Install the CLI via the Python package manager pip​
>> $ pip install lucidtech-las-cli
List models that are available for predictions
>> $ las models list{"models": [{"modelId": "las:model:<hex>",...}],"nextToken": null}
Upload a document
>> $ las documents create invoice.pdf{"documentId": "las:document:<hex>","contentType": "application/pdf"}
Run inference on the document using a model
>> $ las predictions create las:document:<hex> las:model:<hex>{"documentId": "las:document:<hex>","predictions": [...]}
Suppose we make a prediction that returns incorrect values and we wish to improve the model for future use. We can do so by sending feedback to the model, telling it what the expected values should have been.
>> $ las documents create invoice.pdf{"documentId": "las:document:<hex>","contentType": "application/pdf"}>> $ las documents update las:document:<hex> --fields total_amount=300.00 due_date=2020-02-28{"documentId": "las:document:<hex>","groundTruth": [...]}
Consent ID is an identifier you can assign to documents to keep track of document ownership for your customers.
>> $ las documents create invoice.pdf --consent-id las:consent:<hex>{"documentId": "las:document:<hex>","contentType": "application/pdf","consentId": "las:consent:<hex>"}
>> $ las documents create invoice.pdf --consent-id las:consent:<hex>{"documentId": "las:document:<hex>","contentType": "application/pdf","consentId": "las:consent:<hex>"}>> $ las documents get las:document:<hex> --download-content invoice2.pdf{"documentId": "las:document:<hex>","contentType": "application/pdf","consentId": "las:consent:<hex>","content": "XXXXXXXXX... [TRUNCATED]"}
Suppose we wish to delete all documents associated with a customer in our ERP database or other systems. We need to provide a consent_id to the prediction method that uniquely identifies the customer and use that consent_id to delete documents.
>> $ las consents delete las:consent:<hex>{"consentId": "las:consent:<hex>","documentIds": [...]}
Creating a batch is a way to group documents. This is useful for specifying batches of documents to use in improving the model later.
>> $ las batches create{"batchId": "las:batch:<hex>",...}