Database company Couchbase Inc. is looking to support the development of artificial intelligence-powered agents with the addition of Capella AI Services to its flagship cloud data platform, Couchbase Capella.

Announced today, the Capella AI Services are supposed to help companies address some of the most pressing challenges they face during AI development and deployment.

AI agents are one of the hottest trends in AI at the moment, referring to intelligent applications that can automate actions and tasks on behalf of users with minimal supervision. Think an AI customer support chatbot that can automatically process a refund request, or a virtual assistant that can book a hotel on someone’s behalf and add that booking to their calendar.

The new services, available in preview today, include model hosting, automated vectorization, unstructured data preprocessing and AI agent catalog capabilities. Essentially, the company is bundling everything developers require to prototype, build, test and then deploy their AI agents, while ensuring both the underlying data and the models are stored close together.

Couchbase Capella is the cloud-based version of the open-source Couchbase NoSQL database, and its main advantage compared to traditional databases like Oracle is that it can process both structured and unstructured information, which makes it an ideal choice for applications that need to access both types of data. It also acts as a data cache.

Over the last year, Couchbase has enhanced Capella’s capabilities in an effort to position it as the database of choice for AI developers. In February, it introduced vector search and retrieval-augmented generation capabilities, while integrating AI frameworks such as LlamaIndex and LangChain to support the development of generative AI applications. Then in September, the company further enhanced Capella’s AI capabilities with Capella Columnar, to support the development of more advanced generative AI applications that can analyze real-time data to deliver more personalized experiences.

A unified platform for AI agents

According to Couchbase, the new Capella AI Services are meant to address concerns enterprises have around performance, latency, control, costs, data security and privacy, as well as the need to manage different kinds of datasets and integrations.

They include model services consisting of managed endpoints for dozens of leading large language models and embeddings models, together with value-added capabilities such as prompt and conversation caching, AI guardrails and keyword filtering. According to Couchbase, these features are necessary to support both RAG and agentic AI.

Capella’s AI Services also extend to unstructured data, enabling developers to extract, clean and transform unstructured documents into a more flexible JavaScript Object Notation or JSON data format, so they can be stored as vectors and accessed and queried by AI models more easily. The vectorization process can be automated too, enabling unstructured information to be indexed in Capella to support the creation of RAG pipelines.

Then there are new AI agent catalog services that aim to accelerate the development of AI agents, providing a centralized repository for tools, prompts and metadata to support LLM flows, traceability and governance, the company said. These services can also automate the discovery of other agent-based tools needed to answer user’s questions and manage AI guardrails.

Matt McDonough, Couchbase’s senior vice president of product and partners, said AI agents need to be able to handle a diverse range of data formats to work effectively.

“Couchbase is making this possible by providing a comprehensive AI-powered developer data platform that streamlines RAG pipelines, ensures fast and secure model interactions and enables agent reuse during development and production,” he said. “We’re helping customers through the broad spectrum of AI advances, from simple vector search to RAG chatbots and sophisticated agentic AI apps.”

Elsewhere, the new Capella AI functions are intended to support AI-driven data analytics, classification and summarization within application workflows using the familiar SQL++ programming language syntax. This means developers don’t need to worry about external tooling or custom coding, Couchbase says.

McDonough explained that today’s enhancements provide developers with a unified platform complete with specialized data management tools to handle the complex workflows and LLM interactions needed to power AI agents. By unifying all of these tools, the company is helping developers to avoid problems around excess latency and high operational costs, while mitigating privacy and safety issues, he added.

Carl Olofson, an analyst at International Data Corp., said another challenge for organizations is that they’re required to preserve and analyze all of the interactions between humans and AI agents to ensure ongoing accuracy, reliability and safety for users. He said that’s what Couchbase is addressing with today’s updates.

“Couchbase Capella and its new AI Services are designed to strategically address these challenges, and provide enterprises the scalable architecture and flexibility needed to handle complex RAG workflows and manage huge volumes of new types of AI data,” the analyst said.

Image: SiliconANGLE/Freepik AI