Oracle Cloud Infrastructure Documentation

Reference for Generative AI Agents

This guide lists the predefined objects in OCI Resource Analytics for the Generative AI Agents service. You can find information about views, entity relationships, subject areas, and sample queries.

Views

This section provides information about views within OCI Resource Analytics Generative AI Agents and their columns, data types, keys, and the referred view and column names. The following views are available:

Generative AI Agents Views
Name Description
GENERATIVE_AI_AGENT_AGENT_DIM_V This view stores information about an agent, which is an LLM based autonomous system that understands and generates human-like text, enabling natural language processing interactions.
GENERATIVE_AI_AGENT_AGENT_ENDPOINT_DIM_V This view stores information about the endpoint to access a deployed agent.
GENERATIVE_AI_AGENT_DATA_INGESTION_JOB_DIM_V This view stores information about the data ingestion job for loading data source content into a knowledge base.
GENERATIVE_AI_AGENT_DATA_SOURCE_DIM_V This view stores information about the data source points to the source of your data for agent knowledge retrieval.
GENERATIVE_AI_AGENT_KNOWLEDGE_BASE_DIM_V This view stores information about a knowledge base, which is the base for all data sources that an agent can use to retrieve information.
GENERATIVE_AI_AGENT_TOOL_DIM_V This view stores information about a tool attached to an agent to support agent capabilities.
GENERATIVE_AI_AGENT_AGENT_ENDPOINT_FACT_V Fact table for agent endpoint level for Generative AI Agents resources.
GENERATIVE_AI_AGENT_DATA_INGESTION_JOB_FACT_V Fact table for data ingestion job level for Generative AI Agents resources.

The suffixes in the view names specify the view type:

  • FACT_V: Fact
  • DIM_V: Dimension

Relationship Diagram

This section provides diagrams that define the logical relationship of a fact table with different dimension tables.

The contents of each view and their relationships are listed in the following file: Generative AI Agents views.

GENERATIVE_AI_AGENT_AGENT_ENDPOINT_FACT_V


Relationship diagram showing GENERATIVE_AI_AGENT_AGENT_ENDPOINT_FACT_V and its related dimension tables.

GENERATIVE_AI_AGENT_DATA_INGESTION_JOB_FACT_V


Relationship diagram showing GENERATIVE_AI_AGENT_DATA_INGESTION_JOB_FACT_V and its related dimension tables.

Relationships exist among dimensions. Dimensions can be joined directly to each other.

GENERATIVE_AI_AGENT_TOOL_DIM_V


Relationship diagram showing GENERATIVE_AI_AGENT_TOOL_DIM_V and its related dimension tables.

Sample Queries

Sample queries for Generative AI Agents.

List the number of agents associated with each endpoint ID.

SELECT
    AGENT_ENDPOINT_ID,
    COUNT(AGENT_ID) AS AGENT_COUNT
FROM OCIRA.GENERATIVE_AI_AGENT_AGENT_ENDPOINT_FACT_V F
GROUP BY AGENT_ENDPOINT_ID;

List the number of data ingestion jobs associated with each data source.

SELECT
    DATA_SOURCE_ID,
	COUNT(DATA_INGESTION_JOB_ID)
FROM OCIRA.GENERATIVE_AI_AGENT_DATA_INGESTION_JOB_FACT_V F
GROUP BY DATA_SOURCE_ID;