|
Unreal OpenAI API 1.0.0
|
#include <AssistantTypes.h>
Public Attributes | |
| FString | Id |
| FString | Object |
| int32 | Created_At {0} |
| FString | Name |
| FString | Model |
| FString | Instructions |
| TArray< FAssistantTool > | Tools |
| FAssistantToolResources | Tool_Resources |
| TMap< FString, FString > | Metadata |
| float | Temperature {1.0f} |
| float | Top_P {1.0f} |
| FString | Response_Format |
Represents an assistant that can call the model and use tools.
| int32 FAssistantObjectResponse::Created_At {0} |
The Unix timestamp (in seconds) for when the assistant was created.
| FString FAssistantObjectResponse::Id |
The identifier, which can be referenced in API endpoints.
| FString FAssistantObjectResponse::Instructions |
The system instructions that the assistant uses. The maximum length is 256,000 characters.
| TMap<FString, FString> FAssistantObjectResponse::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.
| FString FAssistantObjectResponse::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.
| FString FAssistantObjectResponse::Name |
The name of the assistant. The maximum length is 256 characters.
| FString FAssistantObjectResponse::Object |
The object type, which is always assistant.
| FString FAssistantObjectResponse::Response_Format |
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.
| float FAssistantObjectResponse::Temperature {1.0f} |
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.
| FAssistantToolResources FAssistantObjectResponse::Tool_Resources |
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.
| TArray<FAssistantTool> FAssistantObjectResponse::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, or function.
| float FAssistantObjectResponse::Top_P {1.0f} |
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.