Skip to content
  • Auto
  • Light
  • Dark

Agents

Agents

Create an Agent
agents.create(AgentCreateParams**kwargs) -> AgentCreateResponse
post/v2/gen-ai/agents
Delete an Agent
agents.delete(struuid) -> AgentDeleteResponse
delete/v2/gen-ai/agents/{uuid}
List Agents
agents.list(AgentListParams**kwargs) -> AgentListResponse
get/v2/gen-ai/agents
Retrieve an Existing Agent
agents.retrieve(struuid) -> AgentRetrieveResponse
get/v2/gen-ai/agents/{uuid}
Update an Agent
agents.update(strpath_uuid, AgentUpdateParams**kwargs) -> AgentUpdateResponse
put/v2/gen-ai/agents/{uuid}
Update Agent Status
agents.update_status(strpath_uuid, AgentUpdateStatusParams**kwargs) -> AgentUpdateStatusResponse
put/v2/gen-ai/agents/{uuid}/deployment_visibility
ModelsExpand Collapse
class APIAgent:

An Agent

anthropic_api_key: Optional[APIAnthropicAPIKeyInfo]

Anthropic API Key Info

api_key_infos: Optional[List[APIAgentAPIKeyInfo]]

Api key infos

created_at: Optional[datetime]

Creation date

formatdate-time
created_by: Optional[str]

Created by

formatuint64
deleted_at: Optional[datetime]

Deleted date

formatdate-time
name: Optional[str]

Name

secret_key: Optional[str]
uuid: Optional[str]

Uuid

api_keys: Optional[List[APIKey]]

Api keys

api_key: Optional[str]

Api key

chatbot: Optional[Chatbot]

A Chatbot

button_background_color: Optional[str]
name: Optional[str]

Name of chatbot

primary_color: Optional[str]
secondary_color: Optional[str]
starting_message: Optional[str]
chatbot_identifiers: Optional[List[ChatbotIdentifier]]

Chatbot identifiers

agent_chatbot_identifier: Optional[str]

Agent chatbot identifier

child_agents: Optional[List[APIAgent]]

Child agents

conversation_logs_enabled: Optional[bool]

Whether conversation logs are enabled for the agent

created_at: Optional[datetime]

Creation date / time

formatdate-time
deployment: Optional[Deployment]

Description of deployment

created_at: Optional[datetime]

Creation date / time

formatdate-time
name: Optional[str]

Name

status: Optional[Literal["STATUS_UNKNOWN", "STATUS_WAITING_FOR_DEPLOYMENT", "STATUS_DEPLOYING", 6 more]]
Accepts one of the following:
"STATUS_UNKNOWN"
"STATUS_WAITING_FOR_DEPLOYMENT"
"STATUS_DEPLOYING"
"STATUS_RUNNING"
"STATUS_FAILED"
"STATUS_WAITING_FOR_UNDEPLOYMENT"
"STATUS_UNDEPLOYING"
"STATUS_UNDEPLOYMENT_FAILED"
"STATUS_DELETED"
updated_at: Optional[datetime]

Last modified

formatdate-time
url: Optional[str]

Access your deployed agent here

uuid: Optional[str]

Unique id

visibility: Optional[APIDeploymentVisibility]
  • VISIBILITY_UNKNOWN: The status of the deployment is unknown
  • VISIBILITY_DISABLED: The deployment is disabled and will no longer service requests
  • VISIBILITY_PLAYGROUND: Deprecated: No longer a valid state
  • VISIBILITY_PUBLIC: The deployment is public and will service requests from the public internet
  • VISIBILITY_PRIVATE: The deployment is private and will only service requests from other agents, or through API keys
description: Optional[str]

Description of agent

functions: Optional[List[Function]]
api_key: Optional[str]

Api key

created_at: Optional[datetime]

Creation date / time

formatdate-time
created_by: Optional[str]

Created by user id from DO

formatuint64
description: Optional[str]

Agent description

faas_name: Optional[str]
faas_namespace: Optional[str]
input_schema: Optional[object]
name: Optional[str]

Name

output_schema: Optional[object]
updated_at: Optional[datetime]

Last modified

formatdate-time
url: Optional[str]

Download your agent here

uuid: Optional[str]

Unique id

guardrails: Optional[List[Guardrail]]

The guardrails the agent is attached to

agent_uuid: Optional[str]
created_at: Optional[datetime]
default_response: Optional[str]
description: Optional[str]
guardrail_uuid: Optional[str]
is_attached: Optional[bool]
is_default: Optional[bool]
metadata: Optional[object]
name: Optional[str]
priority: Optional[int]
type: Optional[Literal["GUARDRAIL_TYPE_UNKNOWN", "GUARDRAIL_TYPE_JAILBREAK", "GUARDRAIL_TYPE_SENSITIVE_DATA", "GUARDRAIL_TYPE_CONTENT_MODERATION"]]
Accepts one of the following:
"GUARDRAIL_TYPE_UNKNOWN"
"GUARDRAIL_TYPE_JAILBREAK"
"GUARDRAIL_TYPE_SENSITIVE_DATA"
"GUARDRAIL_TYPE_CONTENT_MODERATION"
updated_at: Optional[datetime]
uuid: Optional[str]
if_case: Optional[str]
instruction: Optional[str]

