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

Cancels a run that is in_progress.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/runs/{run_id}/cancel

Method: POST

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

Required Arguments:

• thread_id

• run_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 create_message(String.t(), [map()] | String.t(), :assistant | :user,
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  metadata: map(),
  attachments: [%{file_id: String.t(), tools: [map()]}],
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.MessageObject.t()} | {:error, any()}

Create a message.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/messages

Method: POST

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

Required Arguments:

• thread_id

• content:

• role: The role of the entity that is creating the message. Allowed values include:

• user: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages.

• assistant: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation.

Optional Arguments:

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

• attachments: A list of files attached to the message, and the tools they should be added to.

• 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.

• 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 create_run(String.t(), String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  truncation_strategy: ExOpenAI.Components.TruncationObject.t(),
  top_p: float(),
  tools: [map()],
  tool_choice: ExOpenAI.Components.AssistantsApiToolChoiceOption.t(),
  temperature: float(),
  stream: boolean(),
  response_format: ExOpenAI.Components.AssistantsApiResponseFormatOption.t(),
  parallel_tool_calls: ExOpenAI.Components.ParallelToolCalls.t(),
  model:
    (:"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(),
  metadata: map(),
  max_prompt_tokens: integer(),
  max_completion_tokens: integer(),
  instructions: String.t(),
  additional_messages: [ExOpenAI.Components.CreateMessageRequest.t()],
  additional_instructions: String.t(),
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.RunObject.t()} | {:error, any()}

Create a run.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/runs

Method: POST

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

Required Arguments:

• thread_id

• assistant_id: The ID of the assistant to use to execute this run.

Optional Arguments:

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

• additional_instructions: Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.

• additional_messages: Adds additional messages to the thread before creating the run.

• instructions: Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis.

• max_completion_tokens: The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.

• max_prompt_tokens: The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.

• 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: The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.

• parallel_tool_calls:

• response_format:

• stream: If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.

• 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_choice:

• tools: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.

• 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

• truncation_strategy:

• 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 create_thread(
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  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()
        }
      ]
    }
  },
  metadata: map(),
  messages: [ExOpenAI.Components.CreateMessageRequest.t()],
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.ThreadObject.t()} | {:error, any()}

Create a thread.

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

Method: POST

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

Required Arguments:

Optional Arguments:

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

• messages: A list of messages to start the thread with.

• 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.

• tool_resources: A set of resources that are made available to the assistant's tools in this thread. 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.

• 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 create_thread_and_run(String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  truncation_strategy: ExOpenAI.Components.TruncationObject.t(),
  top_p: float(),
  tools: [map()],
  tool_resources: %{
    code_interpreter: %{file_ids: [String.t()]},
    file_search: %{vector_store_ids: [String.t()]}
  },
  tool_choice: ExOpenAI.Components.AssistantsApiToolChoiceOption.t(),
  thread: ExOpenAI.Components.CreateThreadRequest.t(),
  temperature: float(),
  stream: boolean(),
  response_format: ExOpenAI.Components.AssistantsApiResponseFormatOption.t(),
  parallel_tool_calls: ExOpenAI.Components.ParallelToolCalls.t(),
  model:
    (:"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(),
  metadata: map(),
  max_prompt_tokens: integer(),
  max_completion_tokens: integer(),
  instructions: String.t(),
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.RunObject.t()} | {:error, any()}

Create a thread and run it in one request.

Endpoint: https://api.openai.com/v1/threads/runs

Method: POST

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

Required Arguments:

• assistant_id: The ID of the assistant to use to execute this run.

Optional Arguments:

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

• instructions: Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.

• max_completion_tokens: The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.

• max_prompt_tokens: The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.

• 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: The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.

• parallel_tool_calls:

• response_format:

• stream: If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.

• 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

• thread: If no thread is provided, an empty thread will be created.

• tool_choice:

• 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: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.

