MMS • Sergio De Simone
At its Google Cloud Next conference, Google officially introduced new capabilities for its enterprise AI platform, Vertex AI, which aim to enable more advanced user workflows, among other things.
After announcing them at its last Google I/O conference as a technology preview, Google has extended Vertex AI Search and Conversation capabilities with new features and announced their general availability.
Thanks to Vertex AI Search, developers can retrieve information from a variety of enterprise sources, such as document repositories, databases, website, and other kinds of applications. They can, for example, easily build a search engine able to interact with customers based on that information, says Google.
Vertex AI Search and Conversation offers a simple orchestration layer to combine enterprise data with generative foundation models, as well as with conversational AI and information retrieval technologies.
Vertex AI Conversation enables the creation of natural-sounding, human-like chatbots. For example, developers can create a chatbot based on a website, enterprise documents, FAQs, emails, and so on.
Vertex AI lets developers combine deterministic workflows with generative outputs, combining rules-based processes with dynamic AI to create apps that are engaging but reliable.
The new features that Google has just announced should enable building intelligent apps that go beyond just retrieving important information by taking actions on behalf of their users.
They include support to handle follow-up-questions without restarting the interaction, thanks to multi-turn search; a tighter integration with third-party application using extensions and data connectors, which make it possible to connect to a variety of applications like MongoDB, Datastax, Salesforce, JIRA, and others; and the possibility of increasing confidence in the quality of returned results by basing generative outputs on enterprise data.
Vertex AI Search can also be combined with vector search to leverage its ability to find “similar” solutions with the aim of supporting semantic search, personalized recommendations, multi-modal search, and so on.
Vertex AI Search will in future support access controls to ensure users can only see information they are entitled to, and additional features like citations, relevance scores, and summarization.
Vertex AI is a platform aimed at developers with little machine learning expertise. A few months ago, Google made support for Generative AI on Vertex AI generally available, including the PaLM 2 powered text model, the Embeddings API for text, and foundational models in Model Garden.