Agent instruction. Instructions help your agent to perform its job effectively. See Write Effective Agent Instructions for best practices.

k: Optional[int]
knowledge_bases: Optional[List[APIKnowledgeBase]]

Knowledge bases

added_to_agent_at: Optional[datetime]

Time when the knowledge base was added to the agent

formatdate-time
created_at: Optional[datetime]

Creation date / time

formatdate-time
database_id: Optional[str]
embedding_model_uuid: Optional[str]
is_public: Optional[bool]

Whether the knowledge base is public or not

last_indexing_job: Optional[APIIndexingJob]

IndexingJob description

name: Optional[str]

Name of knowledge base

project_id: Optional[str]
region: Optional[str]

Region code

tags: Optional[List[str]]

Tags to organize related resources

updated_at: Optional[datetime]

Last modified

formatdate-time
user_id: Optional[str]

Id of user that created the knowledge base

formatint64
uuid: Optional[str]

Unique id for knowledge base

logging_config: Optional[LoggingConfig]
galileo_project_id: Optional[str]

Galileo project identifier

galileo_project_name: Optional[str]

Name of the Galileo project

insights_enabled: Optional[bool]

Whether insights are enabled

insights_enabled_at: Optional[datetime]

Timestamp when insights were enabled

formatdate-time
log_stream_id: Optional[str]

Identifier for the log stream

log_stream_name: Optional[str]

Name of the log stream

max_tokens: Optional[int]
model: Optional[APIAgentModel]

Description of a Model

name: Optional[str]

Agent name

openai_api_key: Optional[APIOpenAIAPIKeyInfo]

OpenAI API Key Info

parent_agents: Optional[List[APIAgent]]

Parent agents

project_id: Optional[str]
provide_citations: Optional[bool]

Whether the agent should provide in-response citations

region: Optional[str]

Region code

retrieval_method: Optional[APIRetrievalMethod]
  • RETRIEVAL_METHOD_UNKNOWN: The retrieval method is unknown
  • RETRIEVAL_METHOD_REWRITE: The retrieval method is rewrite
  • RETRIEVAL_METHOD_STEP_BACK: The retrieval method is step back
  • RETRIEVAL_METHOD_SUB_QUERIES: The retrieval method is sub queries
  • RETRIEVAL_METHOD_NONE: The retrieval method is none
route_created_at: Optional[datetime]

Creation of route date / time

formatdate-time
route_created_by: Optional[str]
route_name: Optional[str]

Route name

route_uuid: Optional[str]
tags: Optional[List[str]]

Agent tag to organize related resources

temperature: Optional[float]
template: Optional[Template]

Represents an AgentTemplate entity

created_at: Optional[datetime]

The agent template's creation date

formatdate-time
description: Optional[str]

Deprecated - Use summary instead

guardrails: Optional[List[TemplateGuardrail]]

List of guardrails associated with the agent template

priority: Optional[int]

Priority of the guardrail

formatint32
uuid: Optional[str]

Uuid of the guardrail

instruction: Optional[str]

Instructions for the agent template

k: Optional[int]

The 'k' value for the agent template

formatint64
knowledge_bases: Optional[List[APIKnowledgeBase]]

List of knowledge bases associated with the agent template

added_to_agent_at: Optional[datetime]

Time when the knowledge base was added to the agent

formatdate-time
created_at: Optional[datetime]

Creation date / time

formatdate-time
database_id: Optional[str]
embedding_model_uuid: Optional[str]
is_public: Optional[bool]

Whether the knowledge base is public or not

last_indexing_job: Optional[APIIndexingJob]

IndexingJob description

name: Optional[str]

Name of knowledge base

project_id: Optional[str]
region: Optional[str]

Region code

tags: Optional[List[str]]

Tags to organize related resources

updated_at: Optional[datetime]

Last modified

formatdate-time
user_id: Optional[str]

Id of user that created the knowledge base

formatint64
uuid: Optional[str]

Unique id for knowledge base

long_description: Optional[str]

The long description of the agent template

max_tokens: Optional[int]

The max_tokens setting for the agent template

formatint64
model: Optional[APIAgentModel]

Description of a Model

name: Optional[str]

Name of the agent template

short_description: Optional[str]

The short description of the agent template

summary: Optional[str]

The summary of the agent template

tags: Optional[List[str]]

List of tags associated with the agent template

temperature: Optional[float]

The temperature setting for the agent template

formatfloat
template_type: Optional[Literal["AGENT_TEMPLATE_TYPE_STANDARD", "AGENT_TEMPLATE_TYPE_ONE_CLICK"]]
  • AGENT_TEMPLATE_TYPE_STANDARD: The standard agent template
  • AGENT_TEMPLATE_TYPE_ONE_CLICK: The one click agent template
Accepts one of the following:
"AGENT_TEMPLATE_TYPE_STANDARD"
"AGENT_TEMPLATE_TYPE_ONE_CLICK"
top_p: Optional[float]

The top_p setting for the agent template

formatfloat
updated_at: Optional[datetime]

The agent template's last updated date

formatdate-time
uuid: Optional[str]

Unique id

top_p: Optional[float]
updated_at: Optional[datetime]

Last modified

formatdate-time
url: Optional[str]

Access your agent under this url

user_id: Optional[str]

Id of user that created the agent

formatuint64
uuid: Optional[str]

Unique agent id

version_hash: Optional[str]

