Update Agent

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

string

required

The id of the agent.

Body

application/json

hooks

object[]

The hooks of the agent. These are used for real-time conversation events such as function_calls, messages and much more.

initial_message

string

The initial message that the agent will say. If null, the agent will wait for the user to speak first.

language_model

object

The language model of the agent.

language_model.provider

enum<string>

required

The language model provider.

Available options:

openai

language_model.credential_id

string

The credential id to use for the provider. If null, we include the provider cost in the conversation.

language_model.max_tokens

integer

default:

300

The maximum number of tokens to generate for an each response from the agent. Default is 300.

language_model.model

default:

gpt-3.5-turbo-0125

The OpenAI language model to use.

Available options:

gpt-3.5-turbo,

gpt-3.5-turbo-0125,

gpt-3.5-turbo-1106,

gpt-3.5-turbo-16k,

gpt-3.5-turbo-0613,

gpt-4-turbo,

gpt-4-turbo-2024-04-09,

gpt-4-turbo-preview,

gpt-4-0125-preview,

gpt-4-1106-preview,

gpt-4-0613,

gpt-4,

gpt-4o

language_model.temperature

number

default:

The temperature of the model. Default is 0 for optimized caching performance.

Required range: 0 < x < 2

language_model.tools

object[]

The list of OpenAI tools.

max_duration_seconds

integer

default:

600

The maximum conversation duration in seconds. If null, the conversation can be of any duration. The default value is 10 min.

metadata

object

The metadata of the agent. This is used to store additional information about the agent.

prompt

string

The prompt of the agent.

transcriber

object

The transcriber of the agent.

voice

object

The synthesizer of the agent.

webhooks

object[]

The webhooks of the agent. These are used for real-time conversation events such as function_calls, messages and much more.

Response

200 - application/json

account_id

string

required

The id of the owner of the agent.

created_at

string

required

The date and time the agent was created.

string

required

The id of the agent.

updated_at

string

required

The date and time the agent was last updated.

uri

string

required

The uri of the agent.

hooks

object[]

The hooks of the agent. These are used for real-time conversation events such as function_calls, messages and much more.

initial_message

string

The initial message that the agent will say. If null, the agent will wait for the user to speak first.

language_model

object

language_model.provider

enum<string>

required

The language model provider.

Available options:

openai

language_model.credential_id

string

The credential id to use for the provider. If null, we include the provider cost in the conversation.

language_model.max_tokens

integer

default:

300

The maximum number of tokens to generate for an each response from the agent. Default is 300.

language_model.model

default:

gpt-3.5-turbo-0125

The OpenAI language model to use.

Available options:

gpt-3.5-turbo,

gpt-3.5-turbo-0125,

gpt-3.5-turbo-1106,

gpt-3.5-turbo-16k,

gpt-3.5-turbo-0613,

gpt-4-turbo,

gpt-4-turbo-2024-04-09,

gpt-4-turbo-preview,

gpt-4-0125-preview,

gpt-4-1106-preview,

gpt-4-0613,

gpt-4,

gpt-4o

language_model.temperature

number

default:

The temperature of the model. Default is 0 for optimized caching performance.

Required range: 0 < x < 2

language_model.tools

object[]

The list of OpenAI tools.

max_duration_seconds

integer

default:

600

The maximum conversation duration in seconds. If null, the conversation can be of any duration. The default value is 10 min.

metadata

object

The metadata of the agent. This is used to store additional information about the agent.

prompt

string

The prompt of the agent.

transcriber

object

voice

object

webhooks

object[]

The webhooks of the agent. These are used for real-time conversation events such as function_calls, messages and much more.

Agents

Conversations

Phone Numbers

Credentials

Authorizations

Path Parameters

Body

Response