Boost Search Relevance with MongoDB Atlas’ Native Hybrid Search

Mai Nguyen and Henry Weller
June 25, 2025

We’re excited to introduce a native hybrid search experience that seamlessly combines the power of MongoDB Atlas’ native text search and vector search capabilities. Now in public preview, this capability leverages reciprocal rank fusion (RRF) to rank result sets from both text and vector searches, significantly improving relevance and user experiences. It simplifies application development by eliminating the need for separate search engines and vector databases, allowing developers to implement hybrid search out-of-the-box and quickly refine search accuracy for their use cases.

The new $rankFusion aggregation stage has helped us implement hybrid search much more easily and efficiently, as we can combine the power of keyword search and semantic search under one umbrella in MongoDB Atlas. This has improved the context retrieval accuracy for our Eddy AI chatbot by 30%.

Dr. Selvaraaju Murugesan, Head of Data Science, Kovai.co

Read the documentation to learn more.

Hybrid search: Precision meets semantic relevance

Search is the cornerstone of information discovery and application development. Whether you're shopping online, researching a medical condition, or analyzing business data, search helps us find the information we need. As technology evolves, so do user expectations of how they interact with searches and how their searches will perform.

Modern applications—from catalog search and product recommendations to retrieval-augmented generation (RAG) and emerging AI agents—require high-quality retrieval to handle unstructured data effectively. Relying solely on text or vector search as a single retrieval technique may not deliver the highest relevance and accuracy. While excellent for precise keyword retrieval, text search can struggle to understand nuanced language or identify semantically similar concepts. On the other hand, vector search is ideal for open-ended queries and high-dimensional data (images, audio, video, etc.), but it may miss crucial information that requires exact matches.

Consider the search query “quick and easy Italian dinner recipes.” While traditional text search efficiently identifies recipes containing these keywords in their titles, descriptions, or tags, it often lacks a deeper understanding of concepts like "quick and easy" or the nuances of Italian cuisine beyond literal terms. Adding vector search significantly enhances results by capturing semantically related ideas such as "simple," "minimal prep," or "10-minute meal," alongside recipes featuring classic Italian flavors like tomatoes, olive oil, garlic, oregano, and mozzarella, all suitable for a savory evening meal. This hybrid approach ultimately provides users with a more comprehensive and relevant search experience, balancing accuracy with broader discovery.

Combine the best of both worlds for engaging user experiences

Organizations are increasingly turning to hybrid search, using the combined strength of text and vector search to maximize the value of data and provide enhanced user experiences.

  • Improved accuracy for search, RAG, and AI agents: By leveraging both approaches, you deliver search results that are semantically relevant and precisely accurate. Hybrid search provides the foundation for more insightful and accurate responses from your generative AI models, reducing hallucinations.

  • Streamlined architecture: Organizations running hybrid search via separate search engines and vector databases typically encounter high complexity and costs. MongoDB simplifies hybrid search implementations by providing this integrated capability in the operational database, eliminating the need to manage multiple systems, reducing costs, and increasing efficiency.

  • Enhanced user experiences: Users benefit from more relevant and comprehensive search results, increasing user satisfaction.

How the Financial Times spearheaded AI-powered content discovery with hybrid search

The Financial Times, the leading business news organization, has successfully implemented hybrid search, combining MongoDB’s native full-text and vector search capabilities to power content discovery on its website (aiming to deploy the capability across all its digital properties). This enables relevant results for natural language queries and delivers robust content recommendations, providing readers with an enhanced web experience. The highly relevant article suggestions boost engagement and retention by saving valuable time for busy executives—the Financial Times' core subscriber demographic.

Hear more about the story in this video.

Nowadays with AI becoming more popular for solving different problems, the ability to do vector search alongside the standard keyword search is crucial. MongoDB Atlas is not just offering a database or search. What drew our attention to it was that it's kind of a full package… It gives a lot of things that you can get from a platform out-of-the-box.

Dimitar Terziev, Technical Director for Core Platforms, Financial Times

Get started with hybrid search in MongoDB Atlas

You can now streamline hybrid search implementations with a single $rankFusion aggregation stage. This allows for effortlessly combining full-text and vector search result sets into a unified ranked list, quickly surfacing the most relevant information.

Leveraging native and powerful query capabilities within Atlas, you can flexibly combine $rankFusion with various MongoDB aggregation stages—$vectorSearch, $search, $geoNear, $sort, and $match. This allows for the adjustment of weighted criteria, the production of custom relevance scores, and result sorting to address diverse requirements and use cases.

See the demo of hybrid search in action.

View the documentation to get started.

