Assistant API — assistant

Build assistants that can call models and use tools to perform tasks.

oai_create_assistant(): Create an assistant with a model and instructions.

oai_modify_assistant(): Modify an assistant's properties.

oai_list_assistants(): List all assistants.

oai_retrieve_assistant(): Retrieve an assistant.

oai_delete_assistant(): Delete an assistant.

Usage

oai_create_assistant(
  model,
  name = NULL,
  description = NULL,
  instructions = NULL,
  tools = NULL,
  tool_resources = NULL,
  metadata = NULL,
  temperature = NULL,
  top_p = NULL,
  response_format = NULL,
  .classify_response = TRUE,
  .async = FALSE
)

oai_modify_assistant(
  assistant_id,
  model = NULL,
  name = NULL,
  description = NULL,
  instructions = NULL,
  tools = NULL,
  tool_resources = NULL,
  metadata = NULL,
  temperature = NULL,
  top_p = NULL,
  response_format = NULL,
  .classify_response = TRUE,
  .async = FALSE
)

oai_list_assistants(
  limit = NULL,
  order = NULL,
  after = NULL,
  before = NULL,
  .classify_response = TRUE
)

oai_retrieve_assistant(assistant_id, .classify_response = TRUE, .async = FALSE)

oai_delete_assistant(assistant_id, .async = FALSE)

Arguments

model: Character. ID of the model to use. You can use the oai_list_models() to see all of your available models.
name: Character or NULL. Optional. The name of the assistant. The maximum length is 256 characters.
description: Character or NULL. Optional. The description of the assistant. The maximum length is 512 characters.
instructions: Character or NULL. Optional. The system instructions that the assistant uses. The maximum length is 256,000 characters.
tools: List. Optional. Defaults to NULL. A list of tools 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.
tool_resources: List. Optional. 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.
metadata: List. Optional. 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.
temperature: Numeric. Optional. Defaults to 1. 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.
top_p: Numeric. Optional. Defaults to 1. 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.
response_format: Character or List. Optional. 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 list(type = "json_object") enables JSON mode, which guarantees 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.
.classify_response: Logical. If TRUE (default), the response is classified as an R6 object. If FALSE, the response is returned as a list.
.async: Logical. If TRUE, the request is performed asynchronously.
assistant_id: Character. The ID of the assistant to retrieve.
limit: Integer. Optional. A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
order: Character. Optional. Sort order by the created_at timestamp of the objects. "asc" for ascending order and "desc" for descending order.
after: Character. Optional. A cursor for use in pagination. after 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 after = "obj_foo" in order to fetch the next page of the list.
before: Character. Optional. 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.

Value

Functions oai_create_assistant(), oai_modify_assistant(), and oai_retrieve_assistant() return an Assistant R6 object.

Function oai_list_assistants() returns a list of Assistant R6 objects.

Function oai_delete_assistant() returns the deletion status.