Vertex by Google | AI Agents

Agent framework

•

By Google

Google Vertex AI Agent is a state-of-the-art platform developed to enable developers and organizations to build, deploy, and scale advanced AI agents efficiently. As part of Google Cloud's extensive AI ecosystem, it harnesses the capabilities of large language models (LLMs) and sophisticated machine learning technologies, aiming to transform business operations and enhance customer interactions.

Features

This platform offers a variety of features that facilitate the creation and management of AI agents. Below is an overview of the key features available through Google Vertex AI Agent:

Feature	Description
No-Code AI Agent Creation	Enables the creation of conversational AI agents using natural language inputs without requiring code, making AI development accessible to non-experts.
Data Grounding	Integrates enterprise data to ensure AI outputs are accurate and relevant, utilizing systems like Vertex AI Search and Retrieval Augmented Generation (RAG) APIs.
Efficient Testing and Deployment	Offers tools for performance evaluation and tuning, allowing for scalable deployment across enterprise-ready infrastructure.
Secure and Compliant	Meets industry standards such as HIPAA and ISO 27000-series, ensuring security and reliability for enterprise applications.
Advanced AI Capabilities	Includes document parsing, ranking, grounded generation, and fact-checking APIs for tailored business solutions.
Scalable Vector Search	Supports applications that can handle billions of vectors, integrating vector and keyword search for effective data management.
LangChain Integration	Supports the open-source Python framework LangChain, enhancing the capabilities of AI agents with advanced libraries.

Use Cases

Google Vertex AI Agent can be applied in various scenarios to enhance business processes and customer interactions:

Search Application: Leverages a combination of data storage and web search to provide answers to user inquiries, similar to traditional Retrieval Augmented Generation (RAG) systems.
Chat Application: Facilitates complex user interactions and guidance, surpassing the capabilities of pre-LLM chatbots by utilizing large language models.
Recommendation Application: Utilizes data storage to recommend items or content based on user interactions, enhancing user engagement and satisfaction.
Agent Application: Allows developers to create an LLM-agent system with multiple agents, defining high-level goals and steps for complex AI workflows.

How to Get Started

To begin utilizing Google Vertex AI Agent, developers and organizations can explore the platform through Google Cloud. Interested users can sign up for a trial or access the relevant documentation through the Google Cloud website. For further guidance, contacting Google Cloud support for personalized assistance is also an option.

Vertex AI Pricing Overview

The pricing for Vertex AI from Google is structured across various categories as follows:

1. Generative AI Pricing

Imagen Model for Image Generation: $0.0001 per image
Text, Chat, and Code Generation: $0.0001 per 1,000 characters
Text Data Upload, Training, Deployment, and Prediction: $0.05 per hour
Video Data Training and Prediction: $0.462 per node hour
Image Data Training, Deployment, and Prediction: $1.375 per node hour

2. AutoML Models

Training: $3.465 per node hour
Training (Edge on-device model): $18.00 per node hour
Deployment and Online Prediction: $1.375 – $2.002 per node hour
Batch Prediction: $2.222 per node hour

3. Vertex AI Forecast

Prediction:
- $0.2 per 1K data points (0-1M points)
- $0.1 per 1K data points (1M-50M points)
- $0.02 per 1K data points (>50M points)
Training: $21.25/hr in all regions

4. Vertex AI Workbench

Compute: Starting from $0.045564 per vCPU/hour
Memory: Starting from $0.0061068 per GB hour
Accelerators: Starting from $0.492 per hour
Disks: Starting from $0.144 per GB per month

5. Vertex AI Agent Builder Pricing

Vertex AI Agents Chat: $12.00 / 1,000 query
Vertex AI Agents Voice: $0.002 / second
Index Storage: $5.00 / GiB of raw data per month

6. Vertex AI Search Pricing

Search and Browse Queries: $2.50 per 1,000 requests

7. Vertex AI Free Trial and Freemium Version

Free Trial: $300 in free credits for 90 days

These prices are subject to change and may vary based on specific configurations and usage. For the most up-to-date pricing information, it is recommended to refer directly to Google Cloud's official documentation or contact their sales team.