Constructor Detail

Method Detail

• model

   final AssistantCreateParams.Builder model(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.

• model

   final AssistantCreateParams.Builder model(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.

• model

   final AssistantCreateParams.Builder model(String value)

  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 AssistantCreateParams.Builder description(String description)

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

• description

   final AssistantCreateParams.Builder description(Optional<String> description)

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

• description

   final AssistantCreateParams.Builder description(JsonField<String> description)

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

• instructions

   final AssistantCreateParams.Builder instructions(String instructions)

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

• instructions

   final AssistantCreateParams.Builder instructions(Optional<String> instructions)

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

• instructions

   final AssistantCreateParams.Builder instructions(JsonField<String> instructions)

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

• metadata

   final AssistantCreateParams.Builder metadata(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.

• metadata

   final AssistantCreateParams.Builder metadata(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.

• metadata

   final AssistantCreateParams.Builder metadata(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 AssistantCreateParams.Builder name(String name)

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

• name

   final AssistantCreateParams.Builder name(Optional<String> name)

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

• name

   final AssistantCreateParams.Builder name(JsonField<String> name)

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

• reasoningEffort

   final AssistantCreateParams.Builder reasoningEffort(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.

• reasoningEffort

   final AssistantCreateParams.Builder reasoningEffort(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.

• reasoningEffort

   final AssistantCreateParams.Builder reasoningEffort(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 AssistantCreateParams.Builder responseFormat(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.

• responseFormat

   final AssistantCreateParams.Builder responseFormat(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.

• responseFormat

   final AssistantCreateParams.Builder responseFormat(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.

• responseFormat

   final AssistantCreateParams.Builder responseFormat(ResponseFormatText responseFormatText)

  Default response format. Used to generate text responses.

• responseFormat

   final AssistantCreateParams.Builder responseFormat(ResponseFormatJsonObject responseFormatJsonObject)

  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.

• responseFormat

   final AssistantCreateParams.Builder responseFormat(ResponseFormatJsonSchema responseFormatJsonSchema)

  JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

• responseFormatJsonValue

   final AssistantCreateParams.Builder responseFormatJsonValue()

  auto is the default value

• temperature

   final AssistantCreateParams.Builder temperature(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.

• temperature

   final AssistantCreateParams.Builder temperature(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.

• temperature

   final AssistantCreateParams.Builder temperature(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.

• temperature

   final AssistantCreateParams.Builder temperature(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 AssistantCreateParams.Builder toolResources(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.

• toolResources

   final AssistantCreateParams.Builder toolResources(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.

• toolResources

   final AssistantCreateParams.Builder toolResources(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 AssistantCreateParams.Builder tools(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.

• tools

   final AssistantCreateParams.Builder tools(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.

• addTool

   final AssistantCreateParams.Builder addTool(AssistantTool tool)

  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.

• addTool

   final AssistantCreateParams.Builder addTool(CodeInterpreterTool codeInterpreter)

  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.

• addTool

   final AssistantCreateParams.Builder addTool(FileSearchTool fileSearch)

  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.

• addTool

   final AssistantCreateParams.Builder addTool(FunctionTool 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.

• addFunctionTool

   final AssistantCreateParams.Builder addFunctionTool(FunctionDefinition 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.

• topP

   final AssistantCreateParams.Builder topP(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.

• topP

   final AssistantCreateParams.Builder topP(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.

• topP

   final AssistantCreateParams.Builder topP(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.

• topP

   final AssistantCreateParams.Builder topP(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 AssistantCreateParams.Builder additionalBodyProperties(Map<String, JsonValue> additionalBodyProperties)

• putAdditionalBodyProperty

   final AssistantCreateParams.Builder putAdditionalBodyProperty(String key, JsonValue value)

• putAllAdditionalBodyProperties

   final AssistantCreateParams.Builder putAllAdditionalBodyProperties(Map<String, JsonValue> additionalBodyProperties)

• removeAdditionalBodyProperty

   final AssistantCreateParams.Builder removeAdditionalBodyProperty(String key)

• removeAllAdditionalBodyProperties

   final AssistantCreateParams.Builder removeAllAdditionalBodyProperties(Set<String> keys)

• additionalHeaders

   final AssistantCreateParams.Builder additionalHeaders(Headers additionalHeaders)

• additionalHeaders

   final AssistantCreateParams.Builder additionalHeaders(Map<String, Iterable<String>> additionalHeaders)

• putAdditionalHeader

   final AssistantCreateParams.Builder putAdditionalHeader(String name, String value)

• putAdditionalHeaders

   final AssistantCreateParams.Builder putAdditionalHeaders(String name, Iterable<String> values)

• putAllAdditionalHeaders

   final AssistantCreateParams.Builder putAllAdditionalHeaders(Headers additionalHeaders)

• putAllAdditionalHeaders

   final AssistantCreateParams.Builder putAllAdditionalHeaders(Map<String, Iterable<String>> additionalHeaders)

• replaceAdditionalHeaders

   final AssistantCreateParams.Builder replaceAdditionalHeaders(String name, String value)

• replaceAdditionalHeaders

   final AssistantCreateParams.Builder replaceAdditionalHeaders(String name, Iterable<String> values)

• replaceAllAdditionalHeaders

   final AssistantCreateParams.Builder replaceAllAdditionalHeaders(Headers additionalHeaders)

• replaceAllAdditionalHeaders

   final AssistantCreateParams.Builder replaceAllAdditionalHeaders(Map<String, Iterable<String>> additionalHeaders)

• removeAdditionalHeaders

   final AssistantCreateParams.Builder removeAdditionalHeaders(String name)

• removeAllAdditionalHeaders

   final AssistantCreateParams.Builder removeAllAdditionalHeaders(Set<String> names)

• additionalQueryParams

   final AssistantCreateParams.Builder additionalQueryParams(QueryParams additionalQueryParams)

• additionalQueryParams

   final AssistantCreateParams.Builder additionalQueryParams(Map<String, Iterable<String>> additionalQueryParams)

• putAdditionalQueryParam

   final AssistantCreateParams.Builder putAdditionalQueryParam(String key, String value)

• putAdditionalQueryParams

   final AssistantCreateParams.Builder putAdditionalQueryParams(String key, Iterable<String> values)

• putAllAdditionalQueryParams

   final AssistantCreateParams.Builder putAllAdditionalQueryParams(QueryParams additionalQueryParams)

• putAllAdditionalQueryParams

   final AssistantCreateParams.Builder putAllAdditionalQueryParams(Map<String, Iterable<String>> additionalQueryParams)

• replaceAdditionalQueryParams

   final AssistantCreateParams.Builder replaceAdditionalQueryParams(String key, String value)

• replaceAdditionalQueryParams

   final AssistantCreateParams.Builder replaceAdditionalQueryParams(String key, Iterable<String> values)

• replaceAllAdditionalQueryParams

   final AssistantCreateParams.Builder replaceAllAdditionalQueryParams(QueryParams additionalQueryParams)

• replaceAllAdditionalQueryParams

   final AssistantCreateParams.Builder replaceAllAdditionalQueryParams(Map<String, Iterable<String>> additionalQueryParams)

• removeAdditionalQueryParams

   final AssistantCreateParams.Builder removeAdditionalQueryParams(String key)

• removeAllAdditionalQueryParams

   final AssistantCreateParams.Builder removeAllAdditionalQueryParams(Set<String> keys)

• build

   final AssistantCreateParams build()