agents

Creates, updates, deletes, gets or lists an agents resource.

Overview

Name	agents
Type	Resource
Id	azure.ai_agents.agents

Fields

The following fields are returned by SELECT queries:

get_agent

Name	Datatype	Description
id	string	The identifier, which can be referenced in API endpoints. Required.
name	string	The name of the agent. Required.
created_at	string (date-time)	The Unix timestamp, in seconds, representing when this object was created. Required.
description	string	The description of the agent. Required.
instructions	string	The system instructions for the agent to use. Required.
metadata	object	A set of up to 16 key/value pairs that can be attached to an object, used for storing additional information about that object in a structured format. Keys may be up to 64 characters in length and values may be up to 512 characters in length. Required.
model	string	The ID of the model to use. Required.
object	string	The object type, which is always assistant. Required. Default value is "assistant".
response_format	object	The response format of the tool calls used by this agent. Is one of the following types: str, Union[str, "_models.AgentsResponseFormatMode"], AgentsResponseFormat, ResponseFormatJsonSchemaType
temperature	number	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. Required.
tool_resources	object	A set of resources that are used by the agent's tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs. Required.
tools	array	The collection of tools enabled for the agent. Required.
top_p	number	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. Required.

list_agents

Name	Datatype	Description
id	string	The identifier, which can be referenced in API endpoints. Required.
name	string	The name of the agent. Required.
created_at	string (date-time)	The Unix timestamp, in seconds, representing when this object was created. Required.
description	string	The description of the agent. Required.
instructions	string	The system instructions for the agent to use. Required.
metadata	object	A set of up to 16 key/value pairs that can be attached to an object, used for storing additional information about that object in a structured format. Keys may be up to 64 characters in length and values may be up to 512 characters in length. Required.
model	string	The ID of the model to use. Required.
object	string	The object type, which is always assistant. Required. Default value is "assistant".
response_format	object	The response format of the tool calls used by this agent. Is one of the following types: str, Union[str, "_models.AgentsResponseFormatMode"], AgentsResponseFormat, ResponseFormatJsonSchemaType
temperature	number	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. Required.
tool_resources	object	A set of resources that are used by the agent's tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs. Required.
tools	array	The collection of tools enabled for the agent. Required.
top_p	number	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. Required.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get_agent	select	assistant_id, endpoint		Retrieves an existing agent.
list_agents	select	endpoint	limit, order, after, before	Gets a list of agents that were previously created.
create_agent	insert	endpoint		Creates a new agent.
update_agent	exec	assistant_id, endpoint		Modifies an existing agent.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
assistant_id	string	The ID of the agent to modify. Required.
endpoint	string	The service endpoint host (no scheme), e.g. myaccount.table.cosmos.azure.com:443 - value of the client endpoint parameter. (default: )
after	string
before	string	A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list. Default value is None.
limit	integer	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20. Default value is None.
order	string	Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order. Known values are: "asc" and "desc". Default value is None.

SELECT examples

get_agent

Retrieves an existing agent.

SELECT
id,
name,
created_at,
description,
instructions,
metadata,
model,
object,
response_format,
temperature,
tool_resources,
tools,
top_p
FROM azure.ai_agents.agents
WHERE assistant_id = '{{ assistant_id }}' -- required
AND endpoint = '{{ endpoint }}' -- required
;

list_agents

Gets a list of agents that were previously created.

SELECT
id,
name,
created_at,
description,
instructions,
metadata,
model,
object,
response_format,
temperature,
tool_resources,
tools,
top_p
FROM azure.ai_agents.agents
WHERE endpoint = '{{ endpoint }}' -- required
AND limit = '{{ limit }}'
AND order = '{{ order }}'
AND after = '{{ after }}'
AND before = '{{ before }}'
;

INSERT examples

create_agent

Creates a new agent.

INSERT INTO azure.ai_agents.agents (
endpoint
)
SELECT 
'{{ endpoint }}'
RETURNING
id,
name,
created_at,
description,
instructions,
metadata,
model,
object,
response_format,
temperature,
tool_resources,
tools,
top_p
;

Manifest

# Description fields are for documentation purposes
- name: agents
props:
  - name: endpoint
    value: "{{ endpoint }}"
    description: Required parameter for the agents resource.

Lifecycle Methods

update_agent

Modifies an existing agent.

EXEC azure.ai_agents.agents.update_agent 
@assistant_id='{{ assistant_id }}' --required, 
@endpoint='{{ endpoint }}' --required
;