The latest version of the agent

workspace: Optional[APIWorkspace]
class APIAgentAPIKeyInfo:

Agent API Key Info

created_at: Optional[datetime]

Creation date

formatdate-time
created_by: Optional[str]

Created by

formatuint64
deleted_at: Optional[datetime]

Deleted date

formatdate-time
name: Optional[str]

Name

secret_key: Optional[str]
uuid: Optional[str]

Uuid

class APIAgentModel:

Description of a Model

agreement: Optional[APIAgreement]

Agreement Description

created_at: Optional[datetime]

Creation date / time

formatdate-time
inference_name: Optional[str]

Internally used name

inference_version: Optional[str]

Internally used version

is_foundational: Optional[bool]

True if it is a foundational model provided by do

metadata: Optional[object]

Additional meta data

name: Optional[str]

Name of the model

parent_uuid: Optional[str]

Unique id of the model, this model is based on

provider: Optional[Literal["MODEL_PROVIDER_DIGITALOCEAN", "MODEL_PROVIDER_ANTHROPIC", "MODEL_PROVIDER_OPENAI"]]
Accepts one of the following:
"MODEL_PROVIDER_DIGITALOCEAN"
"MODEL_PROVIDER_ANTHROPIC"
"MODEL_PROVIDER_OPENAI"
updated_at: Optional[datetime]

Last modified

formatdate-time
upload_complete: Optional[bool]

Model has been fully uploaded

url: Optional[str]

Download url

usecases: Optional[List[Literal["MODEL_USECASE_UNKNOWN", "MODEL_USECASE_AGENT", "MODEL_USECASE_FINETUNED", 4 more]]]

Usecases of the model

Accepts one of the following:
"MODEL_USECASE_UNKNOWN"
"MODEL_USECASE_AGENT"
"MODEL_USECASE_FINETUNED"
"MODEL_USECASE_KNOWLEDGEBASE"
"MODEL_USECASE_GUARDRAIL"
"MODEL_USECASE_REASONING"
"MODEL_USECASE_SERVERLESS"
uuid: Optional[str]

Unique id

version: Optional[APIModelVersion]

Version Information about a Model

class APIAnthropicAPIKeyInfo:

Anthropic API Key Info

created_at: Optional[datetime]

Key creation date

formatdate-time
created_by: Optional[str]

Created by user id from DO

formatuint64
deleted_at: Optional[datetime]

Key deleted date

formatdate-time
name: Optional[str]

Name

updated_at: Optional[datetime]

Key last updated date

formatdate-time
uuid: Optional[str]

Uuid

APIDeploymentVisibility = Literal["VISIBILITY_UNKNOWN", "VISIBILITY_DISABLED", "VISIBILITY_PLAYGROUND", 2 more]
  • VISIBILITY_UNKNOWN: The status of the deployment is unknown
  • VISIBILITY_DISABLED: The deployment is disabled and will no longer service requests
  • VISIBILITY_PLAYGROUND: Deprecated: No longer a valid state
  • VISIBILITY_PUBLIC: The deployment is public and will service requests from the public internet
  • VISIBILITY_PRIVATE: The deployment is private and will only service requests from other agents, or through API keys
"VISIBILITY_UNKNOWN"
"VISIBILITY_DISABLED"
"VISIBILITY_PLAYGROUND"
"VISIBILITY_PUBLIC"
"VISIBILITY_PRIVATE"
class APIOpenAIAPIKeyInfo:

OpenAI API Key Info

created_at: Optional[datetime]

Key creation date

formatdate-time
created_by: Optional[str]

Created by user id from DO

formatuint64
deleted_at: Optional[datetime]

Key deleted date

formatdate-time
models: Optional[List[APIAgentModel]]

Models supported by the openAI api key

agreement: Optional[APIAgreement]

Agreement Description

created_at: Optional[datetime]

Creation date / time

formatdate-time
inference_name: Optional[str]

Internally used name

inference_version: Optional[str]

Internally used version

is_foundational: Optional[bool]

True if it is a foundational model provided by do

metadata: Optional[object]

Additional meta data

name: Optional[str]

Name of the model

parent_uuid: Optional[str]

Unique id of the model, this model is based on

provider: Optional[Literal["MODEL_PROVIDER_DIGITALOCEAN", "MODEL_PROVIDER_ANTHROPIC", "MODEL_PROVIDER_OPENAI"]]
Accepts one of the following:
"MODEL_PROVIDER_DIGITALOCEAN"
"MODEL_PROVIDER_ANTHROPIC"
"MODEL_PROVIDER_OPENAI"
updated_at: Optional[datetime]

Last modified

formatdate-time
upload_complete: Optional[bool]

Model has been fully uploaded

url: Optional[str]

Download url

usecases: Optional[List[Literal["MODEL_USECASE_UNKNOWN", "MODEL_USECASE_AGENT", "MODEL_USECASE_FINETUNED", 4 more]]]

Usecases of the model

Accepts one of the following:
"MODEL_USECASE_UNKNOWN"
"MODEL_USECASE_AGENT"
"MODEL_USECASE_FINETUNED"
"MODEL_USECASE_KNOWLEDGEBASE"
"MODEL_USECASE_GUARDRAIL"
"MODEL_USECASE_REASONING"
"MODEL_USECASE_SERVERLESS"
uuid: Optional[str]

