@spec create_assistant(
  (:"gpt-3.5-turbo-16k-0613"
   | :"gpt-3.5-turbo-0125"
   | :"gpt-3.5-turbo-1106"
   | :"gpt-3.5-turbo-0613"
   | :"gpt-3.5-turbo-16k"
   | :"gpt-3.5-turbo"
   | :"gpt-4-32k-0613"
   | :"gpt-4-32k-0314"
   | :"gpt-4-32k"
   | :"gpt-4-0613"
   | :"gpt-4-0314"
   | :"gpt-4"
   | :"gpt-4-vision-preview"
   | :"gpt-4-1106-preview"
   | :"gpt-4-turbo-preview"
   | :"gpt-4-0125-preview"
   | :"gpt-4-turbo-2024-04-09"
   | :"gpt-4-turbo"
   | :"gpt-4o-2024-05-13"
   | :"gpt-4o")
  | String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  top_p: float(),
  tools: [map()],
  tool_resources: %{
    code_interpreter: %{file_ids: [String.t()]},
    file_search: %{
      vector_store_ids: [String.t()],
      vector_stores: [
        %{
          chunking_strategy:
            %{
              static: %{
                chunk_overlap_tokens: integer(),
                max_chunk_size_tokens: integer()
              },
              type: :static
            }
            | %{type: :auto},
          file_ids: [String.t()],
          metadata: map()
        }
      ]
    }
  },
  temperature: float(),
  response_format: ExOpenAI.Components.AssistantsApiResponseFormatOption.t(),
  name: String.t(),
  metadata: map(),
  instructions: String.t(),
  description: String.t(),
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.AssistantObject.t()} | {:error, any()}

Create an assistant with a model and instructions.

Endpoint: https://api.openai.com/v1/assistants

Method: POST

Docs: https://platform.openai.com/docs/api-reference/assistants

Required Arguments:

• model: 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.

Optional Arguments:

• stream_to: PID or function of where to stream content to

• description: The description of the assistant. The maximum length is 512 characters.

• instructions: The system instructions that the assistant uses. The maximum length is 256,000 characters.

• metadata: 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 maxium of 512 characters long.

• name: The name of the assistant. The maximum length is 256 characters.

• response_format:

• temperature: 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.

Example: 1

• tool_resources: 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: 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: 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.

Example: 1

• openai_api_key: OpenAI API key to pass directly. If this is specified, it will override the api_key config value.

• openai_organization_key: OpenAI API key to pass directly. If this is specified, it will override the organization_key config value.

• base_url: Which API endpoint to use as base, defaults to https://api.openai.com/v1

@spec delete_assistant(String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t()
) :: {:ok, ExOpenAI.Components.DeleteAssistantResponse.t()} | {:error, any()}

Delete an assistant.

Endpoint: https://api.openai.com/v1/assistants/{assistant_id}

Method: DELETE

Docs: https://platform.openai.com/docs/api-reference/assistants

Required Arguments:

• assistant_id

Optional Arguments:

• openai_api_key: OpenAI API key to pass directly. If this is specified, it will override the api_key config value.

• openai_organization_key: OpenAI API key to pass directly. If this is specified, it will override the organization_key config value.

• base_url: Which API endpoint to use as base, defaults to https://api.openai.com/v1

@spec get_assistant(String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t()
) :: {:ok, ExOpenAI.Components.AssistantObject.t()} | {:error, any()}

Retrieves an assistant.

Endpoint: https://api.openai.com/v1/assistants/{assistant_id}

Method: GET

Docs: https://platform.openai.com/docs/api-reference/assistants

Required Arguments:

• assistant_id

Optional Arguments:

• openai_api_key: OpenAI API key to pass directly. If this is specified, it will override the api_key config value.

• openai_organization_key: OpenAI API key to pass directly. If this is specified, it will override the organization_key config value.

• base_url: Which API endpoint to use as base, defaults to https://api.openai.com/v1

@spec list_assistants(
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  before: String.t(),
  after: String.t(),
  order: String.t(),
  limit: integer(),
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.ListAssistantsResponse.t()} | {:error, any()}

Returns a list of assistants.

Endpoint: https://api.openai.com/v1/assistants

Method: GET

Docs: https://platform.openai.com/docs/api-reference/assistants

Required Arguments:

Optional Arguments:

• stream_to: PID or function of where to stream content to

• limit

• order

• after

• before

• openai_api_key: OpenAI API key to pass directly. If this is specified, it will override the api_key config value.

• openai_organization_key: OpenAI API key to pass directly. If this is specified, it will override the organization_key config value.

• base_url: Which API endpoint to use as base, defaults to https://api.openai.com/v1

@spec modify_assistant(String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  top_p: float(),
  tools: [map()],
  tool_resources: %{
    code_interpreter: %{file_ids: [String.t()]},
    file_search: %{vector_store_ids: [String.t()]}
  },
  temperature: float(),
  response_format: ExOpenAI.Components.AssistantsApiResponseFormatOption.t(),
  name: String.t(),
  model: String.t(),
  metadata: map(),
  instructions: String.t(),
  description: String.t(),
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.AssistantObject.t()} | {:error, any()}

Modifies an assistant.

Endpoint: https://api.openai.com/v1/assistants/{assistant_id}

Method: POST

Docs: https://platform.openai.com/docs/api-reference/assistants

Required Arguments:

• assistant_id

Optional Arguments:

• stream_to: PID or function of where to stream content to

• description: The description of the assistant. The maximum length is 512 characters.

• instructions: The system instructions that the assistant uses. The maximum length is 256,000 characters.

• metadata: 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 maxium of 512 characters long.

• model: 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.

• name: The name of the assistant. The maximum length is 256 characters.

• response_format:

• temperature: 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.

Example: 1

• tool_resources: 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: 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: 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.

Example: 1

• openai_api_key: OpenAI API key to pass directly. If this is specified, it will override the api_key config value.

• openai_organization_key: OpenAI API key to pass directly. If this is specified, it will override the organization_key config value.

• base_url: Which API endpoint to use as base, defaults to https://api.openai.com/v1