LLM-based methods

Extract free text from unstructured documents using large language model (LLM)-based SenseML methods. For example, extract information from legal paragraphs in contracts and leases, or results from research papers.

The following LLM-based methods are alternatives to layout-based methods for structured documents, for example, tax documents or insurance forms.

MethodExample use caseChained-prompt example1Notes
List method"For each vehicle in an auto insurance declaration, extract the VIN, model, and year.""For the extracted list of vehicles, sort them by year of manufacture"Extracts a list of data from a document, where you don't know how the data are represented.
Query Group method"When does the policy period end?"
"What's the account number?"
"Redact the account number by returning only the last 4 digits"Extracts a single fact or data point.
NLP Table method"For each transaction in a bank statement table, extract the date and amount."N/AExtracts a list of data from a document, where you know they're in a table.

Notes