create_assistant
Create custom AI assistants with Telnyx telephony integration by defining instructions, models, and tools like voice calls, messaging, and webhooks.
Instructions
Create a new AI Assistant. The user will provide some details (sometimes detailed, sometimes vague) about the agent they want to create.
Args:
name: Required. Name of the assistant. If not provided, will be generated based on context.
model: Required. Model to use for the assistant. Defaults to meta-llama/Meta-Llama-3.1-70B-Instruct.
instructions: Required. Core instructions or behaviors for the agent.
description: Optional. A summary of the agent's purpose.
tools: Optional. List of tools for the assistant, each containing:
- type: Required. Type of tool ("function", "retrieval", "webhook",
"hangup", "send_dtmf", "transfer").
- function: Optional. For function tools, contains:
- name: Required. Name of the function.
- description: Optional. Description of the function.
- parameters: Required. Parameters schema for the function.
- retrieval: Optional. For retrieval tools, contains:
- bucket_ids: Required. List of bucket IDs for retrieval.
- max_num_results: Optional. Maximum number of results to retrieve.
- webhook: Optional. For webhook tools, contains:
- name: Required. The name of the tool.
- description: Required. The description of the tool.
- url: Required. The URL of the external tool to be called. This URL can be
templated like: https://example.com/api/v1/{id}, where {id} is a
placeholder for a value that will be provided by the assistant if
path_parameters are provided with the id attribute.
- method: Optional. The HTTP method to be used. Possible values:
[GET, POST, PUT, DELETE, PATCH]. Default value: POST.
- headers: Optional. Array of header objects with:
- name: String name of the header.
- value: String value of the header. Supports mustache templating.
e.g., Bearer {{#integration_secret}}test-secret{{/integration_secret}}.
Secrets can be found in `list_integration_secrets`
- body_parameters: Optional. JSON Schema object describing the body parameters:
- properties: Object defining the properties of the body parameters.
- required: Array of strings listing required properties.
- type: String. Possible value: "object".
- path_parameters: Optional. JSON Schema object describing the path parameters:
- properties: Object defining the properties of the path parameters.
- required: Array of strings listing required properties.
- type: String. Possible value: "object".
- query_parameters: Optional. JSON Schema object describing the query parameters:
- properties: Object defining the properties of the query parameters.
- required: Array of strings listing required properties.
- type: String. Possible value: "object".
- hangup: Optional. For hangup tools, contains:
- description: Optional. Description of the hangup function. Defaults to
"This tool is used to hang up the call."
- send_dtmf: Optional. For DTMF tools, contains an empty object. This tool
allows sending DTMF tones during a call.
- transfer: Optional. For transfer tools, contains:
- targets: Required. Array of transfer targets, each with:
- name: Optional. Name of the target.
- to: Required. Destination number or SIP URI.
- from: Required. Number or SIP URI placing the call.
- custom_headers: Optional. Array of custom SIP headers, each with:
- name: Required. Name of the header.
- value: Required. Value of the header. Supports mustache templating.
greeting: Optional. A short welcoming message. Will be generated if not provided.
llm_api_key_ref: Optional. LLM API key reference.
transcription: Optional. Transcription settings with:
- model: Optional. Model to use for transcription.
messaging_settings: Optional. Messaging settings with:
- default_messaging_profile_id: Optional. Default messaging profile ID.
- delivery_status_webhook_url: Optional. Webhook URL for delivery status updates.
insight_settings: Optional. Insight settings with:
- insight_group_id: Optional. Insight group ID.
dynamic_variables_webhook_url: Optional. Dynamic variables webhook URL.
dynamic_variables: Optional. Dynamic variables dictionary.
Returns:
Dict[str, Any]: Response data
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| request | Yes |