Unique id

version: Optional[APIModelVersion]

Version Information about a Model

name: Optional[str]

Name

updated_at: Optional[datetime]

Key last updated date

formatdate-time
uuid: Optional[str]

Uuid

APIRetrievalMethod = Literal["RETRIEVAL_METHOD_UNKNOWN", "RETRIEVAL_METHOD_REWRITE", "RETRIEVAL_METHOD_STEP_BACK", 2 more]
  • RETRIEVAL_METHOD_UNKNOWN: The retrieval method is unknown
  • RETRIEVAL_METHOD_REWRITE: The retrieval method is rewrite
  • RETRIEVAL_METHOD_STEP_BACK: The retrieval method is step back
  • RETRIEVAL_METHOD_SUB_QUERIES: The retrieval method is sub queries
  • RETRIEVAL_METHOD_NONE: The retrieval method is none
"RETRIEVAL_METHOD_UNKNOWN"
"RETRIEVAL_METHOD_REWRITE"
"RETRIEVAL_METHOD_STEP_BACK"
"RETRIEVAL_METHOD_SUB_QUERIES"
"RETRIEVAL_METHOD_NONE"
class APIWorkspace:
agents: Optional[List[APIAgent]]

Agents

created_at: Optional[datetime]

Creation date

formatdate-time
created_by: Optional[str]

The id of user who created this workspace

formatuint64
created_by_email: Optional[str]

The email of the user who created this workspace

deleted_at: Optional[datetime]

Deleted date

formatdate-time
description: Optional[str]

Description of the workspace

evaluation_test_cases: Optional[List[APIEvaluationTestCase]]

Evaluations

archived_at: Optional[datetime]
created_at: Optional[datetime]
created_by_user_email: Optional[str]
created_by_user_id: Optional[str]
dataset: Optional[Dataset]
created_at: Optional[datetime]

Time created at.

formatdate-time
dataset_name: Optional[str]

Name of the dataset.

dataset_uuid: Optional[str]

UUID of the dataset.

file_size: Optional[str]

The size of the dataset uploaded file in bytes.

formatuint64
has_ground_truth: Optional[bool]

Does the dataset have a ground truth column?

row_count: Optional[int]

Number of rows in the dataset.

formatint64
dataset_name: Optional[str]
dataset_uuid: Optional[str]
description: Optional[str]
latest_version_number_of_runs: Optional[int]
metrics: Optional[List[APIEvaluationMetric]]
description: Optional[str]
inverted: Optional[bool]

If true, the metric is inverted, meaning that a lower value is better.

metric_name: Optional[str]
metric_type: Optional[Literal["METRIC_TYPE_UNSPECIFIED", "METRIC_TYPE_GENERAL_QUALITY", "METRIC_TYPE_RAG_AND_TOOL"]]
Accepts one of the following:
"METRIC_TYPE_UNSPECIFIED"
"METRIC_TYPE_GENERAL_QUALITY"
"METRIC_TYPE_RAG_AND_TOOL"
metric_uuid: Optional[str]
metric_value_type: Optional[Literal["METRIC_VALUE_TYPE_UNSPECIFIED", "METRIC_VALUE_TYPE_NUMBER", "METRIC_VALUE_TYPE_STRING", "METRIC_VALUE_TYPE_PERCENTAGE"]]
Accepts one of the following:
"METRIC_VALUE_TYPE_UNSPECIFIED"
"METRIC_VALUE_TYPE_NUMBER"
"METRIC_VALUE_TYPE_STRING"
"METRIC_VALUE_TYPE_PERCENTAGE"
range_max: Optional[float]

The maximum value for the metric.

formatfloat
range_min: Optional[float]

The minimum value for the metric.

formatfloat
name: Optional[str]
star_metric: Optional[APIStarMetric]
test_case_uuid: Optional[str]
total_runs: Optional[int]
updated_at: Optional[datetime]
updated_by_user_email: Optional[str]
updated_by_user_id: Optional[str]
version: Optional[int]
name: Optional[str]

Name of the workspace

updated_at: Optional[datetime]

Update date

formatdate-time
uuid: Optional[str]

Unique id

AgentsAPI Keys

Create an Agent API Key
agents.api_keys.create(strpath_agent_uuid, APIKeyCreateParams**kwargs) -> APIKeyCreateResponse
post/v2/gen-ai/agents/{agent_uuid}/api_keys
Delete API Key for an Agent
agents.api_keys.delete(strapi_key_uuid, APIKeyDeleteParams**kwargs) -> APIKeyDeleteResponse
delete/v2/gen-ai/agents/{agent_uuid}/api_keys/{api_key_uuid}
List Agent API Keys
agents.api_keys.list(stragent_uuid, APIKeyListParams**kwargs) -> APIKeyListResponse
get/v2/gen-ai/agents/{agent_uuid}/api_keys
Regenerate API Key for an Agent
agents.api_keys.regenerate(strapi_key_uuid, APIKeyRegenerateParams**kwargs) -> APIKeyRegenerateResponse
put/v2/gen-ai/agents/{agent_uuid}/api_keys/{api_key_uuid}/regenerate
Update API Key for an Agent
agents.api_keys.update(strpath_api_key_uuid, APIKeyUpdateParams**kwargs) -> APIKeyUpdateResponse
put/v2/gen-ai/agents/{agent_uuid}/api_keys/{api_key_uuid}