← Previous

Dynamic Term-Based Boosting in MongoDB Atlas Search

Search relevance is the bedrock of any modern user experience. While MongoDB Atlas Search offers a fantastic out-of-the-box relevance model with BM25, its standard approach treats all search terms with a uniform level of importance. For applications that demand precision, this isn't enough. What if you need to boost content from an expert author? Or prioritize a trending topic for the next 48 hours? Or ensure a specific promotional product always appears at the top? Relying on query-time boosting alone can lead to complex, brittle queries that are a nightmare to maintain. There's a more elegant solution. Enter the embedded scoring pattern—an advanced technique in Atlas Search that allows you to embed term-level boosting logic directly within your documents. It's a powerful way to make your relevance scoring data-driven, adaptable, and incredibly precise without ever changing your query structure. Why you need embedded scoring: From uniform to granular The standard approach to boosting is like using a single volume knob for an entire orchestra. The embedded scoring pattern, on the other hand, gives you a mixing board with a dedicated slider for every single instrument. This enables application owners to seamlessly build business-focused use cases, such as: Prioritizing authority: Elevate content from verified experts or high-authority authors. Boosting trends: Dynamically increase the rank of time-sensitive or trending topics. Elevating promotions: Ensure seasonal or promotional products get the visibility they need. By encoding scoring logic alongside your content, you solve the "one-size-fits-all" limitation and give yourself unparalleled control. Under the hood: Building the embedded scoring pattern Let's get practical. Implementing this pattern involves two key steps: designing the index and structuring your documents. 1. The index design: Defining your boosts First, you need to tell Atlas Search how to understand your custom boosts. You do this by defining a field with the embeddedDocuments type in your search index. This creates a dedicated space for your term-boost pairs. { "mappings": { "dynamic": true, "fields": { "indexed_terms": { "type": "embeddedDocuments", "dynamic": false, "fields": { "term": { "type": "string" }, "boost": { "type": "number" } } } } } } This index definition creates a special array, indexed_terms , ready to hold our custom scoring rules. 2. The document structure: Encoding relevance With the index in place, you can now add the indexed_terms array to your documents. Each object in this array contains a term and a corresponding boost value. Consider this sample document: { "id": "content_12345", "title": "Advanced Machine Learning Techniques for Natural Language Processing", "description": "Comprehensive guide covering transformer models and neural networks", "tags": ["technology", "AI", "tutorial"], "author": "Dr. Sarah Chen", "indexed_terms": [ { "term": "machine learning", "boost": 25.0 }, // High boost for the primary topic { "term": "dr. sarah chen", "boost": 20.0 }, // High boost for an expert author { "term": "tutorial", "boost": 8.0 } // Lower boost for the content format ] } As you can see, we've assigned a high score to the core topic ("machine learning") and the expert author, ensuring this document ranks highly for those queries. The query: Putting embedded scores into action Now for the magic. The query below uses the compound operator to combine our new embedded scoring with traditional field-based search. [ { "$search": { "index": "default", "compound": { "should": [ { // Clause 1: Use our embedded scores "embeddedDocument": { "path": "indexed_terms", "operator": { "text": { "path": "indexed_terms.term", "query": "machine learning", "score": { // Use the boost value from the document! "function": { "path": { "value": "indexed_terms.boost", "undefined": 0.0 } } } } } } }, { // Clause 2: Standard search across other fields "text": { "path": ["title", "description"], "query": "machine learning", // Add a small constant score for matches in these fields "score": { "constant": { "value": 5 } } } } ] }, "scoreDetails": true } }, { "$project": { "_id": 0, "id": 1, "title": 1, "author": 1, "relevanceScore": { "$meta": "searchScore" }, "scoreDetails": { "$meta": "searchScoreDetails" } } } ] In this query, a user searches for "machine learning". If our sample document is part of the index, the final score is a combination of our boosts: 25 points from the indexed_terms match. 5 points from the match in the title field. Total Score: 30 This gives us precise, predictable, and highly tunable ranking behavior. Aggregation strategies You can even control how multiple matches within the indexed_terms array contribute to the score. The three main strategies are: table, th, td { border: 1px solid black; border-collapse: collapse; } th, td { padding: 5px; } Strategy Use Case maximum Highlights the single most relevant term that matched. sum Accumulates the score across all matching terms. mean Normalizes the score by averaging the boost of all matching terms. Power comes with responsibility: Performance considerations While powerful, this pattern requires foresight and planning. Embedding terms increases your index size. If 1 million documents each get five embedded terms, your index now has to manage 6 million entries. To keep things snappy and scalable, follow these best practices: Be selective: Only embed high-impact terms. Don't use it for your entire vocabulary. Quantize boosts: Use discrete boost levels (e.g., 5, 10, 15, 20) instead of hyper-specific decimals. This improves caching and consistency. Perform regular cleanup: Create processes to remove obsolete or low-performing terms from the indexed_terms arrays. Always monitor your index size, query latency, and memory usage in the Atlas UI to ensure your implementation remains performant. Take control of your search destiny The embedded scoring pattern in MongoDB Atlas Search is a game-changer for anyone serious about search relevance. It moves beyond static, one-size-fits-all ranking and gives you dynamic, context-aware control directly within your data. You can use this pattern to implement business-driven ranking logic, enable real-time personalization, and achieve full transparency for tuning and debugging your search scores. While this article gives you a powerful head start, your journey into advanced relevance doesn't end here. For more in-depth implementation examples, guidance on operational analytics, and best practices to ensure your embedded boost values stay aligned with business goals, we highly recommend diving into the official MongoDB Atlas Search documentation . It's the perfect resource for taking this pattern from concept to production. Stop letting your search engine make all the decisions. Try the embedded scoring pattern today and unlock a new level of precision and power in Atlas Search.

June 24, 2025
Next →

Innovating with MongoDB | Customer Successes, July 2025

How time flies! Summer is in full swing, and it’s already time for another MongoDB customer success roundup. This month, we’re focusing on customers who have combined the flexibility of MongoDB Atlas with cutting-edge AI advancements to unlock insights and fuel innovation. Let’s be honest—AI is everywhere. We’re intrigued, inspired, and maybe a little overwhelmed by its possibilities. But the hype exists for a good reason: AI is a groundbreaking technology that’s poised to transform every industry, job, and task, and it’s fundamentally changing how software interacts with data. We’re quickly learning, though, that delivering meaningful outcomes with AI requires the right infrastructure. With MongoDB Atlas , companies are leveraging vector search, seamless document modeling, and large language model (LLM) integrations to make smarter use of their data in real time. Whether that means enhancing engagement, simplifying decision-making, or enabling more efficient processes, MongoDB is helping organizations redefine how they leverage AI to solve critical challenges and create lasting impact. In this issue, I’m particularly excited to share the highlight of an impactful platform developed by CentralReach in the Autism care space – a cause near and dear to my family. They, along with customers like the Financial Times, Ubuy, and Base39, are demonstrating AI’s possibilities and transforming how data powers success. Ubuy Ubuy , an e-commerce platform serving customers in over 180 countries, needed a faster, more scalable solution to manage its catalog of over 300 million products. They were facing significant search performance bottlenecks, which impacted user experience and limited growth potential. By migrating from MySQL to MongoDB Atlas and leveraging Atlas Search and Atlas Vector Search , Ubuy reduced search response times from 4–5 seconds to milliseconds and enabled intent-driven product discovery powered by AI. Now, Ubuy easily handles over 150 million searches annually while delivering personalized recommendations and seamless scalability. AI-driven search enhancements have boosted customer engagement and SEO visibility, transforming global e-commerce and redefining how Ubuy customers access international products. Financial Times The Financial Times (FT) , a global leader in business journalism, wanted to deliver a hybrid search experience that combined traditional keyword precision with AI-driven discovery. With over a million daily searches, scaling this innovative solution quickly was critical. Using MongoDB Atlas—including Atlas Vector Search—the FT developed its AI-powered hybrid search in just 18 weeks. By blending full-text and semantic search capabilities, the solution delivers relevant recommendations instantly, enhancing content discovery for time-strapped readers. Partnering with MongoDB streamlined deployment, enabling the FT to surface hyper-relevant results while positioning itself as a leader in media innovation. With plans to roll out hybrid search across mobile apps and specialist titles next, the FT continues redefining how readers engage with trusted journalism in an AI-enabled world. Through our partnership with The Stack, learn how our customers are achieving extraordinary results with MongoDB. This exclusive content could spark the insights you need to drive your business forward. CentralReach CentralReach , a global leader in autism and intellectual and developmental disability (IDD) care technology, faced the challenge of managing 4 billion clinical data points annually while reducing administrative burdens for behavioral analysts. By building its Care360 platform on MongoDB Atlas and joining the MongoDB AI Applications Program (MAAP), CentralReach unified data across 62 million service appointments per year. With flexible document modeling, vector search, and advanced AI pipelines, the platform enables seamless access to patient records and intelligent querying, reducing manual workflows and improving care consistency. CentralReach’s AI-powered solution has streamlined processes, reduced documentation errors, and helped expand access to care for hundreds of thousands globally. With MongoDB Atlas’s scalability and powerful AI integrations, CentralReach is redefining autism care delivery. Base39 Base39 , a Brazil-based fintech, set out to streamline complex credit analysis using AI-driven insights. Manual processes and data scarcity limited efficiency and accuracy, often delaying loan assessments by up to 10 days. By leveraging MongoDB Atlas on AWS , as well as Atlas Vector Search and LLM integrations, Base39 transformed its workflow. With agentic AI and predictive algorithms, loan applications are now assessed in minutes, achieving 96% cost reductions and improved data insights. MongoDB’s flexible schema and native vector search capabilities helped boost productivity while cutting infrastructure costs by 84%. By empowering developers to focus on innovation instead of management, Base39 has set a new standard in AI-powered credit analysis. Video spotlight: Cisco Before you go, check out how Cisco is redefining innovation with generative AI while prioritizing security. Omar Santos, Distinguished Engineer at Cisco, shares how MongoDB Atlas Vector Search accelerated development and saved millions through smarter, safer AI applications. Want to get inspired by your peers and discover all the ways we empower businesses to innovate for the future? Visit MongoDB’s Customer Success Stories hub to see why these customers, and so many more, build modern applications with MongoDB.

July 17, 2025