How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Need help?

Contact us
Oracle

Oracle Generative AI Agent Runtime API

The generativeAiAgentRuntime API from Oracle — 4 operation(s) for generativeaiagentruntime.

Documentation Provider Profile APIs.io OpenAPI GitHub

Oracle Generative AI Agent Runtime API is one of 378 APIs that Oracle publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include generativeAiAgentRuntime. The published artifact set on APIs.io includes an OpenAPI specification and an API reference.

This API exposes 6 operations across 4 paths, and defines 22 schemas. It is described by OpenAPI 3.2.0, at version 20240531.

Requests are made against 2 base URLs: http://127.0.0.1/20240531, https://127.0.0.1/20240531.

6 operations 4 paths 22 schemas 1 DELETE1 GET3 POST1 PUT

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
20240531
Base URL
https://{host}:{port}/ords/
Resource Areas
1

Paths & Operations 6

Across 4 paths, the API surfaces 6 operations — 1 DELETE, 1 GET, 3 POST, 1 PUT. Each is listed below with its method, path, parameters, and response codes.

generativeAiAgentRuntime 6
POST
/agentEndpoints/{agentEndpointId}/actions/chat
Chat with endpoint
Chat 4 params body → 200400401404409412429500
POST
/agentEndpoints/{agentEndpointId}/sessions
Creates an agent Session.
CreateSession 3 params body → 200400401404409429500default
DELETE
/agentEndpoints/{agentEndpointId}/sessions/{sessionId}
Delete a session and all associated information.
DeleteSession 4 params → 204400401404412429500default
GET
/agentEndpoints/{agentEndpointId}/sessions/{sessionId}
Return the session resource identified by the session ID.
GetSession 3 params → 200400401404429500default
PUT
/agentEndpoints/{agentEndpointId}/sessions/{sessionId}
Update session metadata, including but not limited to description, tags.
UpdateSession 4 params body → 200400401404412429500default
POST
/knowledgeBases/{knowledgeBaseId}/actions/retrieveMetadata
Retrieve Metadata of knowledge base
RetrieveMetadata 4 params body → 200400401404409412429500

Schemas 22

The contract defines 22 schemas that model the data the API accepts and returns. The most detailed are KnowledgeBaseMetadataSummary (7 properties), ChatResult (6 properties), ChatDetails (6 properties), Trace (6 properties). Each schema is shown below with its type and property counts.

RetrieveMetadataDetails
object
Details to retrieve metadata
1 property
ChatDetails
object
Chat details for managing user interactions and tool executions.
6 properties
Paragraph
object
The paragraph of the generated message that contains a citation.
3 properties 3 required
Citation
object
The source of information for the agent's response.
6 properties
ParagraphCitation
object
The source of information for the paragraph of agent's response.
2 properties 1 required
KnowledgeBaseMetadataValue
object
Represents a metadata value and the number of appearances in knowledge base.
2 properties 2 required
Message
object
The Message resource generated by the agent.
3 properties 2 required
CreateSessionDetails
object
Information about the new session.
2 properties
SourceDetails
object
The details of source of the event.
2 properties
UpdateSessionDetails
object
Information about the updated session.
2 properties
KnowledgeBaseMetadataSummary
object
Represents metadata about a field including its name, type, supported operations, and possible values.
7 properties 4 required
RequiredAction
object
Represents an action that needs to be performed by the user or client.
2 properties 2 required
ToolInput
object
Base object for tool input parameters. The 'toolInputType' discriminator determines the specific input structure to be used.
2 properties 2 required
ToolOutput
object
Base schema for tool outputs. Identified by toolOutputType, which determines the format of the output content.
3 properties 2 required
Error
object
The error message information.
2 properties 2 required
MetadataFilter
object
Filter for retrieving specific metadata
2 properties 2 required
PerformedAction
object
The base structure for an action that has already been performed.
2 properties 2 required
Session
object
A session represents an interactive conversation initiated by a user through an API to engage with an agent. It involves a series of exchanges where the user s…
6 properties 2 required
Trace
object
The trace that displays the internal progression, such as reasoning and actions during an execution.
6 properties 1 required
MessageContent
object
The content of the message.
3 properties 1 required
ChatResult
object
The response of a chat request.
6 properties
SourceLocation
object
The location of the data files that the agent will use.
1 property 1 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

oracle-generativeaiagentruntime-api-openapi.yml Raw ↑

Other APIs Oracle publishes across the network.

Oracle Database REST APIs
AE Profile APIs.io
Oracle Integration Cloud API
AE Profile APIs.io
Oracle Fusion Cloud Applications API
AE Profile APIs.io
Oracle Fusion Cloud Financials REST API
AE Profile APIs.io
Oracle Fusion Cloud HCM REST API
AE Profile APIs.io
Oracle Fusion Cloud CX Sales and Service REST API
AE Profile APIs.io
Oracle Fusion Cloud SCM REST API
AE Profile APIs.io
Oracle Fusion Cloud Procurement REST API
AE Profile APIs.io
Oracle Content Management API
AE Profile APIs.io
OCI Generative AI API
AE Profile APIs.io
OCI AI Vision API
AE Profile APIs.io
OCI AI Language API
AE Profile APIs.io
#generativeAiAgentRuntime
← Back to O APIs
API Details
ID
oracle:oracle-generativeaiagentruntime-api
Base URL
https://{host}:{port}/ords/
Docs
https://docs.oracle.com/en/database/oracle/oracle-database/
Provider
Oracle
APIs.io →  GitHub →
Explore more
All APIs Providers APIs.io Network
Work with this as data

Every API here is available over the API and to AI agents over MCP. APIs is not yet its own endpoint on the v1 API. Reach this content through network search and the tag graph, or the MCP server below.

Installs https://mcp.apievangelist.com/mcp in Claude, Cursor, VS Code and the rest — one button, every client.

MCP tools for apis
4 tools reach this content
  • search_api_evangelistSearch every content type across the network at once.
  • find_relatedThe shared-tag relevance graph — what else covers this.
  • get_tagEverything one tag labels, across all content types.
  • guide_topicPRO — a curated bundle for a topic: area, guidance, rules, papers, stories, services.
All tools & prompts
Call it yourself
curl for this page
Search the network for this 
curl "https://api.apievangelist.com/v1/search?q=oracle-generativeaiagentruntime-api&limit=10"
Everything under a tag 
curl "https://api.apievangelist.com/v1/tags/oracle-generativeaiagentruntime-api"

Discovery needs no key. Full bodies and the synthesis endpoints are Pro.

Get an API key

Free tier, no email required. Sign in with whichever identity you already have.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have. Your account

Where this information came from

This is an independent, third-party profile of Oracle Generative AI Agent Runtime API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.