One of Yoom's AI features allows you to extract text from images and PDF files using OCR. You can extract text data from files in various formats to automate your workflows.

The actions in this feature vary in capability and task consumption. However, the basic setup process is identical across all actions.

📌 Available Plans

The "Extract Text with OCR" feature is available on all plans.

1. In the Flowbot editor, click the "+" button to add a step.

2. Under operation type selection, click "OCR".

3. Select the "Read Invoices (5 tasks)" action.

4. Update the title (optional), attach your file, configure any additional items you want to extract if needed, and run a test. Once text extraction is successful, click Save.

☝️ Note: How to attach files:

☝️ Note:

For standardized documents such as invoices or business cards, default extraction items are pre-configured. If there are other specific details you wish to extract, enter custom items in the "Additional Items to Extract" field.

📍 Example: Bank Name, Invoice Title, etc.

Please keep the following in mind when using the OCR feature:

1. Test Limits: Test execution limits vary depending on the action. If you exceed the limit, please wait until the next available test window.

2. Full Document & Multi-line Reading: Reading text across an entire document or spanning multiple lines may not yield complete results due to system specifications.

3. File Size Limit: The maximum file size that can be processed is 7MB. Please ensure your files are 7MB or smaller.

4. AI Processing: Due to the nature of AI specifications, extraction may fail with a small probability. If extraction fails, please re-run the action.