Assistants

Build Assistants that can call models and use tools.

Modify assistant

Deprecated

POST/assistants/{assistant_id}

Delete assistant

Deprecated

DELETE/assistants/{assistant_id}

ModelsExpand Collapse

Assistant = object { id, created_at, description, 10 more }

Represents an assistant that can call the model and use tools.

id: string

The identifier, which can be referenced in API endpoints.

created_at: number

The Unix timestamp (in seconds) for when the assistant was created.

description: string

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

maxLength512

instructions: string

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

maxLength256000

metadata: 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, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

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.

name: string

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

maxLength256

object: "assistant"

The object type, which is always assistant.

tools: array of CodeInterpreterTool { type } or FileSearchTool { type, file_search } or FunctionTool { function, type }

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.

One of the following:

CodeInterpreterTool = object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

FileSearchTool = object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

minimum1

maximum50

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

minimum0

maximum1

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

One of the following:

"auto"

"default_2024_08_21"

FunctionTool = object { function, type }

function: FunctionDefinition { name, description, parameters, strict }

type: "function"

The type of tool being defined: function

response_format: optional AssistantResponseFormatOption

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: optional 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.

minimum0

maximum2

tool_resources: optional object { code_interpreter, file_search }

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.

code_interpreter: optional object { file_ids }

file_ids: optional array of string

A list of file IDs made available to the `code_interpreter`` tool. There can be a maximum of 20 files associated with the tool.

file_search: optional object { vector_store_ids }

vector_store_ids: optional array of string

The ID of the vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.

top_p: optional 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.

minimum0

maximum1

AssistantDeleted = object { id, deleted, object }

id: string

deleted: boolean

object: "assistant.deleted"

AssistantStreamEvent = object { data, event, enabled } or object { data, event } or object { data, event } or 22 more

Represents an event emitted when streaming a Run.

Each event in a server-sent events stream has an event and data property:

event: thread.created
data: {"id": "thread_123", "object": "thread", ...}

We emit events whenever a new object is created, transitions to a new state, or is being streamed in parts (deltas). For example, we emit thread.run.created when a new run is created, thread.run.completed when a run completes, and so on. When an Assistant chooses to create a message during a run, we emit a thread.message.created event, a thread.message.in_progress event, many thread.message.delta events, and finally a thread.message.completed event.

We may add additional events over time, so we recommend handling unknown events gracefully in your code. See the Assistants API quickstart to learn how to integrate the Assistants API with streaming.

One of the following:

object { data, event, enabled }

Occurs when a new thread is created.

data: Thread { id, created_at, metadata, 2 more }

Represents a thread that contains messages.

event: "thread.created"

enabled: optional boolean

Whether to enable input audio transcription.

object { data, event }

Occurs when a new run is created.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.created"

object { data, event }

Occurs when a run moves to a queued status.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.queued"

object { data, event }

Occurs when a run moves to an in_progress status.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.in_progress"

object { data, event }

Occurs when a run moves to a requires_action status.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.requires_action"

object { data, event }

Occurs when a run is completed.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.completed"

object { data, event }

Occurs when a run ends with status incomplete.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.incomplete"

object { data, event }

Occurs when a run fails.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.failed"

object { data, event }

Occurs when a run moves to a cancelling status.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.cancelling"

object { data, event }

Occurs when a run is cancelled.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.cancelled"

object { data, event }

Occurs when a run expires.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.expired"

object { data, event }

Occurs when a run step is created.

data: RunStep { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

event: "thread.run.step.created"

object { data, event }

Occurs when a run step moves to an in_progress state.

data: RunStep { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

event: "thread.run.step.in_progress"

object { data, event }

Occurs when parts of a run step are being streamed.

data: RunStepDeltaEvent { id, delta, object }

Represents a run step delta i.e. any changed fields on a run step during streaming.

event: "thread.run.step.delta"

object { data, event }

Occurs when a run step is completed.

data: RunStep { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

event: "thread.run.step.completed"

object { data, event }

Occurs when a run step fails.

data: RunStep { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

event: "thread.run.step.failed"

object { data, event }

Occurs when a run step is cancelled.

data: RunStep { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

event: "thread.run.step.cancelled"

object { data, event }

Occurs when a run step expires.

data: RunStep { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

event: "thread.run.step.expired"

object { data, event }

Occurs when a message is created.

data: Message { id, assistant_id, attachments, 11 more }

Represents a message within a thread.

event: "thread.message.created"

object { data, event }

Occurs when a message moves to an in_progress state.

data: Message { id, assistant_id, attachments, 11 more }

Represents a message within a thread.

event: "thread.message.in_progress"

object { data, event }

Occurs when parts of a Message are being streamed.

data: MessageDeltaEvent { id, delta, object }

Represents a message delta i.e. any changed fields on a message during streaming.

event: "thread.message.delta"

object { data, event }

Occurs when a message is completed.

