Artificial Intelligence

Gemini

Learn how to use Gemini with Composio

Overview

SLUG: GEMINI

Description

Comprehensive Gemini integration supporting Veo 3 video generation, Gemini Flash text generation, chat completions, and multimodal AI capabilities via the Google Gemini API.

Authentication Details

generic_api_key
stringRequired

Connecting to Gemini

Create an auth config

Use the dashboard to create an auth config for the Gemini toolkit. This allows you to connect multiple Gemini accounts to Composio for agents to use.

1

Select App

Navigate to Gemini.

2

Configure Auth Config Settings

Select among the supported auth schemes of and configure them here.

3

Create and Get auth config ID

Click “Create Gemini Auth Config”. After creation, copy the displayed ID starting with ac_. This is your auth config ID. This is not a sensitive ID — you can save it in environment variables or a database. This ID will be used to create connections to the toolkit for a given user.

Connect Your Account

Using API Key

1from composio import Composio
2
3# Replace these with your actual values
4gemini_auth_config_id = "ac_YOUR_GEMINI_CONFIG_ID" # Auth config ID created above
5user_id = "0000-0000-0000"  # UUID from database/app
6
7composio = Composio()
8
9def authenticate_toolkit(user_id: str, auth_config_id: str):
10    # Replace this with a method to retrieve an API key from the user.
11    # Or supply your own.
12    user_api_key = input("[!] Enter API key")
13
14    connection_request = composio.connected_accounts.initiate(
15        user_id=user_id,
16        auth_config_id=auth_config_id,
17        config={"auth_scheme": "API_KEY", "val": {"generic_api_key": user_api_key}}
18    )
19
20    # API Key authentication is immediate - no redirect needed
21    print(f"Successfully connected Gemini for user {user_id}")
22    print(f"Connection status: {connection_request.status}")
23    
24    return connection_request.id
25
26
27connection_id = authenticate_toolkit(user_id, gemini_auth_config_id)
28
29# You can verify the connection using:
30connected_account = composio.connected_accounts.get(connection_id)
31print(f"Connected account: {connected_account}")

Tools

Executing tools

To prototype you can execute some tools to see the responses and working on the Gemini toolkit’s playground

Python
1from composio import Composio
2from openai import OpenAI
3import json
4
5openai = OpenAI()
6composio = Composio()
7
8# User ID must be a valid UUID format
9user_id = "0000-0000-0000"  # Replace with actual user UUID from your database
10
11tools = composio.tools.get(user_id=user_id, toolkits=["GEMINI"])
12
13print("[!] Tools:")
14print(json.dumps(tools))
15
16def invoke_llm(task = "What can you do?"):
17    completion = openai.chat.completions.create(
18        model="gpt-4o",
19        messages=[
20            {
21                "role": "user",
22                "content": task,  # Your task here!
23            },
24        ],
25        tools=tools,
26    )
27
28    # Handle Result from tool call
29    result = composio.provider.handle_tool_calls(user_id=user_id, response=completion)
30    print(f"[!] Completion: {completion}")
31    print(f"[!] Tool call result: {result}")
32
33invoke_llm()

Tool List

Tool Name: Count Tokens (Gemini)

Description

Counts the number of tokens in text using gemini tokenization. useful for estimating costs, checking input limits, and optimizing prompts before making api calls.

Action Parameters

model
stringDefaults to gemini-1.5-flash
text
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Download Video (Veo)

Description

Downloads a generated veo video to local storage. takes the video uri from a completed operation and saves it to the specified file path.

Action Parameters

download_path
stringRequired
video_uri
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Embed Content (Gemini)

Description

Generates text embeddings using gemini embedding models. converts text into numerical vectors for semantic search, similarity comparison, clustering, and classification tasks.

Action Parameters

model
stringDefaults to text-embedding-004
task_type
string
text
stringRequired
title
string

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Generate Content (Gemini)

Description

Generates text content from prompts using gemini models. supports various models like gemini flash and pro with configurable temperature, token limits, and safety settings for diverse text generation tasks.

Action Parameters

max_output_tokens
integer
model
stringDefaults to gemini-1.5-flash
prompt
stringRequired
safety_settings
array
stop_sequences
array
system_instruction
string
temperature
number
top_k
integer
top_p
number

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Generate Image (Gemini 2.5 Flash)

Description

Generates images from text prompts using gemini 2.5 flash image preview model. supports creative image generation with customizable parameters like aspect ratio, safety settings, and optional file saving.

Action Parameters

max_output_tokens
integer
model
stringDefaults to gemini-2.5-flash-image-preview
prompt
stringRequired
safety_settings
array
save_path
string
system_instruction
string
temperature
number
top_k
integer
top_p
number

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Generate Videos (Veo)

Description

Generates videos from text prompts using google's veo models. creates high-quality video content with customizable aspect ratios, duration, and style controls. returns operation id for tracking progress.

Action Parameters

aspect_ratio
string
extras
object
model
stringDefaults to veo-3.0-generate-preview
negative_prompt
string
person_generation
string
prompt
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Get Videos Operation (Veo)

Description

Checks the status of a veo video generation operation. use the operation name from generatevideos to track progress and get the download url when complete.

Action Parameters

operation_name
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: List Models (Gemini API)

Description

Lists available gemini and veo models with their capabilities and limits. useful for discovering supported models and their features before making generation requests.

Action Parameters

filter_prefix
string

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Wait For Video (Veo)

Description

Polls a veo video generation operation until completion or timeout. automatically checks status at intervals and returns the final video url when ready.

Action Parameters

operation_name
stringRequired
poll_interval_s
integerDefaults to 10
timeout_s
integer

Action Response

data
objectRequired
error
string
successful
booleanRequired