> ## Documentation Index
> Fetch the complete documentation index at: https://launchdarkly-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# List AI Configs
> > For the complete documentation index, see [llms.txt](https://launchdarkly-preview.mintlify.app/llms.txt). For the full documentation snapshot, see [llms-full.txt](https://launchdarkly-preview.mintlify.app/llms-full.txt).
Get a list of all AI Configs in the given project.
## OpenAPI
````yaml /openapi/launchdarkly-api.json get /api/v2/projects/{projectKey}/ai-configs
openapi: 3.0.3
info:
title: LaunchDarkly REST API
description: >
> For the complete documentation index, see
https://launchdarkly-preview.mintlify.app/llms.txt.
> For the full documentation snapshot, see
https://launchdarkly-preview.mintlify.app/llms-full.txt.
This is the LaunchDarkly REST API. It lets you build custom integrations,
automate your workflow, and manage feature flags and other LaunchDarkly
resources programmatically.
For authentication, rate limits, pagination, versioning, JSON Patch and
semantic patches, beta resources, and the full SDK End-of-Life table, read
the [REST API overview](https://launchdarkly-preview.mintlify.app/api).
To fetch the complete OpenAPI spec, use [Get OpenAPI
spec](https://launchdarkly.com/docs/api/other/get-openapi-spec).
contact:
name: LaunchDarkly Technical Support Team
url: https://support.launchdarkly.com
email: support@launchdarkly.com
license:
name: Apache 2.0
url: https://www.apache.org/licenses/LICENSE-2.0
version: '2.0'
servers:
- url: https://app.launchdarkly.com
description: ' Default'
- url: https://app.launchdarkly.us
description: ' Federal'
security:
- ApiKey:
- read
- write
tags:
- name: Access tokens
description: >-
The access tokens API allows you to list, create, modify, and delete
access tokens programmatically.
- name: Account members
description: >-
The account members API allows you to invite new members to an account by
making a `POST` request to `/api/v2/members`. When you invite a new member
to an account, an invitation is sent to the email you provided.
- name: Account usage (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: AI Configs
description: >-
The AI Configs API allows you to create, retrieve, and edit AI Configs, AI
Config variations, and AI model configurations.
- name: Announcements
description: >-
The announcements API lets you create and update a custom announcement
banner that appears in the LaunchDarkly user interface for everyone in
your organization.
- name: Applications (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Approvals
description: >-
An account member can request approval on changes to a flag or AI Config's
targeting or variations, or to a segment's targeting. Members may be
required to request approval depending on the settings in their
LaunchDarkly project.
- name: Approvals (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Audit log
description: >-
LaunchDarkly maintains a record of all the changes made to any resource in
the system. You can access this history using the audit log API, including
filtering by timestamps, or using a custom policy to select which entries
to receive.
- name: Code references
description: >-
> ### Code references is an Enterprise feature > > Code references is
available to customers on an Enterprise plan. To learn more, [read about
our pricing](https://launchdarkly.com/pricing/).
- name: Context settings
description: >-
You can use the context settings API to assign a context to a specific
variation for any feature flag. To learn more, read [View and manage
contexts](https://launchdarkly.com/docs/home/observability/context-attributes#view-and-manage-contexts).
- name: Contexts
description: >-
Contexts are people, services, machines, or other resources that encounter
feature flags in your product. Contexts are identified by their `kind`,
which describes the type of resources encountering flags, and by their
`key`.
- name: Custom roles
description: >-
> ### Custom roles is an Enterprise feature > > Custom roles is available
to customers on an Enterprise plan. To learn more, [read about our
pricing](https://launchdarkly.com/pricing/).
- name: Data Export destinations
description: >-
> ### Data Export is an add-on feature > > Data Export is available as an
add-on for customers on a Foundation or Enterprise plan. To learn more,
[read about our pricing](https://launchdarkly.com/pricing/).
- name: Environments
description: >-
Environments allow you to maintain separate rollout rules in different
contexts, from local development to QA, staging, and production. With the
LaunchDarkly Environments API, you can programmatically list, create, and
manage environments.
