StarTree Enhances Real-Time Analytics Platform with AI Agent Support and Vector Embedding

StarTree boosts AI agent support in its real-time analytics platform - SiliconANGLE

StarTree boosts AI agent support in its real-time analytics platform StarTree Inc., the developer of a managed service based on the Apache Pinot real-time data analytics platform, is enhancing support for artificial intelligence workloads with two enhancements being announced today. They include support for Anthropic PBC's Model Context Protocol and vector embedding model hosting. MCP provides a standardized way for AI applications to connect with and interact with external data sources and tools to extend their built-in knowledge. Vector embedding model hosting allows machine learning models to convert multimodal data types such as text, images and audio into dense numerical representations that capture the semantic meaning of the input so it can be accessed via an application program interface or integrated directly into applications. That allows for advanced pattern matching and similarity searches on the data, going beyond text matching. These combined capabilities enable StarTree to support agentic AI applications, real-time retrieval-augmented generation or RAG, and conversational querying of real-time data. MCP is intended to spare developers the hassle of writing large amounts of custom code to integrate outside sources. While currently aimed mainly at developers, "MCP has the potential to benefit almost every stakeholder in the world of AI," according to Jason Andersen, vice president and principal analyst at Moor Insights & Strategy. It functions as an application program interface that eliminates the need for developers to each build bespoke integration hubs. MCP support allows AI agents to dynamically analyze live, structured enterprise data from StarTree's high-concurrency architecture, simplifying the deployment and management of autonomous agents. It also makes natural language-to-SQL queries easier and less brittle to deploy and enables conversational questions to build upon previous answers, StarTree said. "The MCP server allows AI agents to retrieve contextual information in a scalable manner," said Chinmay Soman, head of product. "It enriches every decision that the AI agent makes with fresh data and handles thousands of concurrent queries per second." Agents can also use the server to search for services that satisfy specific requests and connect to them directly. "It can discover schemas and interesting data or insights automatically by essentially having a conversation with the database through the MCP server," Soman said. Vector embeddings allow queries against data types that don't lend themselves well to conventional SQL. StarTree's new vector auto-embedding enables pluggable vector embedding models to streamline the continuous flow of data from source to embedding creation to ingestion. This enables RAG to be done in real time for uses like financial market monitoring and information technology infrastructure observability. "Traditional RAG is pretty batch-oriented," Soman said. "In a case like stock trading, prices can move based on comments on TV or stock filings. You can ingest that data into Pinot and ask questions like how stock is likely to trade that afternoon based on the freshest information." Pinot has supported vector embedding for over a year, but "we are doing it natively in the database so if something changes, we automatically reflect the latest embedding for a given record," Soman said. For example, observability log data can be translated into embeddings and searched immediately. "You can actually have a conversation with your logs," he said. "If you have exact pattern-matching, then text indexing works fine," said Peter Corless, director of product marketing. "But if you want to see if one log incident is like another log incident, you need vector similarity search as well as text indexing. StarTree now provides that capability natively, whereas other analytical databases require one database for vectors and another database for text indexing, he said. StarTree also announced the general availability of Bring Your Own Kubernetes, a new deployment option that gives organizations full control over StarTree infrastructure within their own Kubernetes environments, whether in the cloud, on-premises or in a hybrid architecture. This model is targeted at regulated industries where data residency, compliance and security policies limit cloud processing. It's also a more cost-effective option for organizations with stable, predictable workloads because it saves on computing and egress fees, StarTree said. The company previously offered software-as-a-service and "bring your own cloud" options, but the latter requires delegated access into a customer's cloud account. "That's OK for most customers but for some it's a point of friction," Soman said. "This model is completely disconnected; we don't have any connection to the data plane whatsoever." MCP support will be available in June, with vector embedding due to arrive in the fall.

StarTree Looks To Bring Real-Time Data And Analytics To AI

The additions of Model Context Protocol support and vector auto embedding to the StarTree real-time analytics platform will boost the performance of AI agents and power real-time retrieval-augmented generation. Big data startup StarTree is boosting the capabilities of its real-time analytics software with new functionality that more rapidly provides artificial intelligence applications and agents with data and analytical insights. Additions to the StarTree platform, including Model Context Protocol support and vector auto embedding, are designed to meet the demands of agentic AI and generative AI applications for low-latency queries and real-time data context awareness. StarTree also expanded the range of deployment options for its product with a new Bring Your Own Kubernetes plan that gives organizations full control over the SrarTree analytics infrastructure within their own Kubernetes environments. [Related: Meeting The Data Needs Of The AI World: The 2025 CRN Big Data 100] "There is a need to allow autonomous agents to get the information they need to complete a task," said Chad Meley, StarTree senior vice president, marketing and developer relations, in an interview with CRN. "They need that context of what's happening now in many cases like cashflow analysis or the state of an IT system." StarTree, founded in 2018 and headquartered in Mountain View, Calif., develops a real-time analytics platform that turns streams of raw data, such as website clickstreams, operational applications and sensor data, into actionable intelligence. The cloud-based system is built on Apache Pinot, the open-source, distributed OLAP database designed for real-time analytics that was originally developed by StarTree's founders when they worked at LinkedIn. StarTree's platform has been adopted by businesses and organizations - including more than 30 percent of the Fortune 1000 - for high-performance data analytics and business intelligence tasks that require low latency for queries and high concurrency (the ability to handle tens of thousands of queries per second). Like analytics, the growing wave of AI and generative AI applications and agents - and the large language models that power them - need huge volumes of data to operate and that's driving demand for more sophisticated technologies up and down the "big data stack." They also require sub-second query speeds, real-time context awareness, and the ability to support large numbers of autonomous agents working in parallel, according to StarTree. StarTree today said it is supporting Model Context Protocol (MCP), a standardized way for AI applications - more specifically the large language models LLMs) that power them - to connect and interact with external data sources and tools. That support will be available on StarTree Cloud in June. Peter Corless, StarTree product marketing director, said MCP is essentially an API that connects AI applications and LLMs to other systems. MCP was developed by AI startup Anthropic and announced in November 2024. The MCP support will allow StarTree to act as a local data source within MCP-based architectures and be accessible to MCP data servers, according to the company. That, in turn, will make it possible for AI agents to dynamically analyze live, structured enterprise data. It also makes it easier to deploy natural language-to-SQL queries. And retrieval-augmented generation (RAG) via MCP will allow AI systems to develop "definitive answers" and real-time insights in response to queries from data stored in StarTree. StarTree is also adding vector embedding model hosting into its platform, a move the company said will simplify and accelerate vector embedding generation and data ingestion for real-time RAG use cases based on Amazon Bedrock. The addition makes it possible to instantly transform existing data into AI-ready assets via an automated, rea-time pipeline Corless said. StarTree also announced the general availability of a new deployment option it calls Bring Your Own Kubernetes that the company says gives organizations full control over Star Tree's analytics infrastructure running within their own Kubernetes environments - either on-premises or in a private cloud. The new BYOK option, currently in private preview, is in addition to StarTree's existing deployment options including fully managed SaaS and Bring Your Own Cloud.