Overview Use Cases Connectors Authentication Getting Started with the Python SDK API Reference ai_agents constructAgentConversationMessagesForLLM createAgent describeAgent describeAgentVersion downloadAgentAttachment evaluatePrompt extractAgentWorkflowInformation extractDataUsingLLM generateAgentCode generateCodeForDataQueryUsingLLM listAgentVersions listAgents renderFeatureGroupsForLLM searchFeatureGroups searchWebForLLM updateAgent validateWorkflowGraph ai_chat algorithm annotations application_connectors batch_prediction code_completion custom_loss_function custom_metric database_connectors dataset deployment deployment_conversations docstore document_retrievers documentation eda external_app feature_drift feature_group feature_group_row_process feature_group_template file_connectors graph_dashboard holdout_analysis llm_apps model model_monitoring module natural_language_explanation organization pipelines predict prediction_operator project python_function refresh secrets streaming streaming_connectors upload webhooks API Classes API Inputs Documentation Chat Bot API Search Video Tutorials ChatLLM

Method

extractDataUsingLLM POST

Copy POST

Extract fields from a document using a large language model.

Arguments:

REQUIRED	KEY	TYPE	DESCRIPTION
Yes	fieldDescriptors	list[FieldDescriptor]	A list of fields to extract from the document.
No	documentId	str	The ID of the document to query.
No	documentText	str	The text of the document to query. Only used if document_id is not provided.
No	llmName	LLMName	The name of the language model to use. If not provided, the default language model is used.

Note: The arguments for the API methods follow camelCase but for Python SDK underscore_case is followed.

Response:

KEY

TYPE

DESCRIPTION

success

Boolean

true if the call succeeded, false if there was an error

result

ExtractedFields

KEY	TYPE	Description
data	dict	The fields/data extracted from the document.
rawLlmResponse	str	The raw llm response. Only returned if it could not be parsed to json dict.

Exceptions:

TYPE	WHEN
DataNotFoundError	`documentId` is not found.
InvalidEnumParameterError	An invalid value is passed for `llmName`.

Language: