Class CreateAssistantRequest.Builder
java.lang.Object
io.github.stefanbratanov.jvm.openai.CreateAssistantRequest.Builder
- Enclosing class:
- CreateAssistantRequest
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionbuild()
description
(String description) instructions
(String instructions) model
(OpenAIModel model) responseFormat
(AssistantsResponseFormat responseFormat) temperature
(double temperature) topP
(double topP)
-
Constructor Details
-
Builder
public Builder()
-
-
Method Details
-
model
- Parameters:
model
- ID of the model to use.
-
model
- Parameters:
model
-OpenAIModel
to use
-
name
- Parameters:
name
- The name of the assistant. The maximum length is 256 characters.
-
description
- Parameters:
description
- The description of the assistant. The maximum length is 512 characters.
-
instructions
- Parameters:
instructions
- The system instructions that the assistant uses. The maximum length is 256,000 characters.
-
tool
- Parameters:
tool
- tool to append to the list of tools enabled on the assistant.
-
tools
- Parameters:
tools
- tools to append to the list of tools enabled on the assistant.
-
fileIds
- Parameters:
fileIds
- A list of file IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order.
-
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
- 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
- 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.
-
responseFormat
- Parameters:
responseFormat
- An object specifying the format that the model must output.
-
build
-