What is full-text search and how does it work?

AI-powered search: What you need to know [2025]

The 10 best AI enterprise search tools and platforms [2025]

We're excited to announce the release of Meilisearch v1.14.  In this article, we'll highlight the key changes and improvements in this release.

For a complete list of all updates and fixes, please visit the [changelog](https://github.com/meilisearch/meilisearch/releases/tag/v1.14.0) on GitHub.


<Callout intent="tip">

These powerful new features are coming soon to [Meilisearch Cloud](https://cloud.meilisearch.com/?utm_campaign=release-v1-14&utm_source=blog). Sign up now to be among the first to experience the latest improvements!

</Callout>


## New: granular filterable attributes settings

With Meilisearch v1.14, you can configure filterable attributes using an [advanced object format](https://www.meilisearch.com/docs/reference/api/settings#filterable-attribute-object) that lets you specify exactly which filtering features to enable for each attribute pattern:

```json
{
	"filterableAttributes": [
	  {
	    "attributePatterns": ["genre", "artist"], 
	    "features": { "facetSearch": true, "filter": {"equality": true, "comparison": false } }
	  },
	  {
	    "attributePatterns": ["*rank"],
	    "features": { "facetSearch": false, "filter": {"equality": true, "comparison": true } }
	  },
	  {
	    "attributePatterns": ["albumId"],
	    "features": { "facetSearch": false, "filter": {"equality": true, "comparison": false } }
	  },
	]
}
```

* **String attributes** (e.g., `genre`, `artist`): enable facet search and equality operators (`=` / `!=`) for categorical filtering, while disabling comparison operators (`>`, `<`, `>=`, `<=`), which are unnecessary for string values.
* **Numeric attributes** (e.g., `*rank`): enable comparison operators (`>`, `<`, `>=`, `<=`) for range filtering, while disabling facet search, as it's not relevant for numerical data.
* **Unique identifiers** (e.g., `albumId`): enable equality operators for exact matching, while disabling unused features such as comparison operators and facet search.

This targeted configuration can notably boost indexing performance. 

## Experimental: composite embedders

Meilisearch 1.14 introduces a new experimental feature that lets you use [different embedders at search and indexing time](https://www.meilisearch.com/docs/reference/api/settings#indexingembedder-and-searchembedder), allowing you to optimize for both throughput and latency.
* Use a remote embedder for indexing in bulk, as remote embedders provide the highest bandwidth (embeddings/s)
* Use a local embedder for answering search queries, as local embedders provide the lowest latency (time to first embedding)

Configure your embedders using the new `composite` [source type](https://www.meilisearch.com/docs/reference/api/settings#source). For instance, you can combine a local Hugging Face model for fast search with a remote inference endpoint for efficient indexing:

```json
{
    "embedders": {
        "text": {
            "source": "composite",
            "searchEmbedder": {
                "source": "huggingFace", // locally computed embeddings using a model from the Hugging Face Hub
                "model": "baai/bge-base-en-v1.5",
                "revision": "a5beb1e3e68b9ab74eb54cfd186867f64f240e1a"
            },
            "indexingEmbedder": {
                "source": "rest", // remotely computed embeddings using Hugging Face inference endpoints
                "url": "https://URL.endpoints.huggingface.cloud",
                "apiKey": "hf_XXXXXXX",
                "documentTemplate": "Your {{doc.template}}",
                "request": {
                    "inputs": [
                        "{{text}}",
                        "{{..}}"
                    ]
                },
                "response": [
                    "{{embedding}}",
                    "{{..}}"
                ]
            }
        }
    }
}
```

Meilisearch automatically selects the appropriate embedder based on the current operation.

Activate this feature in your project overview by checking the "Composite embedders" box under "Experimental features". If you are self-hosting Meilisearch, [enable it](https://www.meilisearch.com/docs/reference/api/experimental_features) via the `/experimental-features` route. 

## Experimental: cache embeddings

Meilisearch 1.14 brings a new experimental feature that allows you to [cache search query embeddings](https://www.meilisearch.com/docs/learn/self_hosted/configure_meilisearch_at_launch#search-query-embedding-cache), significantly improving performance when the same query is run multiple times.

To enable the search query embedding cache, launch Meilisearch with either instance option specifying the maximum number of entries to store in the cache:
* the `--experimental-embedding-cache-entries=150` flag
* the `MEILI_EXPERIMENTAL_EMBEDDING_CACHE_ENTRIES=150` environment variable

When enabled, Meilisearch stores the embedding vectors for search queries, eliminating the need to repeatedly generate embeddings for identical queries. This is particularly valuable in scenarios where:

* The same queries are frequently repeated
* You're using multi-search across multiple indexes
* You've implemented local sharding where identical queries are sent to different indexes

## New: get documents by id

You can now [get a set of documents by their primary keys](https://www.meilisearch.com/docs/reference/api/documents#get-documents-with-post):

```json
// POST /indexes/INDEX_UID/documents/fetch
{
    "ids": [785084, 44214, 473],
}
```

