Couchbase Capella AI Services 2024
Streamlining the development of agentic AI applications
Capella AI Services enable enterprises to tackle the expanding data challenges associated with AI development and deployment, simplifying the process of creating secure, scalable agent-based AI applications. By using Capella AI Services, organizations can efficiently prototype, build, test, and deploy application agents, keeping models and data in close proximity. This setup minimizes latency and reduces operational costs, which are common hurdles when integrating new technology components and workflows.
Capella AI Services include:
- Model Services: Offers managed endpoints for leading LLMs and embedding models, and provides value-added capabilities, such as prompt and conversation caching, guardrails, and keyword filtering to support RAG and agentic workflows. The colocation of data and AI models makes it easy to meet the desired privacy and latency requirements for building enterprise-grade RAG applications, without needing to use expensive private links or custom solutions.
- Unstructured Data Services: Extracts, cleans, chunks, and transforms unstructured documents into JSON, preparing them for vectorization. It also extracts structured information from complex documents and makes them queryable in Capella. This saves developers time associated with building DIY preprocessing pipelines.
- Vectorization Services: Automates vectorization and indexing of data stored in Capella. Along with Model and Unstructured Data Services, this helps developers quickly build a RAG pipeline with fewer tools.
- AI Agent Catalog Services: Accelerates agentic application development by offering a centralized repository for tools, metadata, prompts, and audit information for LLM flow, traceability, and governance. It also automates discovery of relevant agent tools to answer user questions, and manages guardrails to ensure that agent exchanges are consistent over time.
- Capella AI Functions: Enhances developer productivity by embedding AI-driven data analysis directly into application workflows using familiar SQL++ syntax, eliminating the need for external tools or custom code. With capabilities like summarization, classification, sentiment analysis, and data masking, Capella empowers developers to seamlessly transform complex transactional and columnar data into actionable insights within a single unified platform.
Capella Free Tier
To improve convenience and accessibility for developers, we’re excited to introduce a new Couchbase Capella™ Free Tier that replaces Capella’s 30-day trial. It allows developers to learn, use, and persist their activity in Capella for as long as they need to, and it supports promoting their work into test and production environments. The free tier is available with forum and community support, and it will open on September 9.
Capella Columnar now on Google Cloud
Couchbase’s JSON-native, real-time analytics is now available on Google Cloud, in addition to AWS. Capella customers get zero-ETL data movement for JSON data into an analytics-ready columnar format, with MPP processing, and separation of compute and storage for high performance and scalability. Capella iQ allows you to use natural language for query generation and chart creation. Additionally, developers can write back data from the columnar store to the Capella transactional store to incorporate calculated metrics into critical applications.
Announcing Couchbase Enterprise Server 7.6 and 7.6.2
Support for vector search and AI-powered adaptive applications
The spring 2024 release of Capella brought support for Couchbase Server 7.6, including high-performance storage, indexing, and retrieval of vector embeddings. Organizations are racing to build hyper-personalized adaptive applications powered by generative AI that deliver exceptional experiences to their end users. Vector search enables organizations to use the retrieval-augmented generation (RAG) framework to interact with LLMs and other foundation models to make AI-powered chatbots and applications safer, up to date, and correctly aligned to specific corporate information. Additionally, teams can use hybrid search, a combination of vector search, text search, range search, explicit value search, and geospatial search, to build out robust search solutions for end users – all within a single platform. There’s no need for a separate vector database. Advanced searches can be supported by a single SQL query and single index to deliver powerful, low-latency results while lowering TCO at the same time. Learn more
Further performance enhancements for vector search
Couchbase Enterprise Server 7.6.2 adds impressive performance and scalability improvements to vector search for self-managed and Capella-based systems, including a 7 times throughput increase and lower memory requirements. It expands support to 4096-dimensional vectors and adds base64 compressed vectors for both data and queries, reducing storage overhead. Learn more
Support for vectors in Couchbase Mobile
Couchbase is the first database vendor to announce vector support for its embeddable mobile database (Couchbase Lite). This will allow customers to build powerful AI-powered applications at the edge where data is produced and consumed. See the Mobile tab for more details.
AI ecosystem integrations
Couchbase is boosting its AI partner ecosystem with LangChain and LlamaIndex to further increase developer productivity. Integration with LangChain enables a common API interface to converse with a broad library of LLMs. Similarly, Couchbase integration with LlamaIndex will provide developers with even more choices for LLMs when building adaptive applications. These integrations will accelerate query prompt assembly, improve response validation, and facilitate RAG applications.
