Class Context (0.13.0)

Context(mapping=None, *, ignore_unknown_fields=False, **kwargs)

A collection of context to apply to this conversation

Attributes

Name Description
system_instruction str
Optional. The basic entry point for data owners creating domain knowledge for Agent. Why: Business jargon (e.g., YTD revenue is calculated as…, Retirement Age is 65 in the USA, etc) and system instructions (e.g., answer like a Pirate) can help the model understand the business context around a user question.
datasource_references google.cloud.geminidataanalytics_v1.types.DatasourceReferences
Required. Data sources that are available for answering the question.
options google.cloud.geminidataanalytics_v1.types.ConversationOptions
Optional. Additional options for the conversation.
example_queries MutableSequence[google.cloud.geminidataanalytics_v1.types.ExampleQuery]
Optional. A list of example queries, providing examples of relevant and commonly used SQL queries and their corresponding natural language queries optionally present. Currently only used for BigQuery data sources and databases (alloydb, cloudsql, spanner) data sources.
looker_golden_queries MutableSequence[google.cloud.geminidataanalytics_v1.types.LookerGoldenQuery]
Optional. A list of golden queries, providing examples of relevant and commonly used Looker queries and their corresponding natural language queries optionally present. Only supported for Looker data sources.
glossary_terms MutableSequence[google.cloud.geminidataanalytics_v1.types.GlossaryTerm]
Optional. Term definitions (currently, only user authored) Not supported for databases (alloydb, cloudsql, spanner) data sources.
schema_relationships MutableSequence[google.cloud.geminidataanalytics_v1.types.Context.SchemaRelationship]
Optional. Relationships between table schema, including referencing and referenced columns.
user_functions google.cloud.geminidataanalytics_v1.types.UserFunctions
Optional. A collection of user functions to be included in context.

Classes

SchemaRelationship

SchemaRelationship(mapping=None, *, ignore_unknown_fields=False, **kwargs)

The relationship between two tables, including referencing and referenced columns. This is a derived context retrieved from Dataplex Dataset Insights.