Generative AI on Vertex AI Cookbook

A collection of guides and examples for Generative AI on Vertex AI.

Explore more in the Generative AI Repository on GitHub.

Gemini Quickstarts

  • phone_android

    Creating Marketing Assets using Gemini 2.0 Flash

    Learn how to combine the multimodal capabilities of Gemini and Grounding with Google Search to create a marketing campaign brief and marketing assets.

    Gemini Grounding Search

    View on GitHub  
  • record_voice_over

    Get started with Chirp 2 for Speech-to-Text

    Learn about how to use Chirp 2, the latest generation of Google's multilingual Automatic Speech Recognition models.

    Chirp Speech

    View on GitHub  
  • add_photo_alternate

    Intro to Imagen 3 Image Generation

    Use Imagen 3 to create photorealistic images.

    Imagen Multimodal

    View on GitHub  
  • photo_size_select_small

    Imagen 3 Image Editing

    Use Imagen 3 to edit photorealistic images using inpainting, outpainting, and Product Image Editing.

    Imagen Multimodal

    View on GitHub  
  • graph_3

    Use AI's multitool, Embeddings, and Vertex AI Vector Search perform semantic matching.

    Embeddings Vector Search

    View on GitHub  
  • raven

    Intro to LangGraph with Gemini

    Learn how to combine LangGraph's workflow capabilities with Gemini's language understanding and generation skills to streamline and automate complex financial analysis tasks.

    Gemini LangChain LangGraph Orchestration

    View on GitHub  
  • podcasts

    Create custom podcast episodes

    Use Gemini, LangGraph, and Text-to-Speech to create custom podcast episodes.

    Gemini LangChain LangGraph Orchestration Speech

    View on GitHub  
  • menu_book

    Storytelling with Gemini and Text-to-Speech

    Use Gemini and Text-to-Speech to create and read a story with multiple characters.

    Gemini Speech

    View on GitHub  
  • code

    Analyze a codebase

    Use Gemini to generate code, summarize a codebase, debug, improve code, and assess code.

    Gemini Multimodal

    View on GitHub  
  • vaccines

    LLM Security for developers

    Learn about prompt injection attacks and how to mitigate them.

    Gemini Prompting Security

    View on GitHub  
  • troubleshoot

    Gen AI Evaluation Service

    Evaluate Gemini responses using metrics and custom datasets.

    Evaluation Gemini

    View on GitHub  
  • tune

    Supervised Fine-tuning with Gemini

    Learn how to fine-tune Gemini for specific tasks.

    Gemini Tuning

    View on GitHub  
  • dry_cleaning

    Intro to Vertex AI RAG Engine

    Build custom RAG workflows with Gemini and Vertex AI RAG Engine.

    Gemini RAG

    View on GitHub  
  • description

    Document Processing with Gemini

    Use Gemini to process documents for classification, extraction, and summarization.

    Gemini Multimodal

    View on GitHub  

All Tutorials

Filter by:
Gemini

Intro to Gemini 2.0 Flash

Get started with Gemini 2.0 in Vertex AI with the Gen AI Python SDK.

View on GitHub
Gemini
Prompting

Intro to Prompt Engineering

Learn the essentials and best practices of prompt engineering.

View on GitHub
Function Calling
Gemini

Function Calling with Gemini

Connect Gemini to external tools using function calling.

View on GitHub
Gemini
Grounding
RAG
Search

Grounding with Gemini

Connect Gemini to real-world data from Google Search or Vertex AI Search to improve response quality.

View on GitHub
Batch Prediction
Gemini

Gemini Batch prediction

Use Batch Prediction to run inference on a large number of examples.

View on GitHub
Gemini

Long Context Window

Use the Long Context Window to process large amounts of multimodal data.

View on GitHub
Gemini

Intro to Context Caching

Use context caching to store frequently used data.

View on GitHub
Gemini

Intro to Controlled Generation with the Gemini API

Learn to control Gemini API output formats for easier data processing.

View on GitHub
Gemini

Call Gemini by using the OpenAI Library

Learn how to call Gemini using Chat Completions.

