Google Gemini (Independent Publisher) (Preview)

Reference

Custom connector for Google Gemini, providing advanced AI multi modal content generation functionalities.Gemini is a family of multimodal large language models developed by Google DeepMind, serving as the successor to LaMDA and PaLM 2. Comprising Gemini Ultra, Gemini Pro, and Gemini Nano, it was announced on December 6, 2023

This connector is available in the following products and regions:

Service	Class	Regions
Logic Apps	Standard	All Logic Apps regions except the following: - Azure Government regions - Azure China regions - US Department of Defense (DoD)
Power Automate	Premium	All Power Automate regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD)
Power Apps	Premium	All Power Apps regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD)

Contact
Name	Priyaranjan KS , Vidya Sagar Alti [Tata Consultancy Services]
URL	https://www.tcs.com
Email	[email protected]

Connector Metadata
Publisher	Priyaranjan KS , Vidya Sagar Alti [Tata Consultancy Services]
Website	https://ai.google.dev/
Privacy policy	https://policies.google.com/privacy
Categories	AI

Creating a connection

The connector supports the following authentication types:


Default	Parameters for creating connection.	All regions	Not shareable

Default

Applicable: All regions

Parameters for creating connection.

This is not shareable connection. If the power app is shared with another user, another user will be prompted to create new connection explicitly.

Name	Type	Description	Required
API Key	securestring	The API Key for this api	True

Throttling Limits

Name	Calls	Renewal Period
API calls per connection	100	60 seconds

Actions

Count tokens	Counts the number of tokens in a given text using the Generative Language Model.
Generate batch embeddings	Generates embedding vectors for a batch of text contents.
Generate embedding	This endpoint is designed to generate an embedding vector for the provided text content, which can be used for various natural language processing tasks such as text similarity, classification, and clustering.
Generate multi modal content	Generates a response from the model given an input message and an image or video.
Generate stream content	By default, the model returns a response after completing the entire generation process. You can achieve faster interactions by not waiting for the entire result, and instead use streaming to handle partial results.
Generate text content	Generates a text response from the model given an input message.
Get all models	Retrieves a list of all available models with their details.
Get model details	Retrieves details of a specific model based on the provided model name.

Count tokens

Operation ID:: countTokens

Counts the number of tokens in a given text using the Generative Language Model.

Parameters

Name	Key	Required	Type	Description
API Version	apiVersion	True	string	API version to use for the vision endpoint.Eg- 'v1beta'
Model Name	modelName	True	string	Model name, Eg- 'gemini-pro'.
Text	text		string	Required. Text content for which the token count is to be determined.

Returns

Name	Path	Type	Description
totalTokens	totalTokens	integer	The total number of tokens in the provided text.

Generate batch embeddings

Operation ID:: batchEmbedContents

Generates embedding vectors for a batch of text contents.

Parameters

Name	Key	Required	Type	Description
API Version	apiVersion	True	string	API version, Eg- 'v1beta'.
Model Name	modelName	True	string	Model name, Eg- 'embedding-001'.
Model	model	True	string	Identifier of the model used for embedding generation.This should match the format 'models/{modelName}'.
Text	text		string	Required.The text content for which the embedding is generated.

Returns

Name	Path	Type	Description
embeddings	embeddings	array of object
values	embeddings.values	array of number	An array of numerical values representing the generated embedding.

Generate embedding

Operation ID:: generateEmbedding

This endpoint is designed to generate an embedding vector for the provided text content, which can be used for various natural language processing tasks such as text similarity, classification, and clustering.

Parameters

Name	Key	Required	Type	Description
API Version	apiVersion	True	string	The version of the API to be used. This parameter defines the versioning scheme of the API endpoint. Eg- 'v1beta'
Model Name	modelName	True	string	The name of the model to be used for generating the embedding. The model name should correspond to one of the models available in the API. Eg- 'embedding-001'
Model Resource Name	model	True	string	Identifier of the model used for embedding generation. This should match the format 'models/{modelName}'.
Text	text		string	Required.The text content for which the embedding is generated.
Task Type	taskType		string	Optional.The type of task for which the embedding is intended. This parameter helps the model to understand the context in which the embedding is generated.
Title	title		string	Optional.An optional title for the content. This is applicable for certain task types like RETRIEVAL_DOCUMENT.

