Class BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder
-
- All Implemented Interfaces:
public final class BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder
-
-
Constructor Summary
Constructors Constructor Description BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder()
-
Method Summary
-
-
Method Detail
-
assistantId
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder assistantId(String assistantId)
The ID of the assistant to use to execute this run.
-
assistantId
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder assistantId(JsonField<String> assistantId)
The ID of the assistant to use to execute this run.
-
additionalInstructions
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder additionalInstructions(String additionalInstructions)
Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.
-
additionalInstructions
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder additionalInstructions(Optional<String> additionalInstructions)
Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.
-
additionalInstructions
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder additionalInstructions(JsonField<String> additionalInstructions)
Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.
-
additionalMessages
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder additionalMessages(List<BetaThreadRunCreateParams.AdditionalMessage> additionalMessages)
Adds additional messages to the thread before creating the run.
-
additionalMessages
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder additionalMessages(Optional<List<BetaThreadRunCreateParams.AdditionalMessage>> additionalMessages)
Adds additional messages to the thread before creating the run.
-
additionalMessages
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder additionalMessages(JsonField<List<BetaThreadRunCreateParams.AdditionalMessage>> additionalMessages)
Adds additional messages to the thread before creating the run.
-
addAdditionalMessage
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder addAdditionalMessage(BetaThreadRunCreateParams.AdditionalMessage additionalMessage)
Adds additional messages to the thread before creating the run.
-
instructions
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder instructions(String instructions)
Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis.
-
instructions
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder instructions(Optional<String> instructions)
Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis.
-
instructions
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder instructions(JsonField<String> instructions)
Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis.
-
maxCompletionTokens
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder maxCompletionTokens(Long maxCompletionTokens)
The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status
incomplete
. Seeincomplete_details
for more info.
-
maxCompletionTokens
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder maxCompletionTokens(Long maxCompletionTokens)
The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status
incomplete
. Seeincomplete_details
for more info.
-
maxCompletionTokens
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder maxCompletionTokens(Optional<Long> maxCompletionTokens)
The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status
incomplete
. Seeincomplete_details
for more info.
-
maxCompletionTokens
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder maxCompletionTokens(JsonField<Long> maxCompletionTokens)
The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status
incomplete
. Seeincomplete_details
for more info.
-
maxPromptTokens
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder maxPromptTokens(Long maxPromptTokens)
The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status
incomplete
. Seeincomplete_details
for more info.
-
maxPromptTokens
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder maxPromptTokens(Long maxPromptTokens)
The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status
incomplete
. Seeincomplete_details
for more info.
-
maxPromptTokens
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder maxPromptTokens(Optional<Long> maxPromptTokens)
The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status
incomplete
. Seeincomplete_details
for more info.
-
maxPromptTokens
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder maxPromptTokens(JsonField<Long> maxPromptTokens)
The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status
incomplete
. Seeincomplete_details
for more info.
-
metadata
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.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.
-
model
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder model(ChatModel model)
The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.
-
model
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder model(Optional<ChatModel> model)
The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.
-
model
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder model(JsonField<ChatModel> model)
The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.
-
model
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder model(String value)
The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.
-
parallelToolCalls
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder parallelToolCalls(Boolean parallelToolCalls)
Whether to enable parallel function calling during tool use.
-
parallelToolCalls
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder parallelToolCalls(JsonField<Boolean> parallelToolCalls)
Whether to enable parallel function calling during tool use.
-
responseFormat
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.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_tokens
or the conversation exceeded the max context length.
-
responseFormat
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.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_tokens
or the conversation exceeded the max context length.
-
responseFormat
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.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_tokens
or the conversation exceeded the max context length.
-
responseFormat
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder responseFormat(AssistantResponseFormatOption.Behavior behavior)
auto
is the default value
-
responseFormat
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.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_tokens
or the conversation exceeded the max context length.
-
responseFormat
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.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_tokens
or the conversation exceeded the max context length.
