Create assistant
Create an assistant with a model and instructions.
ParametersExpand Collapse
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.
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.
ChatModel = :"gpt-5.2" | :"gpt-5.2-2025-12-11" | :"gpt-5.2-chat-latest" | 69 more
The description of the assistant. The maximum length is 512 characters.
The system instructions that the assistant uses. The maximum length is 256,000 characters.
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.
The name of the assistant. The maximum length is 256 characters.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1 default to medium reasoning effort, and do not support none.
- The
gpt-5-pro model defaults to (and only supports) high reasoning effort.
xhigh is supported for all models after gpt-5.1-codex-max.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. - The
gpt-5-promodel defaults to (and only supports)highreasoning effort. xhighis supported for all models aftergpt-5.1-codex-max.
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.
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.
auto is the default value
class ResponseFormatText { type } Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject { type } JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema { json_schema, type } JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: { name, description, schema, strict}Structured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
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: { 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.
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: { file_ids}
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: { vector_store_ids, vector_stores}
The vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.
vector_stores: Array[{ chunking_strategy, file_ids, metadata}]A helper to create a vector store with file_ids and attach it to this assistant. There can be a maximum of 1 vector store attached to the assistant.
A helper to create a vector store with file_ids and attach it to this assistant. There can be a maximum of 1 vector store attached to the assistant.
chunking_strategy: { type} | { static, type}The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.
The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.
class Auto { type } The default strategy. This strategy currently uses a max_chunk_size_tokens of 800 and chunk_overlap_tokens of 400.
The default strategy. This strategy currently uses a max_chunk_size_tokens of 800 and chunk_overlap_tokens of 400.
Always auto.
class Static { static, type }
static: { chunk_overlap_tokens, max_chunk_size_tokens}
The number of tokens that overlap between chunks. The default value is 400.
Note that the overlap must not exceed half of max_chunk_size_tokens.
The maximum number of tokens in each chunk. The default value is 800. The minimum value is 100 and the maximum value is 4096.
Always static.
A list of file IDs to add to the vector store. There can be a maximum of 10000 files in a vector store.
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.
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.
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.
class CodeInterpreterTool { type }
The type of tool being defined: code_interpreter
class FileSearchTool { type, file_search }
The type of tool being defined: file_search
file_search: { max_num_results, ranking_options}Overrides for the file search tool.
Overrides for the file search tool.
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.
ranking_options: { 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.
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.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: :auto | :default_2024_08_21The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool { function, type }
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
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.
ReturnsExpand Collapse
class Assistant { id, created_at, description, 10 more } Represents an assistant that can call the model and use tools.
Represents an assistant that can call the model and use tools.
The identifier, which can be referenced in API endpoints.
The Unix timestamp (in seconds) for when the assistant was created.
The description of the assistant. The maximum length is 512 characters.
The system instructions that the assistant uses. The maximum length is 256,000 characters.
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.
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.
The name of the assistant. The maximum length is 256 characters.
The object type, which is always assistant.
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.
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.
class CodeInterpreterTool { type }
The type of tool being defined: code_interpreter
class FileSearchTool { type, file_search }
The type of tool being defined: file_search
file_search: { max_num_results, ranking_options}Overrides for the file search tool.
Overrides for the file search tool.
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.
ranking_options: { 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.
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.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: :auto | :default_2024_08_21The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool { function, type }
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
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.
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.
auto is the default value
class ResponseFormatText { type } Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject { type } JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema { json_schema, type } JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: { name, description, schema, strict}Structured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
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: { 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.
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: { file_ids}
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: { vector_store_ids}
The ID of the vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.
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.
Create assistant
require "openai"
openai = OpenAI::Client.new(api_key: "My API Key")
assistant = openai.beta.assistants.create(model: :"gpt-4o")
puts(assistant){
"id": "id",
"created_at": 0,
"description": "description",
"instructions": "instructions",
"metadata": {
"foo": "string"
},
"model": "model",
"name": "name",
"object": "assistant",
"tools": [
{
"type": "code_interpreter"
}
],
"response_format": "auto",
"temperature": 1,
"tool_resources": {
"code_interpreter": {
"file_ids": [
"string"
]
},
"file_search": {
"vector_store_ids": [
"string"
]
}
},
"top_p": 1
}Returns Examples
{
"id": "id",
"created_at": 0,
"description": "description",
"instructions": "instructions",
"metadata": {
"foo": "string"
},
"model": "model",
"name": "name",
"object": "assistant",
"tools": [
{
"type": "code_interpreter"
}
],
"response_format": "auto",
"temperature": 1,
"tool_resources": {
"code_interpreter": {
"file_ids": [
"string"
]
},
"file_search": {
"vector_store_ids": [
"string"
]
}
},
"top_p": 1
}