AgentsChat

AgentsChatCompletions

Creates a model response for the given chat conversation.
agents.chat.completions.create(CompletionCreateParams**kwargs) -> CompletionCreateResponse
post/chat/completions?agent=true

AgentsEvaluation Datasets

Create Evaluation Dataset
agents.evaluation_datasets.create(EvaluationDatasetCreateParams**kwargs) -> EvaluationDatasetCreateResponse
post/v2/gen-ai/evaluation_datasets
Create Presigned URLs for Evaluation Dataset File Upload
agents.evaluation_datasets.create_file_upload_presigned_urls(EvaluationDatasetCreateFileUploadPresignedURLsParams**kwargs) -> EvaluationDatasetCreateFileUploadPresignedURLsResponse
post/v2/gen-ai/evaluation_datasets/file_upload_presigned_urls

AgentsEvaluation Metrics

List Evaluation Metrics
agents.evaluation_metrics.list() -> EvaluationMetricListResponse
get/v2/gen-ai/evaluation_metrics
List Datacenter Regions
agents.evaluation_metrics.list_regions(EvaluationMetricListRegionsParams**kwargs) -> EvaluationMetricListRegionsResponse
get/v2/gen-ai/regions

AgentsEvaluation MetricsAnthropic

AgentsEvaluation MetricsAnthropicKeys

Create Anthropic API Key
agents.evaluation_metrics.anthropic.keys.create(KeyCreateParams**kwargs) -> KeyCreateResponse
post/v2/gen-ai/anthropic/keys
Delete Anthropic API Key
agents.evaluation_metrics.anthropic.keys.delete(strapi_key_uuid) -> KeyDeleteResponse
delete/v2/gen-ai/anthropic/keys/{api_key_uuid}
List Anthropic API Keys
agents.evaluation_metrics.anthropic.keys.list(KeyListParams**kwargs) -> KeyListResponse
get/v2/gen-ai/anthropic/keys
List agents by Anthropic key
agents.evaluation_metrics.anthropic.keys.list_agents(struuid, KeyListAgentsParams**kwargs) -> KeyListAgentsResponse
get/v2/gen-ai/anthropic/keys/{uuid}/agents
Get Anthropic API Key
agents.evaluation_metrics.anthropic.keys.retrieve(strapi_key_uuid) -> KeyRetrieveResponse
get/v2/gen-ai/anthropic/keys/{api_key_uuid}
Update Anthropic API Key
agents.evaluation_metrics.anthropic.keys.update(strpath_api_key_uuid, KeyUpdateParams**kwargs) -> KeyUpdateResponse
put/v2/gen-ai/anthropic/keys/{api_key_uuid}

AgentsEvaluation MetricsModels

List Available Models
agents.evaluation_metrics.models.list(ModelListParams**kwargs) -> ModelListResponse
get/v2/gen-ai/models

AgentsEvaluation MetricsOpenAI

AgentsEvaluation MetricsOpenAIKeys

Create OpenAI API Key
agents.evaluation_metrics.openai.keys.create(KeyCreateParams**kwargs) -> KeyCreateResponse
post/v2/gen-ai/openai/keys
Delete OpenAI API Key
agents.evaluation_metrics.openai.keys.delete(strapi_key_uuid) -> KeyDeleteResponse
delete/v2/gen-ai/openai/keys/{api_key_uuid}
List OpenAI API Keys
agents.evaluation_metrics.openai.keys.list(KeyListParams**kwargs) -> KeyListResponse
get/v2/gen-ai/openai/keys
List agents by OpenAI key
agents.evaluation_metrics.openai.keys.list_agents(struuid, KeyListAgentsParams**kwargs) -> KeyListAgentsResponse
get/v2/gen-ai/openai/keys/{uuid}/agents
Get OpenAI API Key
agents.evaluation_metrics.openai.keys.retrieve(strapi_key_uuid) -> KeyRetrieveResponse
get/v2/gen-ai/openai/keys/{api_key_uuid}
Update OpenAI API Key
agents.evaluation_metrics.openai.keys.update(strpath_api_key_uuid, KeyUpdateParams**kwargs) -> KeyUpdateResponse
put/v2/gen-ai/openai/keys/{api_key_uuid}

AgentsEvaluation MetricsWorkspaces

Create a Workspace
agents.evaluation_metrics.workspaces.create(WorkspaceCreateParams**kwargs) -> WorkspaceCreateResponse
post/v2/gen-ai/workspaces
Delete a Workspace
agents.evaluation_metrics.workspaces.delete(strworkspace_uuid) -> WorkspaceDeleteResponse
delete/v2/gen-ai/workspaces/{workspace_uuid}
List Workspaces
agents.evaluation_metrics.workspaces.list() -> WorkspaceListResponse
get/v2/gen-ai/workspaces
List Evaluation Test Cases by Workspace
agents.evaluation_metrics.workspaces.list_evaluation_test_cases(strworkspace_uuid) -> WorkspaceListEvaluationTestCasesResponse
get/v2/gen-ai/workspaces/{workspace_uuid}/evaluation_test_cases
Retrieve an Existing Workspace
agents.evaluation_metrics.workspaces.retrieve(strworkspace_uuid) -> WorkspaceRetrieveResponse
get/v2/gen-ai/workspaces/{workspace_uuid}
Update a Workspace
agents.evaluation_metrics.workspaces.update(strpath_workspace_uuid, WorkspaceUpdateParams**kwargs) -> WorkspaceUpdateResponse
put/v2/gen-ai/workspaces/{workspace_uuid}

