Package io.github.stefanbratanov.jvm.openai

Class CreateRunRequest.Builder

java.lang.Object
io.github.stefanbratanov.jvm.openai.CreateRunRequest.Builder
Enclosing class:
CreateRunRequest
public static class CreateRunRequest.Builder extends Object

  • Constructor Details

    • Builder

      public Builder()

  • Method Details

    • assistantId

      public CreateRunRequest.Builder assistantId(String assistantId)
      Parameters:
      assistantId - The ID of the assistant to use to execute this run.

    • model

      public CreateRunRequest.Builder model(String model)
      Parameters:
      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

      public CreateRunRequest.Builder model(OpenAIModel model)
      Parameters:
      model - OpenAIModel 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.

    • instructions

      public CreateRunRequest.Builder instructions(String instructions)
      Parameters:
      instructions - Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis.

    • additionalInstructions

      public CreateRunRequest.Builder additionalInstructions(String additionalInstructions)
      Parameters:
      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

      public CreateRunRequest.Builder additionalMessages(List<CreateMessageRequest> additionalMessages)
      Parameters:
      additionalMessages - Adds additional messages to the thread before creating the run.

    • tools

      public CreateRunRequest.Builder tools(List<Tool> tools)
      Parameters:
      tools - Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.

    • metadata

      public CreateRunRequest.Builder metadata(Map<String,String> metadata)
      Parameters:
      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 maxium of 512 characters long.

    • temperature

      public CreateRunRequest.Builder temperature(double temperature)
      Parameters:
      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.

    • topP

      public CreateRunRequest.Builder topP(double topP)
      Parameters:
      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.

    • stream

      public CreateRunRequest.Builder stream(boolean stream)
      Parameters:
      stream - If true, returns a stream of events that happen during the Run as server-sent events

    • maxPromptTokens

      public CreateRunRequest.Builder maxPromptTokens(int maxPromptTokens)
      Parameters:
      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 `complete`. See `incomplete_details` for more info.

    • maxCompletionTokens

      public CreateRunRequest.Builder maxCompletionTokens(int maxCompletionTokens)
      Parameters:
      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 `complete`. See `incomplete_details` for more info.

    • truncationStrategy

      public CreateRunRequest.Builder truncationStrategy(TruncationStrategy truncationStrategy)
      Parameters:
      truncationStrategy - The truncation strategy to use for the thread.

    • toolChoice

      public CreateRunRequest.Builder toolChoice(AssistantsToolChoice toolChoice)
      Parameters:
      toolChoice - Controls which (if any) tool is called by the model.

    • parallelToolCalls

      public CreateRunRequest.Builder parallelToolCalls(boolean parallelToolCalls)
      Parameters:
      parallelToolCalls - Whether to enable parallel function calling during tool use.

    • responseFormat

      public CreateRunRequest.Builder responseFormat(AssistantsResponseFormat responseFormat)
      Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message.
      Parameters:
      responseFormat - An object specifying the format that the model must output.

    • build

      public CreateRunRequest build()