View on GitHub
Gemini
Grounding
Search

Creating Marketing Assets using Gemini 2.0 Flash

Learn how to combine the multimodal capabilities of Gemini and Grounding with Google Search to create a marketing campaign brief and marketing assets.

View on GitHub
Chirp
Speech

Get started with Chirp 2 for Speech-to-Text

Learn about how to use Chirp 2, the latest generation of Google's multilingual Automatic Speech Recognition models.

View on GitHub
Imagen
Multimodal

Intro to Imagen 3 Image Generation

Use Imagen 3 to create photorealistic images.

View on GitHub
Imagen
Multimodal

Imagen 3 Image Editing

Use Imagen 3 to edit photorealistic images using inpainting, outpainting, and Product Image Editing.

View on GitHub
Embeddings
Vector Search

Get Started with Text Embeddings + Vertex AI Vector Search

Use AI's multitool, Embeddings, and Vertex AI Vector Search perform semantic matching.

View on GitHub
Gemini
LangChain
LangGraph
Orchestration

Intro to LangGraph with Gemini

Learn how to combine LangGraph's workflow capabilities with Gemini's language understanding and generation skills to streamline and automate complex financial analysis tasks.

View on GitHub
Gemini
LangChain
LangGraph
Orchestration
Speech

Create custom podcast episodes

Use Gemini, LangGraph, and Text-to-Speech to create custom podcast episodes.

View on GitHub
Gemini
Speech

Storytelling with Gemini and Text-to-Speech

Use Gemini and Text-to-Speech to create and read a story with multiple characters.

View on GitHub
Gemini
Multimodal

Analyze a codebase

Use Gemini to generate code, summarize a codebase, debug, improve code, and assess code.

View on GitHub
Gemini
Prompting
Security

LLM Security for developers

Learn about prompt injection attacks and how to mitigate them.

View on GitHub
Evaluation
Gemini

Gen AI Evaluation Service

Evaluate Gemini responses using metrics and custom datasets.

View on GitHub
Gemini
Tuning

Supervised Fine-tuning with Gemini

Learn how to fine-tune Gemini for specific tasks.

View on GitHub
Gemini
RAG

Intro to Vertex AI RAG Engine

Build custom RAG workflows with Gemini and Vertex AI RAG Engine.

View on GitHub
Gemini
Multimodal

Document Processing with Gemini

Use Gemini to process documents for classification, extraction, and summarization.

View on GitHub
Gemini
Multimodal

Intro to the Google Gen AI SDK

Intro to the Google Gen AI SDK.

View on GitHub
Gemini
Multimodal
Prompting

Gemini with Multimodal Data

How to prompt Gemini with multimodal data (text, documents, images, video, and audio).

View on GitHub
Gemini

Getting started with Gemini 2.0 in Vertex AI using REST API

Use Gemini 2.0 with REST/curl.

View on GitHub
Evaluation
Gemini
Prompting

Prompt Engineering, Evaluation, and Prompt Templating

Use Gen AI Evaluation Service SDK for prompt engineering and evaluation.

View on GitHub
Embeddings
Multimodal

Intro to Multimodal Embeddings

Learn about multimodal embeddings.

View on GitHub
Embeddings
Tuning

Intro to Embeddings Tuning

Learn how to tune embeddings models.

View on GitHub
Embeddings
Vector Search

Task Type Embeddings

Learn how to get better embeddings for your specific task.

View on GitHub
Embeddings
Vector Search

Hybrid Search with Vertex AI Vector Search

Learn how to use hybrid search with Vertex AI Vector Search combining semantic & keyword search.

View on GitHub
Agents
Gemini
LangChain
LangGraph

AI Agents for Engineers (Evolution of AI Agents)

This notebook demonstrates 3 different approaches to generating essays using the Gemini API, Zero-Shot, Step-by-Step with LangChain, and Iterative with LangGraph.

View on GitHub
Gemma
Hugging Face

Hugging Face DLCs: Serving Gemma with Text Generation Inference (TGI) on Vertex AI

Learn how to deploy Google Gemma from the Hugging Face Hub on Vertex AI using the Hugging Face Deep Learning Container (DLC) for Text Generation Inference (TGI).

