For the complete documentation index, see llms.txt. This page is also available as Markdown.

Scan Photos or Images

Many raw photos coming from outside like Sales Order, Fuel notes, Reimbursement, Paper document, checklist and other thing. We are building AI agent to read those image, restructure the information and pass it into next AI Agent or internal system.

Create Agent

Go to "Agent", select "Add Agent" menu on the top right. Once the page showing-up, choose the "New Connection"

Choose the OCR model

There are several OCR model you can try. Its recommended to use "OCR-G001" for heavy tasks to manage handwritten notes.

Setup the AI Agent name

You can give name for the AI agent and also see how the default prompt being used for this OCR

Bonus: Next Agent to Parse

This is only scan image and convert into text. The result will be unstructured and need to be re-formated to make it works with system integration that you needed. In that case, you can chain with another AI Agent to manage it.

To chain it, you can tick which the AI Agent will be activated once the OCR completed

Give a shot!

You can paste the image url into the chat

API Integration

You can submit the URL into AI Agents via API. Go to "Channels", Select "Add" and Choose "API". Generate the "API Key" and use that as the authentication during API call.

Congratulations! Now you made OCR AI agent successfully!

Last updated

Was this helpful?