Create a dataset from function outputs
Hand off to an LLM
Build a dataset from a function's corrected outputs.
Pulls the reviewed/corrected outputs (transformations) selected by query and
turns each into a dataset row: the input file, the corrected JSON, and the
schema it was produced with. Columns are created and role-tagged automatically,
so the dataset is self-describing and downstream model comparisons need no
column names. Only name + query are required.
Authorization
API Key x-api-key<token>
Authenticate using API Key in request header
In: header
Request Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
Response Body
application/json
curl -X POST "https://api.bem.ai/v3/datasets/from-function-outputs" \ -H "Content-Type: application/json" \ -d '{ "name": "invoices golden", "query": { "functionNames": [ "invoices" ], "isLabelled": true } }'{
"dataset": {
"id": "string",
"name": "string",
"description": "string",
"versionNum": 0,
"columns": {},
"rowCount": 0,
"createdAt": "2019-08-24T14:15:22Z",
"updatedAt": "2019-08-24T14:15:22Z",
"audit": {
"datasetCreatedBy": {
"userActionID": "string",
"userID": "string",
"userEmail": "string",
"apiKeyName": "string",
"emailAddress": "string",
"createdAt": "2019-08-24T14:15:22Z"
},
"datasetLastUpdatedBy": {
"userActionID": "string",
"userID": "string",
"userEmail": "string",
"apiKeyName": "string",
"emailAddress": "string",
"createdAt": "2019-08-24T14:15:22Z"
},
"versionCreatedBy": {
"userActionID": "string",
"userID": "string",
"userEmail": "string",
"apiKeyName": "string",
"emailAddress": "string",
"createdAt": "2019-08-24T14:15:22Z"
}
}
},
"error": "string"
}See also
- System overview — evaluating extraction quality