Google Gemini | AI Agent Tools

google.dev

•

API Key

Available Actions

These are the specific actions that AI agents can perform with this tool

Embed Content

2 inputs

Generates text embeddings for words, phrases, code, and sentences using the Gemini API.

Inputs

model

The embedding model to use for generating embeddings.

content

The text for which to generate embeddings.

Embed Text Content

2 inputs

Generates embeddings for textual content using specified models.

Inputs

model

The model name to use for embedding.

contents

The text content for which to generate embeddings.

Generate AI Content

2 inputs

This endpoint generates AI content using the Gemini API.

Inputs

model

The model to be used for content generation. For example, 'gemini-2.0-flash'.

contents

The content or prompt to be processed by the AI model.

Generate Content

2 inputs

Generates content using the Gemini 2.0 Flash model

Inputs

Model

The specific model version to use for generating content

Contents

The input text that describes the desired output or task

Generate Content

8 inputs

Generates content based on the provided input using the specified model

Inputs

model

The name of the Model to use for content generation in the format of models/{model}.

contents

Content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries like chat, this is a repeated field containing the conversation history and the latest request.

tools

A list of Tools the Model may use to generate the next response. It can include Function and codeExecution.

toolConfig

Tool configuration for any Tool specified in the request.

safetySettings

A list of unique SafetySetting instances for blocking unsafe content. Overrides default settings for specified SafetyCategory types.

systemInstruction

Developer set system instructions, text-only currently.

generationConfig

Configuration options for model generation and outputs, including candidate count, temperature, and others.

cachedContent

Name of the cached content to use as context for the prediction in the format of cachedContents/{cachedContent}.

Available Actions

These are the specific actions that AI agents can perform with this tool

Embed Content

2 inputs

Generates text embeddings for words, phrases, code, and sentences using the Gemini API.

Inputs

model

The embedding model to use for generating embeddings.

content

The text for which to generate embeddings.

Embed Text Content

2 inputs

Generates embeddings for textual content using specified models.

Inputs

model

The model name to use for embedding.

contents

The text content for which to generate embeddings.

Generate AI Content

2 inputs

This endpoint generates AI content using the Gemini API.

Inputs

model

The model to be used for content generation. For example, 'gemini-2.0-flash'.

contents

The content or prompt to be processed by the AI model.

Generate Content

2 inputs

Generates content using the Gemini 2.0 Flash model

Inputs

Model

The specific model version to use for generating content

Contents

The input text that describes the desired output or task

Generate Content

8 inputs

Generates content based on the provided input using the specified model

Inputs

model

The name of the Model to use for content generation in the format of models/{model}.

contents

tools

A list of Tools the Model may use to generate the next response. It can include Function and codeExecution.

toolConfig

Tool configuration for any Tool specified in the request.

safetySettings

A list of unique SafetySetting instances for blocking unsafe content. Overrides default settings for specified SafetyCategory types.

systemInstruction

Developer set system instructions, text-only currently.

generationConfig

Configuration options for model generation and outputs, including candidate count, temperature, and others.

cachedContent

Name of the cached content to use as context for the prediction in the format of cachedContents/{cachedContent}.