MongoDB Atlas Vector Search Makes Real-Time AI a Reality with Confluent

Today, we’re excited to announce our new integration with Confluent Cloud. MongoDB Atlas Vector Search users now have simple access to data streams across their entire business, enabling them to build cutting-edge Generative AI applications that are grounded in a real-time, contextual, and trustworthy knowledge base. Think of an application like ChatGPT, but if it knew everything about your private enterprise data, including constant awareness of what’s happening in the world and your business right now. Atlas Vector Search allows you to search intelligently across any unstructured data, using the power of Large Language models (LLMs). With Confluent’s data streaming platform, you can provide a continuous supply of AI-ready data for the development of sophisticated customer experiences, bridging the gap between legacy data systems and the modern data stack.

High-value, trusted AI applications require real-time data

Real-time AI needs real-time data from across your organization. The promise of real-time AI is only unlocked when models have all the freshest contextual data they need to respond just in time with the most accurate, relevant, and helpful information. However, building these real-time data connections across on-prem, multi-cloud, public, and private cloud environments for AI use cases is not trivial.

Traditional data integration and processing tools are batch-based and inflexible, creating an untenable number of tightly coupled point-to-point connections that are hard to scale and lack governance. As a result, the data made available is stale and of low fidelity. This introduces unavoidable latency into the AI application and may outright block implementation altogether. The difficulty in gaining access to high-quality, ready-to-use, contextual, and trustworthy data in real-time is hindering developer agility and the pace of AI innovation.

Confluent's data streaming platform fuels MongoDB Atlas Vector Search with real-time data

With the MongoDB Kafka Connector, users can easily configure MongoDB Atlas as a destination for customer 360 data from Confluent Cloud. This data is converted into vector embeddings using various machine learning models (OpenAI, HuggingFace, and more) and orchestrated by Atlas Triggers. Then using Atlas Vector Search, this data can be indexed and searched efficiently to power use cases such as semantic search, recommendation engines, Q&A systems, and many others.

We demonstrate a Chatbot for e-commerce that will allow users to ask natural language questions to discover what they need and then get recommendations on products to buy that suit their preferences. Some of the data required in this scenario includes the currently available inventory, the shipping options, and their session browsing history. The users can refine their product recommendations using a conversational interface, all the while ensuring that the products being recommended are rooted in real-time data.

The benefits of being able to effectively use real-time data are immense, almost critical, in this scenario, since recommending a product that’s not available or can’t be delivered to a user’s location in the time frame they require would mean a lost sale and a dissatisfied customer. The inventory data is rapidly changing - products go in and out of stock constantly. Hence the customer chat/assistant application will need to quickly come up with new sets of recommendations.

With Confluent, MongoDB Atlas Vector Search users can break down data silos, promote data reusability, improve engineering agility, and foster greater trust throughout their organization. This allows more teams to securely and confidently unlock the full potential of all their data with MongoDB Atlas Vector Search. Confluent enables organizations to make real-time contextual inferences on an astonishing amount of data by bringing well-curated, trustworthy streaming data to AI systems, vector databases, and AI-powered applications.

With easy access to data streams from across their entire business, MongoDB Atlas Vector Search users can now:

• Create a real-time knowledge base: Build a shared source of real-time truth for all your operational and analytical data, no matter where it lives for sophisticated model building and fine-tuning

• Bring real-time context at query time: Convert raw data into meaningful chunks with real-time enrichment and continually update your embedding databases for your GenAI use cases

• Build governed, secured, and trusted AI: Establish data lineage, quality, and traceability, providing all your teams with a clear understanding of data origin, movement, transformations, and usage

• Experiment, scale, and innovate faster: Reduce innovation friction as new AI apps and models become available. Decouple data from your data science tools and production AI apps to test and build faster

MongoDB Atlas Vector Search and Confluent enable simple development of real-time AI applications

Our new Confluent integration enables all your teams to tap into a continuously enriched real-time knowledge base, so they can quickly scale and build AI-enabled applications using trusted data streams. Here’s a demo video to demonstrate how this works:

Getting started

Get started by creating a MongoDB Atlas account if you don't already have one. Just click on “Register.” MongoDB offers a free-forever Atlas cluster in the public cloud service of your choice. To learn more about Atlas Vector Search, visit the product page.