- name: Experiments
description: >-
> ### Available for subscription customers > > Experimentation is
available to all customers on a Developer, Foundation, or Enterprise
subscription. If you're on an older Pro or Enterprise plan,
Experimentation is available as an add-on.
- name: Feature flags
description: >-
The feature flags API allows you to list, create, and modify feature flags
and their targeting. For example, you can control percentage rollouts,
target specific contexts, or even toggle off a feature flag
programmatically.
- name: Feature flags (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Flag import configurations (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Flag links (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Flag triggers
description: >-
> ### Flag triggers is an Enterprise feature > > Flag triggers is
available to customers on an Enterprise plan. To learn more, [read about
our pricing](https://launchdarkly.com/pricing/).
- name: Follow flags
description: >-
Follow flags to receive email updates about targeting changes to a flag in
a project and environment.
- name: Holdouts (beta)
description: >-
> ### Available for customers using Experimentation > > Holdouts are
available to customers using
[Experimentation](https://launchdarkly.com/docs/api/experiments).
- name: Insights charts (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Insights deployments (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Insights flag events (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Insights pull requests (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Insights repositories (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Insights scores (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Integration audit log subscriptions
description: >-
Audit log integration subscriptions allow you to send audit log events
hooks to one of dozens of external tools. For example, you can send flag
change event webhooks to external third party software.
- name: Integration delivery configurations (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Integrations (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Layers
description: >-
> ### Available for customers using Experimentation > > Layers are
available to customers using
[Experimentation](https://launchdarkly.com/docs/api/experiments).
- name: Metrics
description: >-
Metrics track flag behavior over time when an experiment is running. The
data generated from experiments gives you more insight into the impact of
a particular flag.
- name: Metrics (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: OAuth2 Clients
description: >-
The OAuth2 client API allows you to register a LaunchDarkly OAuth client
for use in your own custom integrations.
- name: Persistent store integrations (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Projects
description: >-
Projects allow you to manage multiple different software projects under
one LaunchDarkly account. Each project has its own unique set of
environments and feature flags.
- name: Relay Proxy configurations
description: >-
> ### Relay Proxy automatic configuration is an Enterprise feature > >
Relay Proxy automatic configuration is available to customers on an
Enterprise plan. To learn more, [read about our
pricing](https://launchdarkly.com/pricing/).
- name: Release pipelines (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Release policies (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Releases (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Scheduled changes
description: >-
> ### Scheduled flag changes is an Enterprise feature > > Scheduled flag
changes is available to customers on an Enterprise plan. To learn more,
[read about our pricing](https://launchdarkly.com/pricing/).
- name: Segments
description: >-
> ### Synced segments and larger list-based segments are an Enterprise
feature > > This section documents endpoints for rule-based, list-based,
and synced segments.
- name: Tags
description: >-
Tags are simple strings that you can attach to most resources in
LaunchDarkly. Tags are useful for grouping resources into a set that you
can name in a resource specifier.
- name: Teams
description: >-
> ### Teams is an Enterprise feature > > Teams is available to customers
on an Enterprise plan. To learn more, [read about our
pricing](https://launchdarkly.com/pricing/).
- name: Teams (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: User settings
description: >-
> ### Contexts are now available > > After you have upgraded your
LaunchDarkly SDK to use contexts instead of users, you should use
[Contexts](https://launchdarkly.com/docs/api/contexts) instead of the user
settings API.
- name: Users
description: >-
> ### Contexts are now available > > After you have upgraded your
LaunchDarkly SDK to use contexts instead of users, you should use
[Contexts](https://launchdarkly.com/docs/api/contexts) instead of these
endpoints.
- name: Users (beta)
description: >-
> ### Contexts are now available > > After you have upgraded your
LaunchDarkly SDK to use contexts instead of users, you should use
[Contexts](https://launchdarkly.com/docs/api/contexts) instead of these
endpoints.
- name: Views (beta)
description: >-
> ### This feature is in beta > > To use this feature, pass in a header
including the `LD-API-Version` key with value set to `beta`. Use this
header with each call.