data: Message { id, assistant_id, attachments, 11 more }

Represents a message within a thread.

event: "thread.message.completed"

object { data, event }

Occurs when a message ends before it is completed.

data: Message { id, assistant_id, attachments, 11 more }

Represents a message within a thread.

event: "thread.message.incomplete"

ErrorEvent = object { data, event }

Occurs when an error occurs. This can happen due to an internal server error or a timeout.

data: ErrorObject { code, message, param, type }

event: "error"

DoneEvent = object { data, event }

Occurs when a stream ends.

data: "[DONE]"

event: "done"

CodeInterpreterTool = object { type }

type: "code_interpreter"

The type of tool being defined: code_interpreter

FileSearchTool = object { type, file_search }

type: "file_search"

The type of tool being defined: file_search

file_search: optional object { max_num_results, ranking_options }

Overrides for the file search tool.

max_num_results: optional number

The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

minimum1

maximum50

ranking_options: optional object { score_threshold, ranker }

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

See the file search tool documentation for more information.

score_threshold: number

The score threshold for the file search. All values must be a floating point number between 0 and 1.

minimum0

maximum1

ranker: optional "auto" or "default_2024_08_21"

The ranker to use for the file search. If not specified will use the auto ranker.

One of the following:

"auto"

"default_2024_08_21"

FunctionTool = object { function, type }

function: FunctionDefinition { name, description, parameters, strict }

type: "function"

The type of tool being defined: function

MessageStreamEvent = object { data, event } or object { data, event } or object { data, event } or 2 more

Occurs when a message is created.

One of the following:

object { data, event }

Occurs when a message is created.

data: Message { id, assistant_id, attachments, 11 more }

Represents a message within a thread.

event: "thread.message.created"

object { data, event }

Occurs when a message moves to an in_progress state.

data: Message { id, assistant_id, attachments, 11 more }

Represents a message within a thread.

event: "thread.message.in_progress"

object { data, event }

Occurs when parts of a Message are being streamed.

data: MessageDeltaEvent { id, delta, object }

Represents a message delta i.e. any changed fields on a message during streaming.

event: "thread.message.delta"

object { data, event }

Occurs when a message is completed.

data: Message { id, assistant_id, attachments, 11 more }

Represents a message within a thread.

event: "thread.message.completed"

object { data, event }

Occurs when a message ends before it is completed.

data: Message { id, assistant_id, attachments, 11 more }

Represents a message within a thread.

event: "thread.message.incomplete"

RunStepStreamEvent = object { data, event } or object { data, event } or object { data, event } or 4 more

Occurs when a run step is created.

One of the following:

object { data, event }

Occurs when a run step is created.

data: RunStep { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

event: "thread.run.step.created"

object { data, event }

Occurs when a run step moves to an in_progress state.

data: RunStep { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

event: "thread.run.step.in_progress"

object { data, event }

Occurs when parts of a run step are being streamed.

data: RunStepDeltaEvent { id, delta, object }

Represents a run step delta i.e. any changed fields on a run step during streaming.

event: "thread.run.step.delta"

object { data, event }

Occurs when a run step is completed.

data: RunStep { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

event: "thread.run.step.completed"

object { data, event }

Occurs when a run step fails.

data: RunStep { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

event: "thread.run.step.failed"

object { data, event }

Occurs when a run step is cancelled.

data: RunStep { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

event: "thread.run.step.cancelled"

object { data, event }

Occurs when a run step expires.

data: RunStep { id, assistant_id, cancelled_at, 13 more }

Represents a step in execution of a run.

event: "thread.run.step.expired"

RunStreamEvent = object { data, event } or object { data, event } or object { data, event } or 7 more

Occurs when a new run is created.

One of the following:

object { data, event }

Occurs when a new run is created.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.created"

object { data, event }

Occurs when a run moves to a queued status.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.queued"

object { data, event }

Occurs when a run moves to an in_progress status.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.in_progress"

object { data, event }

Occurs when a run moves to a requires_action status.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.requires_action"

object { data, event }

Occurs when a run is completed.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.completed"

object { data, event }

Occurs when a run ends with status incomplete.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.incomplete"

object { data, event }

Occurs when a run fails.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.failed"

object { data, event }

Occurs when a run moves to a cancelling status.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.cancelling"

object { data, event }

Occurs when a run is cancelled.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.cancelled"

object { data, event }

Occurs when a run expires.

data: Run { id, assistant_id, cancelled_at, 24 more }

Represents an execution run on a thread.

event: "thread.run.expired"

ThreadStreamEvent = object { data, event, enabled }

Occurs when a new thread is created.

data: Thread { id, created_at, metadata, 2 more }

Represents a thread that contains messages.

event: "thread.created"

enabled: optional boolean

Whether to enable input audio transcription.

Suggested

Assistants

List assistants

Create assistant

Retrieve assistant

Modify assistant

Delete assistant

ModelsExpand Collapse