AgentsEvaluation MetricsWorkspacesAgents

List agents by Workspace
agents.evaluation_metrics.workspaces.agents.list(strworkspace_uuid, AgentListParams**kwargs) -> AgentListResponse
get/v2/gen-ai/workspaces/{workspace_uuid}/agents
Move Agents to a Workspace
agents.evaluation_metrics.workspaces.agents.move(strpath_workspace_uuid, AgentMoveParams**kwargs) -> AgentMoveResponse
put/v2/gen-ai/workspaces/{workspace_uuid}/agents

AgentsEvaluation Runs

Run an Evaluation Test Case
agents.evaluation_runs.create(EvaluationRunCreateParams**kwargs) -> EvaluationRunCreateResponse
post/v2/gen-ai/evaluation_runs
Retrieve Results of an Evaluation Run
agents.evaluation_runs.list_results(strevaluation_run_uuid, EvaluationRunListResultsParams**kwargs) -> EvaluationRunListResultsResponse
get/v2/gen-ai/evaluation_runs/{evaluation_run_uuid}/results
Retrieve Information About an Existing Evaluation Run
agents.evaluation_runs.retrieve(strevaluation_run_uuid) -> EvaluationRunRetrieveResponse
get/v2/gen-ai/evaluation_runs/{evaluation_run_uuid}
Retrieve Results of an Evaluation Run Prompt
agents.evaluation_runs.retrieve_results(intprompt_id, EvaluationRunRetrieveResultsParams**kwargs) -> EvaluationRunRetrieveResultsResponse
get/v2/gen-ai/evaluation_runs/{evaluation_run_uuid}/results/{prompt_id}
ModelsExpand Collapse
class APIEvaluationMetric:
description: Optional[str]
inverted: Optional[bool]

If true, the metric is inverted, meaning that a lower value is better.

metric_name: Optional[str]
metric_type: Optional[Literal["METRIC_TYPE_UNSPECIFIED", "METRIC_TYPE_GENERAL_QUALITY", "METRIC_TYPE_RAG_AND_TOOL"]]
Accepts one of the following:
"METRIC_TYPE_UNSPECIFIED"
"METRIC_TYPE_GENERAL_QUALITY"
"METRIC_TYPE_RAG_AND_TOOL"
metric_uuid: Optional[str]
metric_value_type: Optional[Literal["METRIC_VALUE_TYPE_UNSPECIFIED", "METRIC_VALUE_TYPE_NUMBER", "METRIC_VALUE_TYPE_STRING", "METRIC_VALUE_TYPE_PERCENTAGE"]]
Accepts one of the following:
"METRIC_VALUE_TYPE_UNSPECIFIED"
"METRIC_VALUE_TYPE_NUMBER"
"METRIC_VALUE_TYPE_STRING"
"METRIC_VALUE_TYPE_PERCENTAGE"
range_max: Optional[float]

The maximum value for the metric.

formatfloat
range_min: Optional[float]

The minimum value for the metric.

formatfloat
class APIEvaluationMetricResult:
error_description: Optional[str]

Error description if the metric could not be calculated.

metric_name: Optional[str]

Metric name

metric_value_type: Optional[Literal["METRIC_VALUE_TYPE_UNSPECIFIED", "METRIC_VALUE_TYPE_NUMBER", "METRIC_VALUE_TYPE_STRING", "METRIC_VALUE_TYPE_PERCENTAGE"]]
Accepts one of the following:
"METRIC_VALUE_TYPE_UNSPECIFIED"
"METRIC_VALUE_TYPE_NUMBER"
"METRIC_VALUE_TYPE_STRING"
"METRIC_VALUE_TYPE_PERCENTAGE"
number_value: Optional[float]

The value of the metric as a number.

formatdouble
reasoning: Optional[str]

Reasoning of the metric result.

string_value: Optional[str]

The value of the metric as a string.

class APIEvaluationPrompt:
ground_truth: Optional[str]

The ground truth for the prompt.

input: Optional[str]
input_tokens: Optional[str]

The number of input tokens used in the prompt.

formatuint64
output: Optional[str]
output_tokens: Optional[str]

The number of output tokens used in the prompt.

formatuint64
prompt_chunks: Optional[List[PromptChunk]]

The list of prompt chunks.

chunk_usage_pct: Optional[float]

The usage percentage of the chunk.

formatdouble
chunk_used: Optional[bool]

Indicates if the chunk was used in the prompt.

index_uuid: Optional[str]

The index uuid (Knowledge Base) of the chunk.

source_name: Optional[str]

The source name for the chunk, e.g., the file name or document title.

text: Optional[str]

Text content of the chunk.

prompt_id: Optional[int]

Prompt ID

formatint64
prompt_level_metric_results: Optional[List[APIEvaluationMetricResult]]

The metric results for the prompt.

error_description: Optional[str]

Error description if the metric could not be calculated.

metric_name: Optional[str]