- name: Webhooks
description: >-
The webhooks API lets you build your own integrations that subscribe to
activities in LaunchDarkly. When you generate an activity in LaunchDarkly,
such as when you change a flag or you create a project, LaunchDarkly sends
an HTTP POST payload to the...
- name: Workflow templates
description: >-
> ### Workflows are in maintenance mode > > The workflows feature is in
maintenance mode, and is planned for future deprecation at a date not yet
specified.
- name: Workflows
description: >-
> ### Workflows are in maintenance mode > > The workflows feature is in
maintenance mode, and is planned for future deprecation at a date not yet
specified.
- name: Other
description: Other requests available in the LaunchDarkly API.
paths:
/api/v2/projects/{projectKey}/ai-configs:
get:
tags:
- AI Configs
summary: List AI Configs
description: >-
> For the complete documentation index, see
[llms.txt](https://launchdarkly-preview.mintlify.app/llms.txt). For the
full documentation snapshot, see
[llms-full.txt](https://launchdarkly-preview.mintlify.app/llms-full.txt).
Get a list of all AI Configs in the given project.
operationId: getAIConfigs
parameters:
- example: default
explode: false
in: path
name: projectKey
required: true
schema:
type: string
style: simple
- description: A sort to apply to the list of AI Configs.
explode: true
in: query
name: sort
required: false
schema:
type: string
style: form
- description: The number of resources to return.
explode: true
in: query
name: limit
required: false
schema:
type: integer
style: form
- description: >-
Where to start in the list. Use this with pagination. For example,
an offset of 10 skips the first ten items and then returns the next
items in the list, up to the query `limit`.
explode: true
in: query
name: offset
required: false
schema:
type: integer
style: form
- description: A filter to apply to the list.
explode: true
in: query
name: filter
required: false
schema:
type: string
style: form
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/AIConfigs'
description: Successful response
'400':
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
description: Bad request
'403':
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
description: Forbidden
'404':
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
description: Not found
'500':
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
description: Internal server error
components:
schemas:
AIConfigs:
example:
_links:
next:
href: href
type: type
last:
href: href
type: type
prev:
href: href
type: type
self:
href: href
type: type
first:
href: href
type: type
totalCount: 2
items:
- _maintainer:
kind: kind
_links:
parent:
href: href
type: type
self:
href: href
type: type
description: description
evaluationMetricKey: evaluationMetricKey
version: 0
tags:
- tags
- tags
dependencies:
- type: agent-graph
key: key
- type: agent-graph
key: key
mode: completion
createdAt: 9
evaluationMetricKeys:
- evaluationMetricKeys
- evaluationMetricKeys
_access:
allowed:
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
denied:
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
variations:
- judgeConfiguration:
judges:
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
instructions: instructions
color: color
_links:
parent:
href: href
type: type
description: description
modelConfigKey: modelConfigKey
judgingConfigKeys:
- judgingConfigKeys
- judgingConfigKeys
version: 1
tools:
- customParameters:
key: ''
version: 2
key: key
- customParameters:
key: ''
version: 2
key: key
createdAt: 6
_publishedAt: 5
_archivedAt: 5
name: name
messages:
- role: role
content: content
- role: role
content: content
comment: comment
model: '{}'
_id: _id
state: state
key: key
- judgeConfiguration:
judges:
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
instructions: instructions
color: color
_links:
parent:
href: href
type: type
