Multimodal Content Understanding
understand_contentMultimodal extraction. Send an image, text, or both; define your schema of fields; get structured JSON.
Brainiall Content Understanding engine. Unified multimodal field extraction over images and text.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "understand_content"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | No | Optional pre-extracted text | |
| image | No | Optional base64 image (will OCR first) | |
| field_schema | No | Map of field_name -> description, e.g. {"invoice_id":"invoice number","total":"amount due"} |