The above query will return the corresponding documents:

```json
{
    "results": [
        {
            "id": 44214,
            "title": "Black Swan"
        },
        {
            "id": 473,
            "title": "Pi"
        },
        {
            "id": 785084,
            "title": "The Whale"
        }
    ],
    "offset": 0,
    "limit": 20,
    "total": 3
}
```

## Contributors shout-out

We want to give a massive thank you to the contributors who made this release possible. Special thanks to [@MichaScant](https://github.com/MichaScant) for their work on [Meilisearch](https://github.com/meilisearch/meilisearch), [@oXtxNt9U](https://github.com/oXtxNt9U) for contributions to [Heed](https://github.com/meilisearch/heed), [@ptondereau](https://github.com/ptondereau) for efforts on [Arroy](https://github.com/meilisearch/arroy), and both [@NarHakobyan](https://github.com/NarHakobyan) and [@mosuka](https://github.com/mosuka) for their contributions to [Charabia](https://github.com/meilisearch/charabia). We’re deeply grateful for your support and collaboration.

---

And that’s a wrap for v1.14! These release notes only highlight the most significant updates. For an exhaustive listing, read the [changelog](https://github.com/meilisearch/meilisearch/releases/tag/v1.14.0) on GitHub.

---

For more information, subscribe to our [monthly newsletter](https://dub.sh/meili-newsletter?utm_campaign=release-v1-14&utm_source=blog), or join our [Product Discussions](https://github.com/orgs/meilisearch/discussions).

For anything else, join our developers community on [Discord](https://discord.meilisearch.com/?utm_campaign=release-v1-14&utm_source=blog).

Meilisearch 1.14

Top 10 Elasticsearch alternatives and competitors in 2025

Spending hours digging through data, only to find irrelevant or incomplete information, is a productivity nightmare.

**Intelligent search is revolutionizing how we navigate digital information**. It transforms frustrating searches into fast, precise discoveries. Intelligent search understands not just your words, but your intent.

By leveraging artificial intelligence and advanced machine learning, intelligent search is more than a technological upgrade. **It's a solution that turns information overload into instant, meaningful insights**.

## Understanding intelligent search

The way we find information online is changing significantly. **Search engines no longer simply match keywords to deliver results.** Today's intelligent search systems use artificial intelligence to understand the deeper meaning behind our queries. They deliver precisely what we need, even when we're not sure how to ask for it.

### What is intelligent search?

Intelligent search is a major advancement over conventional search methods. Traditional search engines rely on exact keyword matching. For example, they find "red shoes" only when those exact words appear. **Intelligent search, however, understands context and intent.**

It can recognize that someone searching for "comfortable footwear for running" might be interested in athletic shoes, even if they don't use those specific terms. This contextual understanding makes intelligent search more intuitive. It also makes it more human-like in its ability to interpret and respond to queries.

### Key components of intelligent search

Intelligent search relies on three fundamental technologies working together:

- **Natural Language Processing (NLP):** Helps systems understand human language in all its complexity, including colloquialisms, misspellings, and context.
- **Machine learning algorithms:** Continuously improve search accuracy by learning from user interactions and feedback.
- [**Semantic analysis**](https://meilisearch.com/blog/semantic-search)**:** Goes beyond surface-level word matching to understand the relationships between concepts. This ensures that searches return relevant results even when query terms don't exactly match the content.

### How intelligent search improves user intent understanding

Understanding user intent is perhaps the most powerful aspect of intelligent search.

When someone types "best pizza near me open now," the system doesn't just look for those exact words. **It understands that the user wants currently open restaurants serving pizza in their geographic area, likely with good reviews.**

This intent recognition extends to professional contexts too. For instance, when an employee searches for "quarterly reports," the system might prioritize recent financial documents while considering the user's role and access permissions.

This contextual awareness makes intelligent search particularly valuable for both consumer applications and enterprise knowledge management.

Modern intelligent search bridges the gap between what users say and what they actually need. By combining advanced technologies with an understanding of human behavior, these systems are making information retrieval more natural and efficient than ever before.

## How intelligent search works

Intelligent search now uses AI and machine learning to understand information like humans do, transforming raw data into meaningful insights.

### Ingesting and connecting data sources for unified search

Creating a unified search experience starts with [connecting multiple data sources](https://meilisearch.com/blog/what-is-federated-search). These sources can include structured databases, unstructured documents, emails, and multimedia content.

Think of it as building a digital library. **Every piece of information, regardless of its format or location, becomes easily accessible through a single search interface.**

For example, imagine a sales manager searching for the most effective sales strategies in the past quarter. The system could analyze sales reports, CRM data, and even transcripts of successful sales calls to identify winning patterns. This gives the manager actionable insights to share with their team.

![enterprise search](https://unable-actionable-car.media.strapiapp.com/enterprise_search_0a1a2e0746.avif)

### Indexing and enriching content for better search outcomes

The real power of intelligent search happens during the indexing phase. This is where raw content transforms into searchable information. This process goes far beyond simple keyword cataloging.