description: description
modelConfigKey: modelConfigKey
judgingConfigKeys:
- judgingConfigKeys
- judgingConfigKeys
version: 1
tools:
- customParameters:
key: ''
version: 2
key: key
- customParameters:
key: ''
version: 2
key: key
createdAt: 6
_publishedAt: 5
_archivedAt: 5
name: name
messages:
- role: role
content: content
- role: role
content: content
comment: comment
model: '{}'
_id: _id
state: state
key: key
name: name
key: key
isInverted: true
updatedAt: 3
- _maintainer:
kind: kind
_links:
parent:
href: href
type: type
self:
href: href
type: type
description: description
evaluationMetricKey: evaluationMetricKey
version: 0
tags:
- tags
- tags
dependencies:
- type: agent-graph
key: key
- type: agent-graph
key: key
mode: completion
createdAt: 9
evaluationMetricKeys:
- evaluationMetricKeys
- evaluationMetricKeys
_access:
allowed:
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
denied:
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
variations:
- judgeConfiguration:
judges:
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
instructions: instructions
color: color
_links:
parent:
href: href
type: type
description: description
modelConfigKey: modelConfigKey
judgingConfigKeys:
- judgingConfigKeys
- judgingConfigKeys
version: 1
tools:
- customParameters:
key: ''
version: 2
key: key
- customParameters:
key: ''
version: 2
key: key
createdAt: 6
_publishedAt: 5
_archivedAt: 5
name: name
messages:
- role: role
content: content
- role: role
content: content
comment: comment
model: '{}'
_id: _id
state: state
key: key
- judgeConfiguration:
judges:
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
instructions: instructions
color: color
_links:
parent:
href: href
type: type
description: description
modelConfigKey: modelConfigKey
judgingConfigKeys:
- judgingConfigKeys
- judgingConfigKeys
version: 1
tools:
- customParameters:
key: ''
version: 2
key: key
- customParameters:
key: ''
version: 2
key: key
createdAt: 6
_publishedAt: 5
_archivedAt: 5
name: name
messages:
- role: role
content: content
- role: role
content: content
comment: comment
model: '{}'
_id: _id
state: state
key: key
name: name
key: key
isInverted: true
updatedAt: 3
properties:
_links:
$ref: '#/components/schemas/PaginatedLinks'
items:
items:
$ref: '#/components/schemas/AIConfig'
type: array
totalCount:
type: integer
required:
- items
- totalCount
type: object
Error:
example:
code: code
message: message
properties:
message:
type: string
code:
type: string
required:
- code
- message
type: object
PaginatedLinks:
example:
next:
href: href
type: type
last:
href: href
type: type
prev:
href: href
type: type
self:
href: href
type: type
first:
href: href
type: type
properties:
first:
$ref: '#/components/schemas/AiConfigsLink'
last:
$ref: '#/components/schemas/AiConfigsLink'
next:
$ref: '#/components/schemas/AiConfigsLink'
prev:
$ref: '#/components/schemas/AiConfigsLink'
self:
$ref: '#/components/schemas/AiConfigsLink'
required:
- self
type: object
AIConfig:
example:
_maintainer:
kind: kind
_links:
parent:
href: href
type: type
self:
href: href
type: type
description: description
evaluationMetricKey: evaluationMetricKey
version: 0
tags:
- tags
- tags
dependencies:
- type: agent-graph
key: key
- type: agent-graph
key: key
mode: completion
createdAt: 9
evaluationMetricKeys:
- evaluationMetricKeys
- evaluationMetricKeys
_access:
allowed:
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
denied:
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
variations:
- judgeConfiguration:
judges:
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
instructions: instructions
color: color
_links:
parent:
href: href
type: type
description: description
modelConfigKey: modelConfigKey
judgingConfigKeys:
- judgingConfigKeys
- judgingConfigKeys
version: 1
tools:
- customParameters:
key: ''
version: 2
key: key
- customParameters:
key: ''
version: 2
key: key
createdAt: 6
_publishedAt: 5
