Class BetaAssistantCreateParams.BetaAssistantCreateBody.Builder
-
- All Implemented Interfaces:
public final class BetaAssistantCreateParams.BetaAssistantCreateBody.Builder
-
-
Constructor Summary
Constructors Constructor Description BetaAssistantCreateParams.BetaAssistantCreateBody.Builder()
-
Method Summary
-
-
Method Detail
-
model
final BetaAssistantCreateParams.BetaAssistantCreateBody.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 BetaAssistantCreateParams.BetaAssistantCreateBody.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 BetaAssistantCreateParams.BetaAssistantCreateBody.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 BetaAssistantCreateParams.BetaAssistantCreateBody.Builder description(String description)
The description of the assistant. The maximum length is 512 characters.
-
description
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder description(Optional<String> description)
The description of the assistant. The maximum length is 512 characters.
-
description
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder description(JsonField<String> description)
The description of the assistant. The maximum length is 512 characters.
-
instructions
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder instructions(String instructions)
The system instructions that the assistant uses. The maximum length is 256,000 characters.
-
instructions
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder instructions(Optional<String> instructions)
The system instructions that the assistant uses. The maximum length is 256,000 characters.
-
instructions
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder instructions(JsonField<String> instructions)
The system instructions that the assistant uses. The maximum length is 256,000 characters.
-
metadata
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder metadata(JsonValue 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. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long.
-
name
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder name(String name)
The name of the assistant. The maximum length is 256 characters.
-
name
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder name(Optional<String> name)
The name of the assistant. The maximum length is 256 characters.
-
name
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder name(JsonField<String> name)
The name of the assistant. The maximum length is 256 characters.
-
responseFormat
final BetaAssistantCreateParams.BetaAssistantCreateBody.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 exceededmax_tokensor the conversation exceeded the max context length.
-
responseFormat
final BetaAssistantCreateParams.BetaAssistantCreateBody.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 exceededmax_tokensor the conversation exceeded the max context length.
-
responseFormat
final BetaAssistantCreateParams.BetaAssistantCreateBody.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 exceededmax_tokensor the conversation exceeded the max context length.
-
responseFormat
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder responseFormat(AssistantResponseFormatOption.Behavior behavior)
autois the default value
-
responseFormat
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder responseFormat(ResponseFormatText responseFormatText)
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 exceededmax_tokensor the conversation exceeded the max context length.
-
responseFormat
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder responseFormat(ResponseFormatJsonObject responseFormatJsonObject)
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 exceededmax_tokensor the conversation exceeded the max context length.
-
responseFormat
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder responseFormat(ResponseFormatJsonSchema responseFormatJsonSchema)
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 exceededmax_tokensor the conversation exceeded the max context length.
-
temperature
final BetaAssistantCreateParams.BetaAssistantCreateBody.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 BetaAssistantCreateParams.BetaAssistantCreateBody.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 BetaAssistantCreateParams.BetaAssistantCreateBody.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 BetaAssistantCreateParams.BetaAssistantCreateBody.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 BetaAssistantCreateParams.BetaAssistantCreateBody.Builder toolResources(BetaAssistantCreateParams.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_interpretertool requires a list of file IDs, while thefile_searchtool requires a list of vector store IDs.
-
toolResources
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder toolResources(Optional<BetaAssistantCreateParams.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_interpretertool requires a list of file IDs, while thefile_searchtool requires a list of vector store IDs.
-
toolResources
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder toolResources(JsonField<BetaAssistantCreateParams.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_interpretertool requires a list of file IDs, while thefile_searchtool requires a list of vector store IDs.
-
tools
final BetaAssistantCreateParams.BetaAssistantCreateBody.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, orfunction.
-
tools
final BetaAssistantCreateParams.BetaAssistantCreateBody.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, orfunction.
-
addTool
final BetaAssistantCreateParams.BetaAssistantCreateBody.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, orfunction.
-
addTool
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder addTool(CodeInterpreterTool codeInterpreterTool)
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, orfunction.
-
addTool
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder addTool(FileSearchTool fileSearchTool)
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, orfunction.
-
addTool
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder addTool(FunctionTool functionTool)
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, orfunction.
-
topP
final BetaAssistantCreateParams.BetaAssistantCreateBody.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 BetaAssistantCreateParams.BetaAssistantCreateBody.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 BetaAssistantCreateParams.BetaAssistantCreateBody.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 BetaAssistantCreateParams.BetaAssistantCreateBody.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.
-
additionalProperties
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder additionalProperties(Map<String, JsonValue> additionalProperties)
-
putAdditionalProperty
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder putAdditionalProperty(String key, JsonValue value)
-
putAllAdditionalProperties
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder putAllAdditionalProperties(Map<String, JsonValue> additionalProperties)
-
removeAdditionalProperty
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder removeAdditionalProperty(String key)
-
removeAllAdditionalProperties
final BetaAssistantCreateParams.BetaAssistantCreateBody.Builder removeAllAdditionalProperties(Set<String> keys)
-
build
final BetaAssistantCreateParams.BetaAssistantCreateBody build()
-
-
-
-