Text Extraction
Enable text reading from image capability for your agent. Useful for recognizing text from images.
Enable this tool will allow your AI agent to be able to extract text from images and documents such as natural scene photo, scanned documents, PDF files, etc. from the chat upload.
How to use: We have enabled it for all agent for free.
Cost: Free
Speed: Depends on the document size.
Size limit: 20MB (Talk to us if you need bigger size.)
Best practice: Combine with Instruction, you can build an AI agent that is able to parse any document and turn the data into a standard format. You can instruct your AI Agent to return in certain JSON format in the Instruction field
