Google Cloud Unveils New Generative AI Tools for Building Search and Conversational Apps
Google Cloud’s blast of new generative AI features for Vertex AI at the Cloud Next event went beyond models with the reveal of two new interactive tools, Vertex AI Search and Vertex AI Conversation. As their names suggest, these tools have been built to simplify creating and deploying search and conversational AI applications leveraging large language models (LLMs).
Vertex AI Model Garden Growth
Vertex AI Search and Vertex AI Conversation offer a streamlined system for making search and conversation apps based on Google’s PaLM 2 and other LLMs. The months of complex development are shortened to hours, with minimal machine learning expertise necessary. Rather than assembling components from scratch, developers can ingest data sources, customize as needed, and launch AI search engines or chatbots out of the box. This rapid prototyping facilitates exploring uses from customer service to enterprise search grounded in real business information.
Vertex AI Search offers Google-quality, multimodal search leveraging foundation models. Vertex AI Conversation helps build natural language chatbots and voice assistants. Developers can tune conversations with website content, documents, FAQs, and more. It combines generative responses with deterministic rules-based logic for reliability. Actions like booking appointments can also be enabled.
“For generative AI to achieve its immense potential, it needs to be broadly accessible and easy to integrate into a range of services. That’s why we offer our customers Vertex AI Search and Conversation— generally available today— to abstract the complexity of creating generative search and chat applications. These products enable even developers with little machine learning expertise to build and deploy intelligent apps in as little as a few hours,” Google Cloud vice presidents Amin Vahdat and Burak Gokturk wrote in a blog post. “Rather than spending months building gen AI apps, enterprise developers can quickly ingest data, add customization, and, with a few clicks, build a search engine or chatbot that can interact with customers and answer questions grounded in the factuality of their enterprise website along with specified structured and unstructured data sources. This ability to quickly prototype generative apps lets enterprises pursue a range of use cases, from food ordering to banking assistance to customer service.”
Both Search and Conversation offer new features announced today, including multi-turn searches and the Extensions and Grounding features available across Vertex AI, which link models and apps to real-time data from a company and source information from that data to limit hallucinations. Google Cloud’s goal seems to be making building search and conversation apps easier in a way familiar to anyone who has used Dialogflow to create a Google Assistant Action or Android app. Vertex AI’s end-to-end platform approach reflects Google Cloud’s strengths with search and conversation representing leading use cases for generative AI.
“Improving search and conversational use cases with generative AI is one of the most widely-applicable gen AI projects we see organizations pursuing, and with Vertex AI Search and Conversation, significantly faster time-to-deployment and time-to-value are within reach,” Vahdat and Gokturk wrote. “Search and conversation use cases provide a clear opportunity for organizations to quickly gain experience with and benefit from generative AI technologies. We look forward to seeing more of our customers leverage Vertex AI Search and Conversation to delight their customers and employees.”