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<AssistantCreateParams.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()

  Returns the raw JSON value of model.

  Unlike model, this method doesn't throw if the JSON field has an unexpected type.

• _description

   final JsonField<String> _description()

  Returns the raw JSON value of description.

  Unlike description, this method doesn't throw if the JSON field has an unexpected type.

• _instructions

   final JsonField<String> _instructions()

  Returns the raw JSON value of instructions.

  Unlike instructions, this method doesn't throw if the JSON field has an unexpected type.

• _metadata

   final JsonField<AssistantCreateParams.Metadata> _metadata()

  Returns the raw JSON value of metadata.

  Unlike metadata, this method doesn't throw if the JSON field has an unexpected type.

• _name

   final JsonField<String> _name()

  Returns the raw JSON value of name.

  Unlike name, this method doesn't throw if the JSON field has an unexpected type.

• _reasoningEffort

   final JsonField<ReasoningEffort> _reasoningEffort()

  Returns the raw JSON value of reasoningEffort.

  Unlike reasoningEffort, this method doesn't throw if the JSON field has an unexpected type.

• _responseFormat

   final JsonField<AssistantResponseFormatOption> _responseFormat()

  Returns the raw JSON value of responseFormat.

  Unlike responseFormat, this method doesn't throw if the JSON field has an unexpected type.

• _temperature

   final JsonField<Double> _temperature()

  Returns the raw JSON value of temperature.

  Unlike temperature, this method doesn't throw if the JSON field has an unexpected type.

• _toolResources

   final JsonField<AssistantCreateParams.ToolResources> _toolResources()

  Returns the raw JSON value of toolResources.

  Unlike toolResources, this method doesn't throw if the JSON field has an unexpected type.

• _tools

   final JsonField<List<AssistantTool>> _tools()

  Returns the raw JSON value of tools.

  Unlike tools, this method doesn't throw if the JSON field has an unexpected type.

• _topP

   final JsonField<Double> _topP()

  Returns the raw JSON value of topP.

  Unlike topP, this method doesn't throw if the JSON field has an unexpected type.

• _additionalProperties

   final Map<String, JsonValue> _additionalProperties()

• toBuilder

   final AssistantCreateParams.Body.Builder toBuilder()

• validate

   final AssistantCreateParams.Body validate()

• isValid

   final Boolean isValid()

• equals

   Boolean equals(Object other)

• hashCode

   Integer hashCode()

• toString

   String toString()

• builder

   final static AssistantCreateParams.Body.Builder builder()

  Returns a mutable builder for constructing an instance of Body.

  The following fields are required:

  .model()