• 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

• truncation_strategy:

• 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_message(String.t(), String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t()
) :: {:ok, ExOpenAI.Components.DeleteMessageResponse.t()} | {:error, any()}

Deletes a message.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/messages/{message_id}

Method: DELETE

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

Required Arguments:

• thread_id

• message_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 delete_thread(String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t()
) :: {:ok, ExOpenAI.Components.DeleteThreadResponse.t()} | {:error, any()}

Delete a thread.

Endpoint: https://api.openai.com/v1/threads/{thread_id}

Method: DELETE

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

Required Arguments:

• thread_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_message(String.t(), String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t()
) :: {:ok, ExOpenAI.Components.MessageObject.t()} | {:error, any()}

Retrieve a message.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/messages/{message_id}

Method: GET

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

Required Arguments:

• thread_id

• message_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_run(String.t(), String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t()
) :: {:ok, ExOpenAI.Components.RunObject.t()} | {:error, any()}

Retrieves a run.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/runs/{run_id}

Method: GET

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

Required Arguments:

• thread_id

• run_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_run_step(String.t(), String.t(), String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t()
) :: {:ok, ExOpenAI.Components.RunStepObject.t()} | {:error, any()}

Retrieves a run step.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/runs/{run_id}/steps/{step_id}

Method: GET

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

Required Arguments:

• thread_id

• run_id

• step_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_thread(String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t()
) :: {:ok, ExOpenAI.Components.ThreadObject.t()} | {:error, any()}

Retrieves a thread.

Endpoint: https://api.openai.com/v1/threads/{thread_id}

Method: GET

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

Required Arguments:

• thread_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_messages(String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  run_id: String.t(),
  before: String.t(),
  after: String.t(),
  order: String.t(),
  limit: integer(),
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.ListMessagesResponse.t()} | {:error, any()}

Returns a list of messages for a given thread.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/messages

Method: GET

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

Required Arguments:

• thread_id

Optional Arguments:

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

• limit

• order

• after

• before

• run_id

• 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_run_steps(String.t(), String.t(),
  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.ListRunStepsResponse.t()} | {:error, any()}

Returns a list of run steps belonging to a run.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/runs/{run_id}/steps

Method: GET

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

Required Arguments:

• thread_id

• run_id

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 list_runs(String.t(),
  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.ListRunsResponse.t()} | {:error, any()}

Returns a list of runs belonging to a thread.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/runs

Method: GET

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

Required Arguments:

• thread_id

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_message(String.t(), String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  metadata: map(),
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.MessageObject.t()} | {:error, any()}

Modifies a message.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/messages/{message_id}

Method: POST

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

Required Arguments:

• thread_id

• message_id

Optional Arguments:

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

• 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.

• 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_run(String.t(), String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  metadata: map(),
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.RunObject.t()} | {:error, any()}

Modifies a run.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/runs/{run_id}

Method: POST

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

Required Arguments:

• thread_id

• run_id

Optional Arguments:

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

• 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.

• 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_thread(String.t(),
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  tool_resources: %{
    code_interpreter: %{file_ids: [String.t()]},
    file_search: %{vector_store_ids: [String.t()]}
  },
  metadata: map(),
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.ThreadObject.t()} | {:error, any()}

Modifies a thread.

Endpoint: https://api.openai.com/v1/threads/{thread_id}

Method: POST

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

Required Arguments:

• thread_id

Optional Arguments:

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

• 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.

• tool_resources: A set of resources that are made available to the assistant's tools in this thread. 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.

• 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 submit_tool_ouputs_to_run(
  String.t(),
  String.t(),
  [%{output: String.t(), tool_call_id: String.t()}],
  base_url: String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  stream: boolean(),
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.RunObject.t()} | {:error, any()}

When a run has the status: "requires_action" and required_action.type is submit_tool_outputs, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request.

Endpoint: https://api.openai.com/v1/threads/{thread_id}/runs/{run_id}/submit_tool_outputs

Method: POST

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

Required Arguments:

• thread_id

• run_id

• tool_outputs: A list of tools for which the outputs are being submitted.

Optional Arguments:

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

• stream: If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.

• 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