Metric name

metric_value_type: Optional[Literal["METRIC_VALUE_TYPE_UNSPECIFIED", "METRIC_VALUE_TYPE_NUMBER", "METRIC_VALUE_TYPE_STRING", "METRIC_VALUE_TYPE_PERCENTAGE"]]
Accepts one of the following:
"METRIC_VALUE_TYPE_UNSPECIFIED"
"METRIC_VALUE_TYPE_NUMBER"
"METRIC_VALUE_TYPE_STRING"
"METRIC_VALUE_TYPE_PERCENTAGE"
number_value: Optional[float]

The value of the metric as a number.

formatdouble
reasoning: Optional[str]

Reasoning of the metric result.

string_value: Optional[str]

The value of the metric as a string.

class APIEvaluationRun:
agent_deleted: Optional[bool]

Whether agent is deleted

agent_name: Optional[str]

Agent name

agent_uuid: Optional[str]

Agent UUID.

agent_version_hash: Optional[str]

Version hash

agent_workspace_uuid: Optional[str]

Agent workspace uuid

created_by_user_email: Optional[str]
created_by_user_id: Optional[str]
error_description: Optional[str]

The error description

evaluation_run_uuid: Optional[str]

Evaluation run UUID.

evaluation_test_case_workspace_uuid: Optional[str]

Evaluation test case workspace uuid

finished_at: Optional[datetime]

Run end time.

formatdate-time
pass_status: Optional[bool]

The pass status of the evaluation run based on the star metric.

queued_at: Optional[datetime]

Run queued time.

formatdate-time
run_level_metric_results: Optional[List[APIEvaluationMetricResult]]
error_description: Optional[str]

Error description if the metric could not be calculated.

metric_name: Optional[str]

Metric name

metric_value_type: Optional[Literal["METRIC_VALUE_TYPE_UNSPECIFIED", "METRIC_VALUE_TYPE_NUMBER", "METRIC_VALUE_TYPE_STRING", "METRIC_VALUE_TYPE_PERCENTAGE"]]
Accepts one of the following:
"METRIC_VALUE_TYPE_UNSPECIFIED"
"METRIC_VALUE_TYPE_NUMBER"
"METRIC_VALUE_TYPE_STRING"
"METRIC_VALUE_TYPE_PERCENTAGE"
number_value: Optional[float]

The value of the metric as a number.

formatdouble
reasoning: Optional[str]

Reasoning of the metric result.

string_value: Optional[str]

The value of the metric as a string.

run_name: Optional[str]

Run name.

star_metric_result: Optional[APIEvaluationMetricResult]
started_at: Optional[datetime]

Run start time.

formatdate-time
status: Optional[Literal["EVALUATION_RUN_STATUS_UNSPECIFIED", "EVALUATION_RUN_QUEUED", "EVALUATION_RUN_RUNNING_DATASET", 6 more]]

Evaluation Run Statuses

Accepts one of the following:
"EVALUATION_RUN_STATUS_UNSPECIFIED"
"EVALUATION_RUN_QUEUED"
"EVALUATION_RUN_RUNNING_DATASET"
"EVALUATION_RUN_EVALUATING_RESULTS"
"EVALUATION_RUN_CANCELLING"
"EVALUATION_RUN_CANCELLED"
"EVALUATION_RUN_SUCCESSFUL"
"EVALUATION_RUN_PARTIALLY_SUCCESSFUL"
"EVALUATION_RUN_FAILED"
test_case_description: Optional[str]

Test case description.

test_case_name: Optional[str]

Test case name.

test_case_uuid: Optional[str]

Test-case UUID.

test_case_version: Optional[int]

Test-case-version.

formatint64

AgentsEvaluation Test Cases

Create Evaluation Test Case.
agents.evaluation_test_cases.create(EvaluationTestCaseCreateParams**kwargs) -> EvaluationTestCaseCreateResponse
post/v2/gen-ai/evaluation_test_cases
List Evaluation Test Cases
agents.evaluation_test_cases.list() -> EvaluationTestCaseListResponse
get/v2/gen-ai/evaluation_test_cases
List Evaluation Runs by Test Case
agents.evaluation_test_cases.list_evaluation_runs(strevaluation_test_case_uuid, EvaluationTestCaseListEvaluationRunsParams**kwargs) -> EvaluationTestCaseListEvaluationRunsResponse
get/v2/gen-ai/evaluation_test_cases/{evaluation_test_case_uuid}/evaluation_runs
Retrieve Information About an Existing Evaluation Test Case
agents.evaluation_test_cases.retrieve(strtest_case_uuid, EvaluationTestCaseRetrieveParams**kwargs) -> EvaluationTestCaseRetrieveResponse
get/v2/gen-ai/evaluation_test_cases/{test_case_uuid}
Update an Evaluation Test Case.
agents.evaluation_test_cases.update(strpath_test_case_uuid, EvaluationTestCaseUpdateParams**kwargs) -> EvaluationTestCaseUpdateResponse
put/v2/gen-ai/evaluation_test_cases/{test_case_uuid}
ModelsExpand Collapse
class APIEvaluationTestCase:
archived_at: Optional[datetime]
created_at: Optional[datetime]
created_by_user_email: Optional[str]
created_by_user_id: Optional[str]
dataset: Optional[Dataset]
created_at: Optional[datetime]

Time created at.

formatdate-time
dataset_name: Optional[str]

Name of the dataset.

dataset_uuid: Optional[str]

