Constructor Detail

Method Detail

• assistantId

   final ThreadCreateAndRunParams.Builder assistantId(String assistantId)

  The ID of the assistant to use to execute this run.

• assistantId

   final ThreadCreateAndRunParams.Builder assistantId(JsonField<String> assistantId)

  The ID of the assistant to use to execute this run.

• instructions

   final ThreadCreateAndRunParams.Builder instructions(String instructions)

  Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.

• instructions

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

  Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.

• instructions

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

  Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.

• maxCompletionTokens

   final ThreadCreateAndRunParams.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. See incomplete_details for more info.

• maxCompletionTokens

   final ThreadCreateAndRunParams.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. See incomplete_details for more info.

• maxCompletionTokens

   final ThreadCreateAndRunParams.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. See incomplete_details for more info.

• maxCompletionTokens

   final ThreadCreateAndRunParams.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. See incomplete_details for more info.

• maxPromptTokens

   final ThreadCreateAndRunParams.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. See incomplete_details for more info.

• maxPromptTokens

   final ThreadCreateAndRunParams.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. See incomplete_details for more info.

• maxPromptTokens

   final ThreadCreateAndRunParams.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. See incomplete_details for more info.

• maxPromptTokens

   final ThreadCreateAndRunParams.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. See incomplete_details for more info.

• metadata

   final ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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.

• model

   final ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.Builder parallelToolCalls(Boolean parallelToolCalls)

  Whether to enable parallel function calling during tool use.

• parallelToolCalls

   final ThreadCreateAndRunParams.Builder parallelToolCalls(JsonField<Boolean> parallelToolCalls)

  Whether to enable parallel function calling during tool use.

• responseFormat

   final ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.Builder responseFormat(ResponseFormatText responseFormatText)

  Default response format. Used to generate text responses.

• responseFormat

   final ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.Builder responseFormat(ResponseFormatJsonSchema responseFormatJsonSchema)

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

• responseFormatJsonValue

   final ThreadCreateAndRunParams.Builder responseFormatJsonValue()

  auto is the default value

• temperature

   final ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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.

• thread

   final ThreadCreateAndRunParams.Builder thread(ThreadCreateAndRunParams.Thread thread)

  Options to create a new thread. If no thread is provided when running a request, an empty thread will be created.

• thread

   final ThreadCreateAndRunParams.Builder thread(JsonField<ThreadCreateAndRunParams.Thread> thread)

  Options to create a new thread. If no thread is provided when running a request, an empty thread will be created.

• toolChoice

   final ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.Builder toolChoice(AssistantToolChoiceOption.Auto auto)

  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 ThreadCreateAndRunParams.Builder toolChoice(AssistantToolChoice assistantToolChoice)

  Specifies a tool the model should use. Use to force the model to call a specific tool.

• toolResources

   final ThreadCreateAndRunParams.Builder toolResources(ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.Builder toolResources(Optional<ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.Builder toolResources(JsonField<ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.Builder tools(List<ThreadCreateAndRunParams.Tool> 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 ThreadCreateAndRunParams.Builder tools(Optional<List<ThreadCreateAndRunParams.Tool>> 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 ThreadCreateAndRunParams.Builder tools(JsonField<List<ThreadCreateAndRunParams.Tool>> 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 ThreadCreateAndRunParams.Builder addTool(ThreadCreateAndRunParams.Tool 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 ThreadCreateAndRunParams.Builder addTool(CodeInterpreterTool codeInterpreter)

  Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.

• addTool

   final ThreadCreateAndRunParams.Builder addTool(FileSearchTool fileSearch)

  Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.

• addTool

   final ThreadCreateAndRunParams.Builder addTool(FunctionTool function)

  Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.

• topP

   final ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.Builder truncationStrategy(ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.Builder truncationStrategy(Optional<ThreadCreateAndRunParams.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 ThreadCreateAndRunParams.Builder truncationStrategy(JsonField<ThreadCreateAndRunParams.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.

• additionalBodyProperties

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

• putAdditionalBodyProperty

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

• putAllAdditionalBodyProperties

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

• removeAdditionalBodyProperty

   final ThreadCreateAndRunParams.Builder removeAdditionalBodyProperty(String key)

• removeAllAdditionalBodyProperties

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

• additionalHeaders

   final ThreadCreateAndRunParams.Builder additionalHeaders(Headers additionalHeaders)

• additionalHeaders

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

• putAdditionalHeader

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

• putAdditionalHeaders

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

• putAllAdditionalHeaders

   final ThreadCreateAndRunParams.Builder putAllAdditionalHeaders(Headers additionalHeaders)

• putAllAdditionalHeaders

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

• replaceAdditionalHeaders

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

• replaceAdditionalHeaders

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

• replaceAllAdditionalHeaders

   final ThreadCreateAndRunParams.Builder replaceAllAdditionalHeaders(Headers additionalHeaders)

• replaceAllAdditionalHeaders

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

• removeAdditionalHeaders

   final ThreadCreateAndRunParams.Builder removeAdditionalHeaders(String name)

• removeAllAdditionalHeaders

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

• additionalQueryParams

   final ThreadCreateAndRunParams.Builder additionalQueryParams(QueryParams additionalQueryParams)

• additionalQueryParams

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

• putAdditionalQueryParam

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

• putAdditionalQueryParams

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

• putAllAdditionalQueryParams

   final ThreadCreateAndRunParams.Builder putAllAdditionalQueryParams(QueryParams additionalQueryParams)

• putAllAdditionalQueryParams

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

• replaceAdditionalQueryParams

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

• replaceAdditionalQueryParams

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

• replaceAllAdditionalQueryParams

   final ThreadCreateAndRunParams.Builder replaceAllAdditionalQueryParams(QueryParams additionalQueryParams)

• replaceAllAdditionalQueryParams

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

• removeAdditionalQueryParams

   final ThreadCreateAndRunParams.Builder removeAdditionalQueryParams(String key)

• removeAllAdditionalQueryParams

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

• build

   final ThreadCreateAndRunParams build()