- Home
- Skills
- Workflow Automation
- Vertex AI Gemini Integrator
Works with the AI Agents you already use
Vertex AI Gemini Integrator
Deploy production-ready Gemini and Vertex AI integrations with strict JSON enforcement and secure ADC authentication.
$12
Vertex AI Gemini Integrator
Example session with this skill installed
I need a Python script for Vertex AI that takes a transcript and returns a JSON list of action items. Use ADC for auth and include retry logic.
- Read your context and instructions
- Compiled the vertex ai gemini
I have generated a production-ready Python script using the `vertexai` SDK. This implementation uses Application Default Credentials for secure authentication and incorporates the `tenacity` library to handle potential API rate limits with exponential backoff. ## Vertex AI Structured Output Implementation ```python import json import vertexai from vertexai.generative_models import GenerativeModel, GenerationConfig from tenacity import retry, stop_after_attempt, wait_exponential, retry_if_exception_type # Initialize Vertex AI with your project and location vertexai.init(project="your-project-id", location="us-central 1") @retry( stop=stop_after_attempt(5), wait=wait_exponential(multiplier=1, min=4, max=10), retry=retry_if_exception_type(Exception) ) def extract_action_items(transcript: str): """ Extracts action items from a transcript and enforces JSON output. Uses ADC for authentication - ensure GOOGLE_APPLICATION_CREDENTIALS is set. """ model = GenerativeModel("gemini-1.5-flash") prompt = f"Extract all action items from the following transcript: {transcript}" # Strict JSON enforcement via GenerationConfig response = model.generate_content( prompt, generation_config=GenerationConfig( response_mime_type="application/json" ) ) try: return json.loads(response.text) except json.JSONDecodeError: return {"error": "Failed to parse model output as JSON"} # Example call transcript_data = "Meeting notes: Sarah will fix the login bug by Friday. Mike needs to update the docs." actions = extract_action_items(transcript_data) print(json.dumps(actions, indent=2)) ``` **Next steps** 1. Ensure the Vertex AI API is enabled in your Google Cloud Console. 2. Run `gcloud auth application-default login` to set up your local environment. 3. Install dependencies: `pip install google-cloud-aiplatform tenacity`.
Connects securely to your tools. The creator never sees your data.
About this skill
## The problem Integrating LLMs into production apps often leads to brittle code, hardcoded secrets, and inconsistent JSON responses that break downstream logic. Managing the differences between Google Cloud Vertex AI and the standalone Gemini API creates unnecessary friction for developers. ## What it does - Generates production-ready Python and Node.js boilerplate for Vertex AI and Gemini API. - Enforces strict JSON output using `response_mime_type` to prevent parsing errors. - Implements secure credential management using Application Default Credentials (ADC). - Provides retry logic patterns using `tenacity` or `p-retry` to handle 429 rate limits. - Scaffolds multi-turn chat architectures with system prompt enforcement. ## Frameworks & tools Node.js, Python, Google Cloud Vertex AI, Gemini API, p-retry, and tenacity. ## Why this beats prompting it yourself Generic prompts often forget to include the specific configuration flags required for reliable JSON mode or fail to mention Google's distinct authentication methods. This skill ensures your integration follows Google's best practices for security and reliability from the first line of code. ## Use cases - Building data extraction pipelines that require validated JSON objects. - Migrating existing OpenAI-based backends to the Gemini ecosystem. - Scaling LLM apps on Google Cloud using managed IAM roles and ADC. - Implementing resilient agents that handle API throttling without crashing. ## Known limitations Requires an active Google Cloud project or Gemini API key. Does not support deprecated PaLM models.
Requires active Google Cloud Project or Gemini API key. Focused on Python and Node.js only; does not support Go, Java, or C++ client libraries.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 4 days ago
Requires
Permissions
Integrates Gemini and Vertex AI clients with exponential backoff for 429 errors and structured JSON enforcement.