_archivedAt: 5
name: name
messages:
- role: role
content: content
- role: role
content: content
comment: comment
model: '{}'
_id: _id
state: state
key: key
- judgeConfiguration:
judges:
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
instructions: instructions
color: color
_links:
parent:
href: href
type: type
description: description
modelConfigKey: modelConfigKey
judgingConfigKeys:
- judgingConfigKeys
- judgingConfigKeys
version: 1
tools:
- customParameters:
key: ''
version: 2
key: key
- customParameters:
key: ''
version: 2
key: key
createdAt: 6
_publishedAt: 5
_archivedAt: 5
name: name
messages:
- role: role
content: content
- role: role
content: content
comment: comment
model: '{}'
_id: _id
state: state
key: key
name: name
key: key
isInverted: true
updatedAt: 3
properties:
_access:
$ref: '#/components/schemas/AiConfigsAccess'
_links:
$ref: '#/components/schemas/ParentAndSelfLinks'
description:
type: string
key:
type: string
_maintainer:
$ref: '#/components/schemas/AIConfig__maintainer'
mode:
default: completion
enum:
- agent
- completion
- judge
type: string
name:
type: string
tags:
type: array
items:
type: string
version:
type: integer
variations:
items:
$ref: '#/components/schemas/AIConfigVariation'
type: array
createdAt:
type: integer
format: int64
updatedAt:
type: integer
format: int64
evaluationMetricKey:
description: Evaluation metric key for this AI Config
type: string
evaluationMetricKeys:
deprecated: true
description: List of evaluation metric keys for this AI Config
items:
type: string
type: array
isInverted:
description: >-
Whether the evaluation metric is inverted, meaning a lower value is
better if set as true
type: boolean
dependencies:
description: Resources that depend on this AI Config, grouped by type
items:
$ref: '#/components/schemas/AIConfigDependency'
type: array
required:
- createdAt
- description
- key
- name
- tags
- updatedAt
- variations
- version
type: object
AiConfigsLink:
example:
href: href
type: type
properties:
href:
type: string
type:
type: string
type: object
AiConfigsAccess:
example:
allowed:
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
denied:
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
- reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
properties:
denied:
items:
$ref: '#/components/schemas/AiConfigsAccessDenied'
type: array
allowed:
items:
$ref: '#/components/schemas/AiConfigsAccessAllowedRep'
type: array
required:
- allowed
- denied
type: object
ParentAndSelfLinks:
description: The location and content type of related resources
example:
parent:
href: href
type: type
self:
href: href
type: type
properties:
self:
$ref: '#/components/schemas/CoreLink'
parent:
$ref: '#/components/schemas/CoreLink'
required:
- parent
- self
type: object
AIConfig__maintainer:
example:
kind: kind
oneOf:
- $ref: '#/components/schemas/MaintainerMember'
- $ref: '#/components/schemas/AiConfigsMaintainerTeam'
properties:
kind:
type: string
required:
- kind
AIConfigVariation:
example:
judgeConfiguration:
judges:
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
instructions: instructions
color: color
_links:
parent:
href: href
type: type
description: description
modelConfigKey: modelConfigKey
judgingConfigKeys:
- judgingConfigKeys
- judgingConfigKeys
version: 1
tools:
- customParameters:
key: ''
version: 2
key: key
- customParameters:
key: ''
version: 2
key: key
createdAt: 6
_publishedAt: 5
_archivedAt: 5
name: name
messages:
- role: role
content: content
- role: role
content: content
comment: comment
model: '{}'
_id: _id
state: state
key: key
properties:
_links:
$ref: '#/components/schemas/ParentLink'
color:
type: string
comment:
type: string
description:
description: >-
Returns the description for the agent. This is only returned for
agent variations.
type: string
instructions:
description: >-
Returns the instructions for the agent. This is only returned for
agent variations.