-
responseFormat
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.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_tokens
or the conversation exceeded the max context length.
-
temperature
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.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 BetaThreadRunCreateParams.BetaThreadRunCreateBody.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 BetaThreadRunCreateParams.BetaThreadRunCreateBody.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 BetaThreadRunCreateParams.BetaThreadRunCreateBody.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.
-
toolChoice
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder toolChoice(AssistantToolChoiceOption toolChoice)
Controls which (if any) tool is called by the model.
none
means the model will not call any tools and instead generates a message.auto
is the default value and means the model can pick between generating a message or calling one or more tools.required
means the model must call one or more tools before responding to the user. Specifying a particular tool like{"type": "file_search"}
or{"type": "function", "function": {"name": "my_function"}}
forces the model to call that tool.
-
toolChoice
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder toolChoice(Optional<AssistantToolChoiceOption> toolChoice)
Controls which (if any) tool is called by the model.
none
means the model will not call any tools and instead generates a message.auto
is the default value and means the model can pick between generating a message or calling one or more tools.required
means the model must call one or more tools before responding to the user. Specifying a particular tool like{"type": "file_search"}
or{"type": "function", "function": {"name": "my_function"}}
forces the model to call that tool.
-
toolChoice
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder toolChoice(JsonField<AssistantToolChoiceOption> toolChoice)
Controls which (if any) tool is called by the model.
none
means the model will not call any tools and instead generates a message.auto
is the default value and means the model can pick between generating a message or calling one or more tools.required
means the model must call one or more tools before responding to the user. Specifying a particular tool like{"type": "file_search"}
or{"type": "function", "function": {"name": "my_function"}}
forces the model to call that tool.
-
toolChoice
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder toolChoice(AssistantToolChoiceOption.Behavior behavior)
none
means the model will not call any tools and instead generates a message.auto
means the model can pick between generating a message or calling one or more tools.required
means the model must call one or more tools before responding to the user.
-
toolChoice
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder toolChoice(AssistantToolChoice assistantToolChoice)
Specifies a tool the model should use. Use to force the model to call a specific tool.
-
tools
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder tools(List<AssistantTool> tools)
Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.
-
tools
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder tools(Optional<List<AssistantTool>> tools)
Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.
-
tools
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder tools(JsonField<List<AssistantTool>> tools)
Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.
-
addTool
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder addTool(AssistantTool tool)
Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.
-
addTool
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder addTool(CodeInterpreterTool codeInterpreterTool)
Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.
-
addTool
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder addTool(FileSearchTool fileSearchTool)
Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.
-
addTool
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder addTool(FunctionTool functionTool)
Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.
-
topP
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.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 BetaThreadRunCreateParams.BetaThreadRunCreateBody.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 BetaThreadRunCreateParams.BetaThreadRunCreateBody.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 BetaThreadRunCreateParams.BetaThreadRunCreateBody.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.
-
truncationStrategy
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder truncationStrategy(BetaThreadRunCreateParams.TruncationStrategy truncationStrategy)
Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run.
-
truncationStrategy
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder truncationStrategy(Optional<BetaThreadRunCreateParams.TruncationStrategy> truncationStrategy)
Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run.
-
truncationStrategy
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder truncationStrategy(JsonField<BetaThreadRunCreateParams.TruncationStrategy> truncationStrategy)
Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run.
-
additionalProperties
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder additionalProperties(Map<String, JsonValue> additionalProperties)
-
putAdditionalProperty
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder putAdditionalProperty(String key, JsonValue value)
-
putAllAdditionalProperties
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder putAllAdditionalProperties(Map<String, JsonValue> additionalProperties)
-
removeAdditionalProperty
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder removeAdditionalProperty(String key)
-
removeAllAdditionalProperties
final BetaThreadRunCreateParams.BetaThreadRunCreateBody.Builder removeAllAdditionalProperties(Set<String> keys)
-
build
final BetaThreadRunCreateParams.BetaThreadRunCreateBody build()
-
-
-
-