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": "File Classifier",
"functionName": "classify",
"toolVersion": "0.0.80",
"description": "Classifies a file into a bin based on its contents",
"input": {
"description": "File to be classified"
},
"output": {
"description": "Places the file into a folder (bin) that its classified into."
},
"result": {
"type": "JSON",
"description": "JSON response containing the bin to which the file was classified into",
"schema": {}
},
"adapter": {
"languageModels": [
{
"isEnabled": true,
"title": "Classifier LLM",
"isRequired": true,
"description": "LLM to use for classification"
}
],
"embeddingServices": [
{
"isEnabled": false
}
],
"vectorStores": [
{
"isEnabled": false
}
],
"textExtractors": [
{
"isEnabled": true,
"adapterId": "textExtractorId",
"title": "Text Extraction Adapter",
"isRequired": true,
"description": "Choose extractor adapter to extract text"
}
]
},
"ioCompatibility": {
"api": {
"sourceSupport": true,
"destinationSupport": true,
"additionalArgs": {
"sync": true
}
},
"file": {
"sourceSupport": true,
"destinationSupport": true,
"additionalArgs": {}
},
"db": {
"destinationSupport": true,
"additionalArgs": {}
}
},
"restrictions": {
"maxFileSize": "200MB",
"allowedFileTypes": [
"*"
]
}
}