Uralstech.UGemini.Models.GeminiModel Class Reference

Information about a Generative Language Model. More...

Inheritance diagram for Uralstech.UGemini.Models.GeminiModel:

Public Attributes
string	Version
	The version number of the model.
string	DisplayName
	The human-readable name of the model. E.g. "Chat Bison".
string	Description
	A short description of the model.
int	InputTokenLimit
	Maximum number of input tokens allowed for this model.
int	OutputTokenLimit
	Maximum number of output tokens available for this model.
string[]	SupportedGenerationMethods
	The model's supported generation methods.
float	Temperature
	Controls the randomness of the output.
float	TopP
	For Nucleus sampling.
int	TopK
	For Top-k sampling.
Public Attributes inherited from Uralstech.UGemini.Models.GeminiModelId
string	Name
	The resource name of the Model.
string	BaseModelId
	The ID of the base model, pass this to the generation request.

Static Public Attributes
static readonly GeminiModelId	Gemini1_0ProVision = "gemini-pro-vision"
	Note: Gemini 1.0 Pro Vision is deprecated. Use 1.5 Flash or 1.5 Pro instead. Gemini 1.0 Pro Vision is a performance-optimized multimodal model that can perform visual-related tasks. For example, 1.0 Pro Vision can generate image descriptions, identify objects present in images, provide information about places or objects present in images, and more.
static readonly GeminiModelId	Gemini1_0Pro = "gemini-1.0-pro"
	Gemini 1.0 Pro is an NLP model that handles tasks like multi-turn text and code chat, and code generation.
static readonly GeminiModelId	Gemini1_5Pro = "gemini-1.5-pro"
	Gemini 1.5 Pro is a mid-size multimodal model that is optimized for a wide-range of reasoning tasks. 1.5 Pro can process large amounts of data at once, including 2 hours of video, 19 hours of audio, codebases with 60,000 lines of code, or 2,000 pages of text.
static readonly GeminiModelId	Gemini1_5Flash = "gemini-1.5-flash"
	Gemini 1.5 Flash is a fast and versatile multimodal model for scaling across diverse tasks.
static readonly GeminiModelId	TextEmbedding004 = "text-embedding-004"
	text-embedding-004 achieves a stronger retrieval performance and outperforms existing models with comparable dimensions, on the standard MTEB embedding benchmarks.
static readonly GeminiModelId	Aqa = "aqa"
	You can use the AQA model to perform Attributed Question-Answering (AQA)–related tasks over a document, corpus, or a set of passages. The AQA model returns answers to questions that are grounded in provided sources, along with estimating answerable probability.
Static Public Attributes inherited from Uralstech.UGemini.Models.GeminiModelId
const string	DefaultModelResourceLocation = "models/"
	The default resource location for all models.

Additional Inherited Members
Public Member Functions inherited from Uralstech.UGemini.Models.GeminiModelId
	GeminiModelId (string nameOrBaseModelId)
	Creates a new GeminiModelId.
	GeminiModelId (string name, string baseModelId)
	Creates a new GeminiModelId.
Static Public Member Functions inherited from Uralstech.UGemini.Models.GeminiModelId
static implicit	operator string (GeminiModelId model)
	Gets the base model ID of the GeminiModelId.
static implicit	operator GeminiModelId (string nameOrBaseModelId)
	Creates a new GeminiModelId with the full name of the model resource (see Name) or the unique ID of the base model.

Detailed Description

Information about a Generative Language Model.

Member Data Documentation

Aqa

readonly GeminiModelId Uralstech.UGemini.Models.GeminiModel.Aqa = "aqa"

static

You can use the AQA model to perform Attributed Question-Answering (AQA)–related tasks over a document, corpus, or a set of passages. The AQA model returns answers to questions that are grounded in provided sources, along with estimating answerable probability.

Supports text input.

DisplayName

string Uralstech.UGemini.Models.GeminiModel.DisplayName

The human-readable name of the model. E.g. "Chat Bison".

The name can be up to 128 characters long and can consist of any UTF-8 characters.

Gemini1_0Pro

readonly GeminiModelId Uralstech.UGemini.Models.GeminiModel.Gemini1_0Pro = "gemini-1.0-pro"

static

Gemini 1.0 Pro is an NLP model that handles tasks like multi-turn text and code chat, and code generation.

Supports text input.

Gemini1_0ProVision

readonly GeminiModelId Uralstech.UGemini.Models.GeminiModel.Gemini1_0ProVision = "gemini-pro-vision"

static

Note: Gemini 1.0 Pro Vision is deprecated. Use 1.5 Flash or 1.5 Pro instead.

Gemini 1.0 Pro Vision is a performance-optimized multimodal model that can perform visual-related tasks.
For example, 1.0 Pro Vision can generate image descriptions, identify objects present in images, provide
information about places or objects present in images, and more.

Supports image, video and text input.

Gemini1_5Flash

readonly GeminiModelId Uralstech.UGemini.Models.GeminiModel.Gemini1_5Flash = "gemini-1.5-flash"

static

Gemini 1.5 Flash is a fast and versatile multimodal model for scaling across diverse tasks.

Supports audio, image, video and text input.

Gemini1_5Pro

readonly GeminiModelId Uralstech.UGemini.Models.GeminiModel.Gemini1_5Pro = "gemini-1.5-pro"

static

Gemini 1.5 Pro is a mid-size multimodal model that is optimized for a wide-range of reasoning tasks.
1.5 Pro can process large amounts of data at once, including 2 hours of video, 19 hours of audio,
codebases with 60,000 lines of code, or 2,000 pages of text.

Supports audio, image, video and text input.

SupportedGenerationMethods

string [] Uralstech.UGemini.Models.GeminiModel.SupportedGenerationMethods

The model's supported generation methods.

The method names are defined as Pascal case strings, such as generateMessage which correspond to API methods.

Temperature

float Uralstech.UGemini.Models.GeminiModel.Temperature

Controls the randomness of the output.

Values can range over [0.0,2.0], inclusive. A higher value will produce responses that are more varied, while a value closer to
0.0 will typically result in less surprising responses from the model. This value specifies default to be used by the backend
while making the call to the model.

TextEmbedding004

readonly GeminiModelId Uralstech.UGemini.Models.GeminiModel.TextEmbedding004 = "text-embedding-004"

static

text-embedding-004 achieves a stronger retrieval performance and outperforms existing models with comparable dimensions, on the standard MTEB embedding benchmarks.

Supports text input.

TopK

int Uralstech.UGemini.Models.GeminiModel.TopK

For Top-k sampling.

Top-k sampling considers the set of topK most probable tokens. This value specifies default to be used by the backend while making the call
to the model. If unset, indicates the model doesn't use top-k sampling, and topK isn't allowed as a generation parameter.

TopP

float Uralstech.UGemini.Models.GeminiModel.TopP

For Nucleus sampling.

Nucleus sampling considers the smallest set of tokens whose probability sum is at least topP. This value specifies default to be used
by the backend while making the call to the model.

Version

string Uralstech.UGemini.Models.GeminiModel.Version

The version number of the model.

This represents the major version

---

The documentation for this class was generated from the following file:

• UGemini/Packages/com.uralstech.ugemini/Runtime/Scripts/Data/Models/GeminiModel.cs