UUID of the dataset.

file_size: Optional[str]

The size of the dataset uploaded file in bytes.

formatuint64
has_ground_truth: Optional[bool]

Does the dataset have a ground truth column?

row_count: Optional[int]

Number of rows in the dataset.

formatint64
dataset_name: Optional[str]
dataset_uuid: Optional[str]
description: Optional[str]
latest_version_number_of_runs: Optional[int]
metrics: Optional[List[APIEvaluationMetric]]
description: Optional[str]
inverted: Optional[bool]

If true, the metric is inverted, meaning that a lower value is better.

metric_name: Optional[str]
metric_type: Optional[Literal["METRIC_TYPE_UNSPECIFIED", "METRIC_TYPE_GENERAL_QUALITY", "METRIC_TYPE_RAG_AND_TOOL"]]
Accepts one of the following:
"METRIC_TYPE_UNSPECIFIED"
"METRIC_TYPE_GENERAL_QUALITY"
"METRIC_TYPE_RAG_AND_TOOL"
metric_uuid: Optional[str]
metric_value_type: Optional[Literal["METRIC_VALUE_TYPE_UNSPECIFIED", "METRIC_VALUE_TYPE_NUMBER", "METRIC_VALUE_TYPE_STRING", "METRIC_VALUE_TYPE_PERCENTAGE"]]
Accepts one of the following:
"METRIC_VALUE_TYPE_UNSPECIFIED"
"METRIC_VALUE_TYPE_NUMBER"
"METRIC_VALUE_TYPE_STRING"
"METRIC_VALUE_TYPE_PERCENTAGE"
range_max: Optional[float]

The maximum value for the metric.

formatfloat
range_min: Optional[float]

The minimum value for the metric.

formatfloat
name: Optional[str]
star_metric: Optional[APIStarMetric]
test_case_uuid: Optional[str]
total_runs: Optional[int]
updated_at: Optional[datetime]
updated_by_user_email: Optional[str]
updated_by_user_id: Optional[str]
version: Optional[int]
class APIStarMetric:
metric_uuid: Optional[str]
name: Optional[str]
success_threshold: Optional[float]

The success threshold for the star metric. This is a value that the metric must reach to be considered successful.

formatfloat
success_threshold_pct: Optional[int]

The success threshold for the star metric. This is a percentage value between 0 and 100.

formatint32

AgentsFunctions

Add Function Route to an Agent
agents.functions.create(strpath_agent_uuid, FunctionCreateParams**kwargs) -> FunctionCreateResponse
post/v2/gen-ai/agents/{agent_uuid}/functions
Delete Function Route for an Agent
agents.functions.delete(strfunction_uuid, FunctionDeleteParams**kwargs) -> FunctionDeleteResponse
delete/v2/gen-ai/agents/{agent_uuid}/functions/{function_uuid}
Update Function Route for an Agent
agents.functions.update(strpath_function_uuid, FunctionUpdateParams**kwargs) -> FunctionUpdateResponse
put/v2/gen-ai/agents/{agent_uuid}/functions/{function_uuid}

AgentsKnowledge Bases

Attach Knowledge Bases to an Agent
agents.knowledge_bases.attach(stragent_uuid) -> APILinkKnowledgeBaseOutput
post/v2/gen-ai/agents/{agent_uuid}/knowledge_bases
Attach Knowledge Base to an Agent
agents.knowledge_bases.attach_single(strknowledge_base_uuid, KnowledgeBaseAttachSingleParams**kwargs) -> APILinkKnowledgeBaseOutput
post/v2/gen-ai/agents/{agent_uuid}/knowledge_bases/{knowledge_base_uuid}
Detach Knowledge Base from an Agent
agents.knowledge_bases.detach(strknowledge_base_uuid, KnowledgeBaseDetachParams**kwargs) -> KnowledgeBaseDetachResponse
delete/v2/gen-ai/agents/{agent_uuid}/knowledge_bases/{knowledge_base_uuid}
ModelsExpand Collapse

Information about a linked knowledge base

An Agent

AgentsRoutes

Add Agent Route to an Agent
agents.routes.add(strpath_child_agent_uuid, RouteAddParams**kwargs) -> RouteAddResponse
post/v2/gen-ai/agents/{parent_agent_uuid}/child_agents/{child_agent_uuid}
Delete Agent Route for an Agent
agents.routes.delete(strchild_agent_uuid, RouteDeleteParams**kwargs) -> RouteDeleteResponse
delete/v2/gen-ai/agents/{parent_agent_uuid}/child_agents/{child_agent_uuid}
Update Agent Route for an Agent
agents.routes.update(strpath_child_agent_uuid, RouteUpdateParams**kwargs) -> RouteUpdateResponse
put/v2/gen-ai/agents/{parent_agent_uuid}/child_agents/{child_agent_uuid}
View Agent Routes
agents.routes.view(struuid) -> RouteViewResponse
get/v2/gen-ai/agents/{uuid}/child_agents

AgentsVersions

List Agent Versions
agents.versions.list(struuid, VersionListParams**kwargs) -> VersionListResponse
get/v2/gen-ai/agents/{uuid}/versions
Rollback to Agent Version
agents.versions.update(strpath_uuid, VersionUpdateParams**kwargs) -> VersionUpdateResponse
put/v2/gen-ai/agents/{uuid}/versions