assistants

Creates, updates, deletes, gets or lists a assistants resource.

Overview

Name	assistants
Type	Resource
Id	openai.assistants.assistants

Fields

Name	Datatype	Description
id	string	The identifier, which can be referenced in API endpoints.
name	string	The name of the assistant. The maximum length is 256 characters.
description	string	The description of the assistant. The maximum length is 512 characters.
created_at	integer	The Unix timestamp (in seconds) for when the assistant was created.
instructions	string	The system instructions that the assistant uses. The maximum length is 256,000 characters.
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long.
model	string	ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.
object	string	The object type, which is always assistant.
response_format	``	Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide. Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON. Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
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.
tool_resources	object	A set of resources that are used by the assistant'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.
tools	array	A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, file_search, or function.
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.

Methods

Name	Accessible by	Required Params	Description
get_assistant	SELECT	assistant_id
list_assistants	SELECT
create_assistant	INSERT	data__model
delete_assistant	DELETE	assistant_id
modify_assistant	UPDATE	assistant_id

SELECT examples

SELECT
id,
name,
description,
created_at,
instructions,
metadata,
model,
object,
response_format,
temperature,
tool_resources,
tools,
top_p
FROM openai.assistants.assistants
;

INSERT example

Use the following StackQL query and manifest file to create a new assistants resource.

Required Properties

/*+ create */
INSERT INTO openai.assistants.assistants (
data__model,
data__name,
data__description,
data__instructions,
data__tools,
data__tool_resources,
data__metadata,
data__temperature,
data__top_p,
data__response_format
)
SELECT 
'{{ model }}',
'{{ name }}',
'{{ description }}',
'{{ instructions }}',
'{{ tools }}',
'{{ tool_resources }}',
'{{ metadata }}',
'{{ temperature }}',
'{{ top_p }}',
'{{ response_format }}'
;

All Properties

/*+ create */
INSERT INTO openai.assistants.assistants (
data__model
)
SELECT 
'{{ model }}'
;

Manifest

- name: assistants
  props:
    - name: data__model
      value: string
    - name: model
      value: string
    - name: name
      value: string
    - name: description
      value: string
    - name: instructions
      value: string
    - name: tools
      value: array
      props:
        - name: type
          value: string
    - name: tool_resources
      props:
        - name: code_interpreter
          props:
            - name: file_ids
              value: array
        - name: file_search
          value: string
    - name: metadata
      value: object
    - name: temperature
      value: number
    - name: top_p
      value: number
    - name: response_format
      value: string

UPDATE example

Updates a assistants resource.

/*+ update */
UPDATE openai.assistants.assistants
SET 
model = '{{ model }}',
name = '{{ name }}',
description = '{{ description }}',
instructions = '{{ instructions }}',
tools = '{{ tools }}',
tool_resources = '{{ tool_resources }}',
metadata = '{{ metadata }}',
temperature = number,
top_p = number,
response_format = '{{ response_format }}'
WHERE 
assistant_id = '{{ assistant_id }}';

DELETE example

Deletes the specified assistants resource.

/*+ delete */
DELETE FROM openai.assistants.assistants
WHERE assistant_id = '{{ assistant_id }}';