View on GitHub
Gemma
LangChain
RAG

Cloud Run GPU Inference: Gemma 2 RAG Q&A with Ollama and LangChain

Learn how to deploy Gemma 2 in Cloud Run to build a simple RAG Q&A application.

View on GitHub
Gemma
Hugging Face

Hugging Face DLCs: Serving PaliGemma using Pytorch Inference on Vertex AI with Custom Handler

Learn how to deploy Google PaliGemma from the Hugging Face Hub on Vertex AI using the Hugging Face Deep Learning Container (DLC) for Pytorch Inference in combination with a custom handler.

View on GitHub
Gemma
Hugging Face
Tuning

Hugging Face DLCs: Fine-tuning Gemma with Transformer Reinforcement Learning (TRL) on Vertex AI

Learn how to fine-tune Gemma with Transformer Reinforcement Learning (TRL) on Vertex AI.

View on GitHub
Hugging Face

Guess who or what app using Hugging Face Deep Learning container model on Vertex AI

Create a"Guess who or what" application using Vertex AI, Hugging Face Deep Learning container, an image generation open model, and Gemini to solve and visualize riddles.

View on GitHub
Embeddings

Visualizing embedding similarity from text documents using t-SNE plots

Visualize embedding similarity from text documents using t-SNE plots.

View on GitHub
Embeddings
Vector Search

Vertex AI Vector Search Quickstart

Learn how to use Vertex AI Vector Search to find similar text documents.

View on GitHub
Embeddings
Gemini
Vector Search

Anomaly Detection of Infrastructure Logs using Gemini and BigQuery Vector Search

Learn how to large volumes of infrastructure logs using Gemini, vector embeddings and BigQuery Vector Search to perform anomaly detection.

View on GitHub
Embeddings
Gemini

Log Anomaly Detection & Investigation with Text Embeddings + BigQuery Vector Search

Learn how to large volumes of audit logs using Gemini, vector embeddings and BigQuery Vector Search to perform anomaly detection.

View on GitHub
Function Calling
Gemini

Working with Data Structures and Schemas in Gemini Function Calling

Learn how to use Gemini Function Calling with data structures and schemas.

View on GitHub
Function Calling
Gemini

Working with Parallel Function Calls and Multiple Function Responses in Gemini

Learn how to use parallel function calls and multiple function responses in Gemini.

View on GitHub
Function Calling
Gemini
Prompting

Introduction to ReAct Agents with Gemini & Function Calling

Learn how to use ReAct Agents with Gemini and Function Calling.

View on GitHub
Function Calling
Gemini

Forced Function Calling with Tool Configurations in Gemini

Learn how to use forced function calling with tool configurations in Gemini.

View on GitHub
Function Calling
Gemini

Using Gemini Function Calling to Get Real-Time Company News and Insights

Learn how to use Gemini Function Calling to get real-time company news and insights.

View on GitHub
Function Calling
Gemini
Multimodal

Multimodal Function Calling with the Gemini API & Python SDK

Learn how to use Gemini Multimodal Function Calling.

View on GitHub
Gemini
RAG
RAG Engine

Advanced RAG Techniques - Vertex RAG Engine Retrieval Quality Evaluation and Hyperparameters Tuning

Learn about advanced RAG techniques with evaluation and hyperparameter tuning.

View on GitHub
Gemini
RAG
RAG Engine

Vertex AI RAG Engine with Pinecone

Learn how to use Pinecone with Vertex AI RAG Engine.

View on GitHub
Gemini
RAG
RAG Engine

Vertex AI RAG Engine with Weaviate

Learn how to use Weaviate with Vertex AI RAG Engine.

View on GitHub
Gemini
RAG
RAG Engine

Vertex AI RAG Engine with Vertex AI Feature Store

Learn how to use Vertex AI Feature Store with Vertex AI RAG Engine.

View on GitHub
Gemini
RAG
RAG Engine

Vertex AI RAG Engine with Vertex AI Vector Search

Learn how to use Vertex AI Vector Search with Vertex AI RAG Engine.