Graph capabilities enabled by query traversals
Couchbase offers support for graph relationship traversals, which means the ability to do recursive queries for hierarchy and network mapping. Query hierarchical data structures allow for complex analyses with ANSI SQL recursive CTE in areas like organization charts, bill of materials, supply chain management, network topology, and social networks. Learn more
New index rebalancing reduces times by up to 80%
In order to make scale-out of index nodes faster without impacting CPU or memory usage, Server 7.6 now utilizes file-based rebalancing. Testing has shown a dramatic improvement in the time to complete rebalances, making the process easier and more successful. Learn more
Couchstore to Magma, one-step upgrade without downtime
Customers will be able to migrate from Couchstore to the Magma storage engine without stopping the front-end workloads. Customers must be on version 7.6 to enable the migration. Migration can be reversed at any time if needed. Learn more
Faster failover times improve HA
In the case of a data node outage, the query will automatically be rerouted to the next available data node without any action from the application. The lower minimum auto-failover timeout has been reduced from 5 seconds to 1 second, and the heartbeat frequency has been reduced from 1 second to 200 milliseconds. Learn more
Query simplifications
To make initial development and testing easier, users can perform all database CRUD and join operations without indexes. This improves the experience for new users with CREATE, INSERT, and SELECT without getting an index error. Additionally, users can do simple key-value range scans based on document key prefixes without needing query and indexing nodes. For the best performance, indexes are still recommended where speed is a priority. Learn more
Couchbase Mobile: What’s New
Introducing Couchbase Edge Server
Couchbase Edge Server is a lightweight, offline-first database solution for edge use cases designed to enable low latency access, offline storage, and processing capabilities for app data in internet poor and computing resource constrained environments such as planes, restaurants, warehouses, theme parks and stadiums.
Edge Server supports a modest number of clients (10’s to hundreds), and runs on edge hardware that lacks the required compute and RAM for a full blown, multi-node database cluster deployment, such as a single board computer like Raspberry Pi or low-end server hardware. It is ideal for powering seatback in-flight apps on airliners or tabletop digital ordering systems at casual dining restaurants, where local clients range in the few hundreds.
Edge Server also offers automatic data synchronization with remote Couchbase Capella App Services and/or Sync Gateway in the cloud. With the Edge Server, app clients can access data even when disconnected from remote servers, while data synchronization to the cloud happens in the background whenever the internet is available. Data access is provided through a simple RESTful interface that any HTTP client can use. Additionally, for more advanced applications that require local storage, Couchbase Lite embedded clients can sync data directly with the local Edge Server.
About Edge Server
Edge Server is a standalone server that is powered by Couchbase Lite Core, the same lite core engine that is the “brain” of the Couchbase Lite database (which has been enterprise-tested and deployed on all Couchbase Lite deployments).
The server supports the following interfaces:
1. REST API: A RESTful interface that allows any HTTP client , including browser applications, to access, query and listen to changes in data.
2. Remote Sync: Enables Edge Server to sync data with with remote upstream Sync Gateway/App Services over websockets based replication protocol.
3. Edge Sync: Allows downstream couchbase lite applications at the edge to sync data with Edge Server.
4. Server Sync: This interface can be used to sync data with another edge server. This is useful to setup a secondary Edge Server as backup (for HA).
Why Edge Server?
While internet dependencies are a known challenge that can cause latency and downtime for edge applications, sometimes getting around those challenges by storing and processing data locally at the edge can also pose a challenge.
This is especially true when there is extremely limited local storage and compute resources available to serve them, such as on planes, in small restaurants, a warehouse in a port, even a major big box retailer in the middle of a city might operate under internet and computing resource constrained conditions.
Couchase Edge Server’s small footprint and built in data synchronization provide the perfect solution for these environments, allowing data to be processed locally using minimal computing resources. This enables a lightning fast experience for app users even without the internet. And when connectivity is available, Edge Server automatically syncs with Couchbase Capella in the cloud for long term data storage and analysis.
Learn more about Edge Server
Check out the Edge Server blog
Download and try the edge server today!
Start building
Check out our developer portal to explore NoSQL, browse resources, and get started with tutorials.
Use Capella free
Get hands-on with Couchbase in just a few clicks. Capella DBaaS is the easiest and fastest way to get started.
Get in touch
Want to learn more about Couchbase offerings? Let us help.