Category: Couchbase Server
-
Azure Key Vault for Credentials
Azure Key Vault is a cloud service for securely storing and accessing secrets, keys, and certificates. Using Azure Key Vault to store Couchbase credentials (rather than application settings or environment variables) provides encryption at…
-
XML to JSON conversion with Json.NET
XML-to-JSON conversion is a common requirement when modernizing .NET applications: migrating from legacy XML-based services or storage to JSON-native systems like Couchbase Server or Couchbase Capella. In C#, two libraries handle this conversion: Newtonsoft…
-
What Is a Token in AI? An Explainer
SUMMARY A token is the smallest unit of text an AI system uses to interpret and generate language, and it can represent a full word, part of a word, a character, or even a…
-
Build Internal Tools on Couchbase Data in Minutes With ToolJet
The Internal Tools Problem Every engineering team has them: the admin panel that took three sprints to build, the customer support dashboard that nobody wants to maintain, the data viewer that’s still a spreadsheet.…
-
Speed, Context, and Savings: Mastering Caching in the Capella AI Model Service
In the rapidly evolving landscape of generative AI, organizations face a persistent “triple threat”: high latency, unpredictable costs, and the loss of conversational context. Every redundant call to a large language model (LLM) is…
-
Vector Store vs. Vector Database: Differences and Similarities
What is a vector store? A vector store is a specialized type of data management system designed to store and retrieve vector embeddings. Think of it as a lightweight library or feature, often integrated…
-
A Breakdown of Graph RAG vs. Vector RAG
Large language models have changed how we interact with information, but they have one fundamental limitation: their knowledge is frozen in time. They can’t access real-time data or information from private, proprietary documents because…
-
Couchbase’s Data API in Practice With NodeRed
Couchbase Capella has a new Data API. If you’re wondering why it is important since we already have SDKs, the answer is addressed in our documentation – but here’s a quick comparison: Some use…
-
Build a Rate Limiter With Couchbase Eventing
Introduction Couchbase Server 8.0 introduces a new Eventing function handler called OnDeploy that allows customers to run business logic during Eventing function deployment or resumption without requiring any external mutation to trigger it. Earlier,…
-
Chatbots for Retail: Types, Use Cases, and Examples
Retail has always thrived on conversation. Decades ago, it was the shop owner greeting you by name. Today, it’s a chatbot popping up on your screen, asking if you need help. Some of these…
-
Increasing the Trust of Your AI Applications
As companies explore advancing probabilistic AI applications from experimentation to mission-critical enterprise systems, trust has become a critical factor for success. Organizations face growing challenges in building, scaling, and managing AI – ranging from…
-
CodeLab: Building a RAG Application With Couchbase Capella Model Services and LangChain
In this tutorial, you will learn how to build a retrieval-augmented generation (RAG) application using Couchbase AI Services to store data, generate embedding using embedding models, and LLM inference. We will create a RAG…