Gemini

Learn how to use Gemini with Composio

Overview

SLUG: GEMINI

Description

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

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: 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 (Nano Banana). Supports creative image generation with customizable parameters like aspect ratio, safety settings, and optional local file saving. Generated images are automatically uploaded to S3 and gives you a downloadable link. NOTE NEVER EVER TRUE SYNC_TO_WORKBENCH IN RUBE_MULTI_EXECUTE_TOOL

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. Returns operation ID for tracking progress. After this, call GEMINI_WAIT_FOR_VIDEO to download the video using the operation ID.

Action Parameters

extras
object
model
stringDefaults to veo-3.0-generate-preview
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 and Download Video (Veo)

Description

Polls a Veo video generation operation until completion, then downloads and returns the video as a FileDownloadable with public URL.

Action Parameters

operation_name
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired