Table of Contents Adding filters: From story to codeFirst try: Add a post-filter in MovieServiceSecond try: Use a pre-filterRefining the search with extra filtersApplying toCriteria() in the searchReducing embedding costs with cachingStrategy with @CacheableA minimal frontendStep 1: HTMLStep 2: JavaScriptStep …
-
The Cost of Not Knowing MongoDB – Part 2 (appV5R0 to appV5R4)
Table of Contents Application Version 5 Revision 0 and Revision 1 (appV5R0 and appV5R1): A simple way to use the Bucket PatternSchemaBulk upsertGet reportsIndexesScenarioLoad tests resultsIssues and improvementsApplication Version 5 Revision 2 (appV5R2): Using the Bucket Pattern with the Computed …
-
Beyond Keywords: Implementing Semantic Search in Java With Spring Data (Part 1)
Table of Contents The magic behind vector searchPrerequisitesEmbeddings with Voyage AIPreparing the datasetMongoDB Atlas Vector Search (index and retrieval)Building the movie search appConfiguring the applicationThe document modelWire the request DTOCommunicating with Voyage AIThe EmbeddingServiceQuerying with Spring Data Vector Search operationThe …
-
The Cost of Not Knowing MongoDB – Part 1: appV0 to appV4
Table of Contents The application: finding fraudulent behavior in transactionsThe load testInitial scenario and data generatorThe instances configurationApplication Version 1 (appV1)SchemaBulk upsertGet reportsIndexesInitial scenario statsLoad test resultsIssues and improvementsApplication Version 2 (appV2)SchemaBulk upsertGet reportsIndexesInitial scenario statsLoad tests resultsIssues and improvementsApplication …
-
Keywords Meet Vectors: Hybrid Search on MongoDB
Table of Contents What is hybrid search?How does it work in MongoDB?Why movies collection are the perfect demoInspecting the anchor documentSanity checksStep 1: Prepare the query vectorStep 2: Run semantic searchStep 3: Apply hybrid scoringStep 4: Hybrid ranking with Reciprocal …
-
Working with Geo Location Data
MongoDB makes it really easy to work with location data (sometimes called Geo Data) by simplifying how to store this type of data and streamlining how you query for it so you can easily create “find nearby” queries, or plot …
-
Agents Meet Databases: The Future of Agentic Architectures
Table of Contents A Quick Overview of AgentsPath 1: Standardized Integration with MCP serversPath 2: Custom Integrations for Control and FlexibilityAccuracy, Security, and Performance ConsiderationsAccuracy: Ensure Reliable Query GenerationSecurity: Maintain Protection and GuardrailsPerformance: Manage Unpredictable Agentic WorkloadsThe Agentic Future Depends …
-
Building an AI Semantic Movie Recommender With Vector Search
Last time, we created a vector search index in a local MongoDB Atlas cluster. Now, let’s put it to work with a real case: building an AI-powered movie recommender that suggests films similar to The Matrix–without any shared keywords. 🕒 …
-
Introduction to Data-Driven Testing with Java and MongoDB
Table of Contents PrerequisitesStep 1: Create the entitiesExplanation of annotations:Step 2: Create a database containerStep 3: Generate our first DDTConclusion As applications expand, the complexity of the rules they enforce also increases. In many systems, these rules are embedded within …
-
Power your AI application with Vector Search
Most major database vendors, like MongoDB , are adding vector search capabilities to their products. It’s becoming a standard feature as demand for AI-powered applications grows. 🕒 Reading time: 3-4 min 🧠 What is vector search needed for? MongoDB Vector …
-
From Zero to Vector Hero – Locally!
In the previous issue, I explained how to run a local MongoDB Atlas cluster using Atlas CLI – no cloud account required. If you missed it, read it here 👉 Run an Atlas cluster locally in minutes. Now let’s see …