type: string
key:
type: string
_id:
type: string
messages:
items:
$ref: '#/components/schemas/Message'
type: array
model:
type: object
modelConfigKey:
type: string
name:
type: string
createdAt:
type: integer
format: int64
version:
type: integer
state:
type: string
_archivedAt:
type: integer
format: int64
_publishedAt:
type: integer
format: int64
tools:
items:
$ref: '#/components/schemas/VariationTool'
type: array
judgeConfiguration:
$ref: '#/components/schemas/JudgeConfiguration'
judgingConfigKeys:
type: array
items:
type: string
required:
- _id
- createdAt
- key
- model
- name
- version
type: object
AIConfigDependency:
description: A resource that depends on this AI Config
example:
type: agent-graph
key: key
properties:
type:
description: The type of the dependent resource
enum:
- agent-graph
type: string
key:
description: The key of the dependent resource
type: string
required:
- key
- type
type: object
AiConfigsAccessDenied:
example:
reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
properties:
action:
type: string
reason:
$ref: '#/components/schemas/AiConfigsAccessDeniedReason'
required:
- action
- reason
type: object
AiConfigsAccessAllowedRep:
example:
reason:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
action: action
properties:
action:
type: string
reason:
$ref: '#/components/schemas/AiConfigsAccessAllowedReason'
required:
- action
- reason
type: object
CoreLink:
example:
href: href
type: type
properties:
href:
type: string
type:
type: string
required:
- href
- type
type: object
MaintainerMember:
properties:
_id:
type: string
email:
type: string
firstName:
type: string
lastName:
type: string
role:
type: string
required:
- _id
- email
- role
type: object
AiConfigsMaintainerTeam:
properties:
key:
type: string
name:
type: string
required:
- key
- name
type: object
ParentLink:
example:
parent:
href: href
type: type
properties:
parent:
$ref: '#/components/schemas/CoreLink'
required:
- parent
type: object
Message:
example:
role: role
content: content
properties:
content:
type: string
role:
type: string
required:
- content
- role
type: object
VariationTool:
example:
customParameters:
key: ''
version: 2
key: key
properties:
key:
description: The key of the tool to use.
type: string
version:
description: The version of the tool.
type: integer
customParameters:
additionalProperties: true
description: Custom metadata and configuration for application-level use
type: object
required:
- key
- version
type: object
JudgeConfiguration:
example:
judges:
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
- samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
properties:
judges:
description: >
List of judges for this variation. When updating, this replaces all
existing judge attachments, and if empty, removes all judge
attachments.
items:
$ref: '#/components/schemas/JudgeAttachment'
type: array
type: object
AiConfigsAccessDeniedReason:
example:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
properties:
resources:
type: array
description: Resource specifier strings
items:
type: string
example:
- proj/*:env/*;qa_*:/flag/*
notResources:
type: array
description: >-
Targeted resources are the resources NOT in this list. The
resources and notActions fields must be
empty to use this field.
items:
type: string
actions:
type: array
description: Actions to perform on a resource
items:
$ref: '#/components/schemas/ActionSpecifier'
example:
- '*'
notActions:
type: array
description: >-
Targeted actions are the actions NOT in this list. The
actions and notResources fields must be
empty to use this field.
items:
$ref: '#/components/schemas/ActionSpecifier'
effect:
type: string
description: >-
Whether this statement should allow or deny actions on the
resources.
example: allow
enum:
- allow
- deny
role_name:
type: string
required:
- effect
type: object
AiConfigsAccessAllowedReason:
example:
role_name: role_name
notActions:
- null
- null
notResources:
- notResources
- notResources
effect: allow
resources:
- proj/*:env/*;qa_*:/flag/*
actions:
- '*'
properties:
resources:
type: array
description: Resource specifier strings
items:
type: string
example:
- proj/*:env/*;qa_*:/flag/*
notResources:
type: array
description: >-
Targeted resources are the resources NOT in this list. The
resources and notActions fields must be
empty to use this field.
items:
type: string
actions:
type: array
description: Actions to perform on a resource
items:
$ref: '#/components/schemas/ActionSpecifier'
example:
- '*'
notActions:
type: array
description: >-
Targeted actions are the actions NOT in this list. The
actions and notResources fields must be
empty to use this field.
items:
$ref: '#/components/schemas/ActionSpecifier'
effect:
type: string
description: >-
Whether this statement should allow or deny actions on the
resources.
example: allow
enum:
- allow
- deny
role_name:
type: string
required:
- effect
type: object
JudgeAttachment:
example:
samplingRate: 0.7061401
judgeConfigKey: judgeConfigKey
properties:
judgeConfigKey:
description: Key of the judge AI Config
type: string
samplingRate:
description: Sampling rate for this judge attachment (0.0 to 1.0)
format: float
maximum: 1
minimum: 0
type: number
required:
- judgeConfigKey
- samplingRate
type: object
ActionSpecifier:
type: string
securitySchemes:
ApiKey:
type: apiKey
in: header
name: Authorization
````