All Implemented Interfaces:: com.openai.core.Params


public final class AssistantCreateParams
 implements Params

Create an assistant with a model and instructions.

Nested Class Summary

Nested Classes
Modifier and Type	Class	Description
`public final class`	`AssistantCreateParams.Body`
`public final class`	`AssistantCreateParams.Builder`	A builder for AssistantCreateParams.
`public final class`	`AssistantCreateParams.ToolResources`	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.

Field Summary

Fields
Modifier and Type	Field	Description

Constructor Summary

Constructors
Constructor	Description

Enum Constant Summary

Enum Constants
Enum Constant	Description

Method Summary

Modifier and Type	Method	Description
`final ChatModel`	`model()`	ID of the model to use.
`final Optional<String>`	`description()`	The description of the assistant.
`final Optional<String>`	`instructions()`	The system instructions that the assistant uses.
`final Optional<Metadata>`	`metadata()`	Set of 16 key-value pairs that can be attached to an object.
`final Optional<String>`	`name()`	The name of the assistant.
`final Optional<ReasoningEffort>`	`reasoningEffort()`	o-series models onlyConstrains effort on reasoning for reasoning models.
`final Optional<AssistantResponseFormatOption>`	`responseFormat()`	Specifies the format that the model must output.
`final Optional<Double>`	`temperature()`	What sampling temperature to use, between 0 and 2.
`final Optional<AssistantCreateParams.ToolResources>`	`toolResources()`	A set of resources that are used by the assistant's tools.
`final Optional<List<AssistantTool>>`	`tools()`	A list of tool enabled on the assistant.
`final Optional<Double>`	`topP()`	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
`final JsonField<ChatModel>`	`_model()`	ID of the model to use.
`final JsonField<String>`	`_description()`	The description of the assistant.
`final JsonField<String>`	`_instructions()`	The system instructions that the assistant uses.
`final JsonField<Metadata>`	`_metadata()`	Set of 16 key-value pairs that can be attached to an object.
`final JsonField<String>`	`_name()`	The name of the assistant.
`final JsonField<ReasoningEffort>`	`_reasoningEffort()`	o-series models onlyConstrains effort on reasoning for reasoning models.
`final JsonField<AssistantResponseFormatOption>`	`_responseFormat()`	Specifies the format that the model must output.
`final JsonField<Double>`	`_temperature()`	What sampling temperature to use, between 0 and 2.
`final JsonField<AssistantCreateParams.ToolResources>`	`_toolResources()`	A set of resources that are used by the assistant's tools.
`final JsonField<List<AssistantTool>>`	`_tools()`	A list of tool enabled on the assistant.
`final JsonField<Double>`	`_topP()`	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
`final Map<String, JsonValue>`	`_additionalBodyProperties()`
`final Headers`	`_additionalHeaders()`
`final QueryParams`	`_additionalQueryParams()`
`Headers`	`_headers()`	The full set of headers in the parameters, including both fixed and additional headers.
`QueryParams`	`_queryParams()`	The full set of query params in the parameters, including both fixed and additional query params.
`final AssistantCreateParams.Builder`	`toBuilder()`
`Boolean`	`equals(Object other)`
`Integer`	`hashCode()`
`String`	`toString()`
`final static AssistantCreateParams.Builder`	`builder()`	Returns a mutable builder for constructing an instance of AssistantCreateParams.

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
- Method Detail
  - model
```
 final ChatModel 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.
  - description
```
 final Optional<String> description()
```
    The description of the assistant. The maximum length is 512 characters.
  - instructions
```
 final Optional<String> instructions()
```
    The system instructions that the assistant uses. The maximum length is 256,000 characters.
  - metadata
```
 final Optional<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.
  - name
```
 final Optional<String> name()
```
    The name of the assistant. The maximum length is 256 characters.
  - reasoningEffort
```
 final Optional<ReasoningEffort> reasoningEffort()
```
    o-series models only
    Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
  - responseFormat
```
 final Optional<AssistantResponseFormatOption> responseFormat()
```
    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
```
 final Optional<Double> 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.
  - toolResources
```
 final Optional<AssistantCreateParams.ToolResources> toolResources()
```
    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
```
 final Optional<List<AssistantTool>> 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.
  - topP
```
 final Optional<Double> topP()
```
    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.
  - _model
```
 final JsonField<ChatModel> _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.
  - _description
```
 final JsonField<String> _description()
```
    The description of the assistant. The maximum length is 512 characters.
  - _instructions
```
 final JsonField<String> _instructions()
```
    The system instructions that the assistant uses. The maximum length is 256,000 characters.
  - _metadata
```
 final JsonField<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.
  - _name
```
 final JsonField<String> _name()
```
    The name of the assistant. The maximum length is 256 characters.
  - _reasoningEffort
```
 final JsonField<ReasoningEffort> _reasoningEffort()
```
    o-series models only
    Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
  - _responseFormat
```
 final JsonField<AssistantResponseFormatOption> _responseFormat()
```
    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
```
 final JsonField<Double> _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.
  - _toolResources
```
 final JsonField<AssistantCreateParams.ToolResources> _toolResources()
```
    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
```
 final JsonField<List<AssistantTool>> _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.
  - _topP
```
 final JsonField<Double> _topP()
```
    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.
  - _additionalBodyProperties
```
 final Map<String, JsonValue> _additionalBodyProperties()
```
  - _additionalHeaders
```
 final Headers _additionalHeaders()
```
  - _additionalQueryParams
```
 final QueryParams _additionalQueryParams()
```
  - _headers
```
 Headers _headers()
```
    The full set of headers in the parameters, including both fixed and additional headers.
  - _queryParams
```
 QueryParams _queryParams()
```
    The full set of query params in the parameters, including both fixed and additional query params.
  - toBuilder
```
 final AssistantCreateParams.Builder toBuilder()
```
  - equals
```
 Boolean equals(Object other)
```
  - hashCode
```
 Integer hashCode()
```
  - toString
```
 String toString()
```
  - builder
```
 final static AssistantCreateParams.Builder builder()
```
    Returns a mutable builder for constructing an instance of AssistantCreateParams.
    The following fields are required:
    .model()

Class AssistantCreateParams

Nested Class Summary

Field Summary

Constructor Summary

Enum Constant Summary

Method Summary

Methods inherited from class java.lang.Object

Constructor Detail

Method Detail

model

description

instructions

metadata

name

reasoningEffort

responseFormat

temperature

toolResources

tools

topP

_model

_description

_instructions

_metadata

_name

_reasoningEffort

_responseFormat

_temperature

_toolResources

_tools

_topP

_additionalBodyProperties

_additionalHeaders

_additionalQueryParams

_headers

_queryParams

toBuilder

equals

hashCode

toString

builder