Returns

Name	Path	Type	Description
values	embedding.values	array of number	An array of numerical values representing the generated embedding.

Operation ID:: GenerateMultiModalContent

Generates a response from the model given an input message and an image or video.

Parameters

Name	Key	Required	Type	Description
API Version	apiVersion	True	string	API version to use for the vision endpoint.Eg- v1beta
Base Model Name	modelName	True	string	Name of the base model.Eg- Enter gemini-pro and corresponding vision model (gemini-pro-vision) will be used
Role	role		string	Optional. The producer of the content. Must be either 'user' or 'model'
Parts	Parts		object
Category	category		string	Optional.The category of content to be filtered.
Threshold	threshold		string	Optional.The threshold for filtering content in the specified category.
Max Output Tokens	maxOutputTokens		integer	Optional.The maximum number of tokens to include in a vision candidate.
Temperature	temperature		number	Optional.Controls the randomness of the vision output.
Top P	topP		number	Optional.The maximum cumulative probability of tokens to consider when sampling.
Top K	topK		integer	Optional.The maximum number of tokens to consider when sampling.
Stop Sequences	stopSequences		array of string	Optional.The set of character sequences that will stop text output generation.

Returns

Name	Path	Type
candidates	candidates	array of object
parts	candidates.content.parts	array of object
items	candidates.content.parts	object
finishReason	candidates.finishReason	string
index	candidates.index	integer
safetyRatings	candidates.safetyRatings	array of object
category	candidates.safetyRatings.category	string
probability	candidates.safetyRatings.probability	string
safetyRatings	promptFeedback.safetyRatings	array of object
category	promptFeedback.safetyRatings.category	string
probability	promptFeedback.safetyRatings.probability	string

Generate stream content

Operation ID:: generateStreamContent

By default, the model returns a response after completing the entire generation process. You can achieve faster interactions by not waiting for the entire result, and instead use streaming to handle partial results.

Parameters

Name	Key	Required	Type	Description
API Version	apiVersion	True	string	API version, Eg- 'v1beta'.
Model Name	modelName	True	string	Model name, Eg- 'gemini-pro'.
Role	role		string	The producer of the content. Must be either 'user' or 'model'
Text	text		string	Required. Text content to be processed.
Category	category		string	Optional. Category of content to be filtered.
Threshold	threshold		string	Optional. Threshold level for content filtering.
Temperature	temperature		number	Optional. Controls randomness in the response. Higher values lead to more varied responses.
Max Output Tokens	maxOutputTokens		integer	Optional. Maximum number of tokens in the generated content.
Top P	topP		number	Optional. Controls diversity of the response. Higher values lead to more diverse responses.
Top K	topK		integer	Optional. Limits the number of high-probability tokens considered at each step.
Candidate Count	candidateCount		integer	Optional. Number of candidate responses to generate.
Stop Sequences	stopSequences		array of string	Optional.The set of character sequences that will stop text output generation.

Returns

Name	Path	Type
		array of object
candidates	candidates	array of object
parts	candidates.content.parts	array of object
text	candidates.content.parts.text	string
role	candidates.content.role	string
finishReason	candidates.finishReason	string
index	candidates.index	integer
safetyRatings	candidates.safetyRatings	array of object
category	candidates.safetyRatings.category	string
probability	candidates.safetyRatings.probability	string
safetyRatings	promptFeedback.safetyRatings	array of object
category	promptFeedback.safetyRatings.category	string
probability	promptFeedback.safetyRatings.probability	string

Generate text content

Operation ID:: GenerateTextContent

Generates a text response from the model given an input message.

