)

1️⃣ Add the OCR Action

Click the + button on the Flowbot edit screen.

In the Action Type selection, click "OCR."

2️⃣ Set Up the Extraction Settings

Enter a title, and select Extract Invoice.

Click Next.

3️⃣ Upload or Attach the File

Attach the image or PDF file.

(Optional) If you need additional text fields, specify them in the Additional Extraction Items field.

Run a test. If the text is extracted successfully, save your changes.

📌 How to Attach Files:

✔️ Use Retrieved Values: Uses value from previous steps in the Flowbot.

✔️ Upload File: Directly upload the file from your device.

📌 Default Extraction Settings:

✔️ For files with a fixed format like invoices and business cards, default text extraction fields are already set.

✔️ If you need extra fields, enter them manually.

📌 Example: Additional Fields to Extract

✔ Bank information
✔ Invoice title


⚠️ Important Notes & Limitations

✔️ Test Run Limits: Each action has a limited number of test runs. If you exceed the limit, wait until the next available test time.
✔️ OCR Accuracy: Due to AI limitations, text across multiple lines or entire file extractions may not be read properly.
✔️ File Size Limit: The maximum file size is 7MB. Files larger than this cannot be processed.
✔️ Retry If Needed: AI-based text extraction may fail occasionally. If an error occurs, rerun the extraction.

📚 Related Guides

  • What You Can & Cannot Do with the "Read Text from Images/PDFs" Operation - View Guide Here

Related Keywords

PDF, file, reading, OCR, reading PDF or images, transcription, extraction, text extraction, text, data extraction

Did this answer your question?