Vertex AI Search and Conversation

Vertex AI’s out-of-box capabilities can remove the need for data chunking, generating embeddings, or managing indexes, conversational decision trees etc, hiding complexity behind a straightforward orchestration interface that lets developers build apps in hours and days with little or no coding and no prior machine learning experience. Enterprises can easily ingest data across various internal and external sources to build applications that understand user intent via natural language, and surface the right information with associated citations and attributions from a company’s public and private data. 

Enterprise developers who want to get started quickly can use the out-of-the-box capabilities to build and deploy chatbots and search engines in hours and days. Developers who want to combine multiple capabilities into enterprise workflows can use our API for direct integration. Advanced developers or AI practitioners can make deep customizations via Vertex AI offerings like Vector Search or Enterprise Knowledge Graph or Contact Center AI.

Apps built with Vertex AI Search and Conversation help enterprises solve the long-standing headache of surfacing personalized and relevant information from across the organization for customers and employees, turning tasks that used to take hours into quick searches or conversational explorations. Thanks to Google’s foundation models, these applications support multi-modal interactions that use not just text but also other forms of data such as images and voice. They can have multi-turn conversations that mean users can ask follow-up questions without having to start from scratch, and offer content summarization, citations and recommendations to aid in knowledge discovery and build confidence in information shared. 

With Vertex AI extensions your chatbots can access 1st or third party applications for information retrieval and to take actions on the user's behalf for e.g. booking a calendar or purchasing a flight. Vertex AI's data connectors offer data ingestion and read only access to data from across your enterprise, Google and third party applications like JIRA, Confluence and Salesforce. This means your search results are always fresh. 

With Vertex AI Search and Conversation enterprise developers have full control over what data their applications access and index, which tools the applications can take actions on behalf of the user and what information is surfaced to which user. All application data and user interactions are stored in the enterprise’s own cloud instance. This data is never accessed by Google Cloud or used to train Google’s underlying machine learning models. Vertex AI Search and Conversation also support several industry compliance standards like HIPAA, DRZ, and CMEK.