Parameters

Name	Key	Required	Type	Description
API Version	apiVersion	True	string	API version to use for the endpoint. Eg- v1beta
Model Name	modelName	True	string	Name of the model to be used for text generation. Eg - gemini-pro
Role	role		string	Optional. The producer of the content. Must be either 'user' or 'model'
Text	text	True	string	Required.Text for generating the response.
Category	category		string	Optional.The category of content to be filtered.
Threshold	threshold		string	Optional.The threshold for filtering content in the specified category.
Max Output Tokens	maxOutputTokens		integer	Optional.The maximum number of tokens to include in a text candidate.
Temperature	temperature		number	Optional.Controls the randomness of the text output.
Top P	topP		number	Optional.The maximum cumulative probability of tokens to consider when sampling.
Top K	topK		integer	Optional.The maximum number of tokens to consider when sampling.
Candidate Count	candidateCount		integer	Optional. Number of candidate responses to generate.
Stop Sequences	stopSequences		array of string	Optional.The set of character sequences that will stop text output generation.

Returns

Name	Path	Type
candidates	candidates	array of object
parts	candidates.content.parts	array of object
text	candidates.content.parts.text	string
finishReason	candidates.finishReason	string
index	candidates.index	integer
safetyRatings	candidates.safetyRatings	array of object
category	candidates.safetyRatings.category	string
probability	candidates.safetyRatings.probability	string
safetyRatings	promptFeedback.safetyRatings	array of object
category	promptFeedback.safetyRatings.category	string
probability	promptFeedback.safetyRatings.probability	string

Get all models

Operation ID:: getAllModels

Retrieves a list of all available models with their details.

Parameters

Name	Key	Required	Type	Description
API Version	apiVersion	True	string	API version, Eg- 'v1beta'.

Returns

Name	Path	Type	Description
models	models	array of object
name	models.name	string	Unique identifier of the model.
version	models.version	string	Version of the model.
displayName	models.displayName	string	Display name of the model.
description	models.description	string	Description of the model.
inputTokenLimit	models.inputTokenLimit	integer	The maximum number of input tokens the model can handle.
outputTokenLimit	models.outputTokenLimit	integer	The maximum number of output tokens the model can generate.
supportedGenerationMethods	models.supportedGenerationMethods	array of string	List of supported generation methods by the model.
temperature	models.temperature	number	Default temperature setting for the model. Not present for all models.
topP	models.topP	number	Default topP setting for the model. Not present for all models.
topK	models.topK	number	Default topK setting for the model. Not present for all models.

Get model details

Operation ID:: getModelDetails

Retrieves details of a specific model based on the provided model name.

Parameters

Name	Key	Required	Type	Description
API Version	apiVersion	True	string	API version, Eg- 'v1beta'.
Model Name	modelName	True	string	Model name, Eg- 'gemini-pro'.

Returns

Name	Path	Type	Description
name	name	string	Unique identifier of the model.
version	version	string	Version of the model.
displayName	displayName	string	Display name of the model.
description	description	string	Description of the model.
inputTokenLimit	inputTokenLimit	integer	The maximum number of input tokens the model can handle.
outputTokenLimit	outputTokenLimit	integer	The maximum number of output tokens the model can generate.
supportedGenerationMethods	supportedGenerationMethods	array of string	List of supported generation methods by the model.
temperature	temperature	number	Default temperature setting for the model.
topP	topP	number	Default topP setting for the model.
topK	topK	number	Default topK setting for the model.

Share via

Google Gemini (Independent Publisher) (Preview)

Creating a connection

Default

Throttling Limits

Actions

Count tokens

Parameters

Returns

Generate batch embeddings

Parameters

Returns

Generate embedding

Parameters

Returns

Parameters

Returns

Generate stream content

Parameters

Returns

Generate text content

Parameters

Returns

Get all models

Parameters

Returns

Get model details

Parameters

Returns

Additional resources

Share via

Google Gemini (Independent Publisher) (Preview)

Creating a connection

Default

Throttling Limits

Actions

Count tokens

Parameters

Returns

Generate batch embeddings

Parameters

Returns

Generate embedding

Parameters

Returns

Generate multi modal content

Parameters

Returns

Generate stream content

Parameters

Returns

Generate text content

Parameters

Returns

Get all models

Parameters

Returns

Get model details

Parameters

Returns

Additional resources