View on GitHub
Gemini
RAG
RAG Engine

Vertex AI RAG Engine with Vertex AI Search

Learn how to use Vertex AI Search with Vertex AI RAG Engine.

View on GitHub
Agents
Gemini
Reasoning Engine

Debugging and Optimizing Agents: A Guide to Tracing in Reasoning Engine

Learn how to use Tracing in Reasoning Engine.

View on GitHub
Gemini
LangChain
Reasoning Engine

Deploying a RAG Application with AlloyDB to LangChain on Vertex AI

View on GitHub
Agents
Gemini
RAG
Reasoning Engine
Search

Building a Conversational Search Agent with Reasoning Engine and RAG on Vertex AI Search

View on GitHub
Agents
Gemini
Reasoning Engine

Intro to Building and Deploying an Agent with Reasoning Engine in Vertex AI

View on GitHub
Agents
Gemini
LangGraph
RAG
Reasoning Engine

Building a Multi-Agent RAG Application with LangGraph and Reasoning Engine

View on GitHub
Gemini
LangGraph
RAG
Reasoning Engine

Deploying a RAG Application with Cloud SQL for PostgreSQL to LangChain on Vertex AI

View on GitHub
Agents
Gemini
Reasoning Engine

Building and Deploying a Google Maps API Agent with Reasoning Engine

View on GitHub
Gemini
LangGraph
Reasoning Engine

Building and Deploying a LangGraph Application with Reasoning Engine in Vertex AI

View on GitHub
Gemini
Multimodal

Gemini 1.5: A workshop in multimodal use cases

View on GitHub
Gemini
Multimodal

Video Analysis with Gemini

View on GitHub
Gemini
Multimodal

YouTube Video Analysis with Gemini

View on GitHub
Gemini
Multimodal
Vector Search

Building a Multimodal Chatbot for Warranty Claims using Gemini and Vector Search in Vertex AI

View on GitHub
Gemini
Multimodal
RAG

Multimodal Retrieval Augmented Generation (RAG) using Gemini API in Vertex AI

View on GitHub
Gemini
LlamaIndex
RAG

LlamaIndex with Vertex AI Vector Search to perform question answering RAG

View on GitHub
Gemini
LangChain
Multimodal
RAG

Multimodal Retrieval Augmented Generation (RAG) with Gemini, Vertex AI Vector Search, and LangChain

View on GitHub
Gemini
RAG

Small-to-big Retrieval-Augmented Generation

View on GitHub
Gemini
Prompting

ReAct (Reasoning + Acting) + Custom tool for Healthcare NL API + Gemini 1.5 Pro + LangChain

View on GitHub
Gemini
Prompting

Using Gemini in Education

View on GitHub
Gemini
Prompting

AI Quick Build Experience

View on GitHub
Gemini
Multimodal
RAG

Code Retrieval Augmented Generation (RAG) with Gemini API

View on GitHub
Gemini
Multimodal

Product listing generation with Gemini 1.5 Pro

View on GitHub
Gemini
Multimodal

Multimodal retail recommendation: using Gemini to recommend items based on images and image reasoning

