LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
Python ai-agentsdata-engineeringdocument-aigenerative-aiidpjson-extractionllmmcp-serverocrpdf-extractionprompt-engineeringstructured-output
{
"schemaVersion": "0.0.1",
"displayName": "Text Extractor",
"functionName": "text_extractor",
"toolVersion": "0.0.76",
"description": "The Text Extractor is a powerful tool designed to convert documents to its text form or Extract texts from documents",
"input": {
"description": "Document"
},
"output": {
"description": "structured json output"
},
"result": {
"type": "TXT",
"description": "Text format of input",
"schema": {}
},
"adapter": {
"textExtractors": [
{
"isEnabled": true,
"adapterId": "extractorId",
"title": "Text Extraction Adapter",
"isRequired": true,
"description": "Adapter to extract"
}
]
},
"ioCompatibility": {
"api": {
"sourceSupport": true,
"destinationSupport": true,
"additionalArgs": {
"sync": true
}
},
"file": {
"sourceSupport": true,
"destinationSupport": true,
"additionalArgs": {}
},
"db": {
"destinationSupport": true,
"additionalArgs": {}
}
},
"restrictions": {
"maxFileSize": "200MB",
"allowedFileTypes": [
"*"
]
}
}