View on GitHub
Gemini
Multimodal
Prompting

Sheet Music Analysis with Gemini

View on GitHub
Gemini
Multimodal

Analyzing movie posters in BigQuery with Gemini 1.5 Flash

View on GitHub
Gemini
LangChain

Getting Started with LangChain 🦜️🔗 + Gemini API in Vertex AI

View on GitHub
Agents
Gemini

Building a Weather Agent with AutoGen and Gemini

View on GitHub
Gemini
Prompting

Vertex AI Prompt Optimizer Notebook UI

View on GitHub
Gemini
Prompting

Vertex AI Prompt Optimizer - Tool usage

View on GitHub
Gemini
Prompting

Vertex AI Prompt Optimizer - Custom metric

View on GitHub
Gemini
Prompting

Intro to Vertex AI Prompt Optimizer

View on GitHub
Gemini
Prompting

Text Summarization with Generative Models on Vertex AI

View on GitHub
Gemini
Prompting

Ideation with Generative Models on Vertex AI

View on GitHub
Gemini
Prompting

Chain of Thought & ReAct

View on GitHub
Gemini
Prompting

Question Answering with Generative Models on Vertex AI

View on GitHub
Gemini
Prompting

Text Classification with Generative Models on Vertex AI

View on GitHub
Gemini
Prompting

Text Extraction with Generative Models on Vertex AI

View on GitHub
Gemini
Tuning

Supervised Fine Tuning with Gemini 1.5 Flash for Change Detection

View on GitHub
Gemini
Tuning

Vertex AI Supervised Tuning Token Count and Cost Estimation

View on GitHub
Gemini
Tuning

Supervised Fine-Tuning with Gemini 1.5 Flash for Q&A

View on GitHub
Gemini
Tuning

Supervised Fine Tuning with Gemini 1.5 Pro for Image Captioning

View on GitHub
Evaluation
Gemini
Model Garden

Use Gen AI Evaluation SDK to Evaluate Models in Vertex AI Studio, Model Garden, and Model Registry

View on GitHub
Evaluation
Gemini
RAG

Evaluate Generated Answers from RAG using Rapid Evaluation and Dataflow ML with Vertex AI Pipelines

View on GitHub
Evaluation
Gemini

Enhancing Quality and Explainability with Vertex AI Evaluation

View on GitHub
Evaluation
Gemini

Evaluate and Compare Gen AI Model Settings

View on GitHub
Evaluation
Gemini

Bring-Your-Own-Autorater using Custom Metrics

View on GitHub
Evaluation
Gemini

Evaluate a Translation Model

View on GitHub
Evaluation
Gemini

Compare and Migrate from PaLM to Gemini Model

View on GitHub
Evaluation
Gemini
Multimodal

Evaluating Multimodal Tasks

View on GitHub
Evaluation
Gemini
LangChain

Evaluate LangChain

View on GitHub
Evaluation
Gemini

Compare Generative AI Models

View on GitHub
Evaluation
Gemini
RAG

Evaluate Generated Answers from RAG for QA with Gen AI Evaluation Service SDK

View on GitHub
Evaluation
Gemini

Customize Model-based Metrics to Evaluate a Gen AI Model

View on GitHub
Evaluation
Gemini
RAG

Evaluate Generative Model Tool Use

View on GitHub
Evaluation
Gemini

Get Started with Generative AI Evaluation Service

View on GitHub
Gemini
Prompting
RAG
Security

Gen AI and LLM Security - ReAct and RAG Attacks & Mitigations

View on GitHub
Gemini
Security

Responsible AI with Gemini API in Vertex AI: Safety Ratings and Thresholds

View on GitHub
Batch Prediction
Gemini

Monitor Batch Prediction with Gemini API

View on GitHub
Batch Prediction
Gemini

Intro to Batch Predictions with the Gemini API using BigQuery Input

View on GitHub
Imagen
Multimodal

Imagen 3 Customized Images

View on GitHub
Gemini
Imagen
Multimodal

Create High Quality Visual Assets with Imagen and Gemini

View on GitHub
Imagen
Multimodal

Create a Photoshop Document with Image Segmentation on Vertex AI

View on GitHub
Gemini
Imagen
Multimodal

Enhance Imagen Prompts with Gemini

View on GitHub
Imagen
Multimodal

Image Segmentation on Vertex AI

View on GitHub
Search

Vertex AI Search with Filters & Metadata

View on GitHub
Gemini
Search

Vertex AI Search - Querying Blended Data Apps and Summarization with Gemini

View on GitHub
Search

Create a Vertex AI Search Datastore and Search Engine

View on GitHub
Search

Building Search Applications with Vertex AI Search

View on GitHub
Gemini
LangChain
RAG
Search

Question Answering Over Documents

View on GitHub
Gemini
RAG
Search

Bulk Question Answering with Vertex AI Search

View on GitHub
Embeddings
Search

Custom Embeddings with Vertex AI Search

View on GitHub
Chirp
Speech

Get Started with Chirp 2 - Advanced Features

View on GitHub
Claude
Function Calling
Model Garden

Multimodal Function Calling with Claude Models

View on GitHub
Agents
Search

Vertex AI Search and Conversation Data Store Status Checker

View on GitHub

What's next