**Modern systems analyze documents for context, extract entities, identify relationships, and create semantic connections between different pieces of content.**

For instance, imagine indexing a technical article about "python programming". The system automatically recognizes that this content relates to both computer programming and the Python language. It creates connections to related topics like "software development," "coding tutorials," or "debugging techniques".

This enrichment process makes search results more relevant and comprehensive. It helps users discover related information they might not have explicitly searched for.

<Callout intent="note">

Curious about how intelligent search systems handle complex relationships in data? Dive deeper into the role of [vector embeddings](https://meilisearch.com/blog/what-are-vector-embeddings)—the backbone of modern semantic search. It explains how these numerical representations help capture the true meaning and context of data, making search systems smarter and more intuitive.
	
</Callout>

### Leveraging NLP to understand user intent and context

NLP serves as the bridge between human communication and machine understanding. When someone types "how do I reset my password," the system doesn't just look for those exact words. **It understands the intent behind the query and recognizes this as a how-to request related to account security.** It can then provide relevant solutions, even if they're worded differently in the knowledge base.

This capability becomes particularly powerful when users don't know the exact terminology for what they're seeking. For example, a customer searching for "phone won't turn on" might receive results about "device power cycling," "battery replacement," and "hardware troubleshooting." These are all relevant solutions that might not share the exact keywords but address the underlying problem.

### Delivering personalized and relevant results

The final piece of the intelligent search puzzle involves delivering results that are not just accurate but [personally relevant](https://www.meilisearch.com/blog/personalization-recommendations) to each user. This process combines several factors:

- User context (location, department, role, previous searches)
- Behavioral data (which results similar users found helpful)
- Content popularity and freshness
- Access permissions and security constraints

For example, imagine two different employees searching for "quarterly reports." A sales manager might see financial performance metrics first. A marketing director might see campaign performance data. **This personalization happens in real-time, creating a more efficient and satisfying search experience.**

## Benefits of intelligent search

[AI-powered search](https://meilisearch.com/blog/ai-powered-search) has transformed information interaction, offering significant advantages over keyword-based systems. Its value is increasingly clear for businesses managing growing digital environments.

### Faster and more accurate information retrieval

Gone are the days of scrolling through endless pages of irrelevant results. Modern intelligent search systems cut through the noise, understanding context and intent to deliver precisely what users need.

![Encrypt emails search results](https://unable-actionable-car.media.strapiapp.com/Encrypt_emails_search_results_c261bc76d1.avif "Example of the Symfony search when they moved to Meilisearch")

For example, when an employee searches for "quarterly marketing budget template 2025", the system recognizes not just the keywords. **It understands they likely want the most recent template, not historical versions or related documents.**

### Enhanced decision-making through better insights

Intelligent search doesn't just find information. **It connects dots across disparate data sources to surface meaningful insights.**

When a sales representative searches for information about a client, the system pulls together recent interactions, contract details, support tickets, and market intelligence into a coherent narrative. This comprehensive view enables faster, more informed decisions.

### Delivering personalized customer experiences at scale

Perhaps the most visible benefit of intelligent search is its ability to transform customer experiences. Ecommerce platforms using intelligent search have seen conversion rates increase significantly. For instance, Bookshop.org, an online bookstore, [**increased overall conversion by 43%**](https://www.meilisearch.com/blog/bookshop-increases-search-based-purchases) by delivering relevant search results.

The real power of intelligent search comes from its ability — and from the people responsible of it — to learn and improve over time.

<Callout intent="tip">

Ready to supercharge your search experience? Deliver lightning-fast search results that will keep your users engaged and boost your conversion rates.
[Explore Meilisearch Cloud](https://meilisearch.com/cloud)

</Callout>

## Intelligent search use cases and applications

Intelligent search is now widely adopted across industries due to its versatility. It transforms how organizations and users interact with information, streamlining operations, enhancing customer experiences, and revolutionizing data retrieval and decision-making.

### Enterprise knowledge management and operational efficiency

Organizations often struggle with scattered information across multiple systems. This makes it challenging for employees to quickly find crucial documents. **Intelligent [enterprise search](https://meilisearch.com/blog/enterprise-search) unifies data sources to deliver relevant information instantly.**

### Ecommerce and personalized customer support

In ecommerce, intelligent search has become a crucial differentiator for businesses seeking to provide seamless shopping experiences. Modern search solutions can process natural language queries like "comfortable running shoes under $100".

They understand not just the price constraint but also the implied comfort requirement. This capability extends to customer support, where AI-powered search helps service representatives quickly access relevant information.

### SaaS platform efficiency

SaaS companies also benefit significantly from intelligent search. By integrating AI-powered search into their platforms, SaaS providers enable users to quickly find relevant features, documentation, or support resources within the application. This reduces user frustration, improves onboarding, and increases overall user satisfaction.

![Example Intelligent Search Huggingface](https://unable-actionable-car.media.strapiapp.com/Example_Intelligent_Search_Huggingface_bad47d2ffb.gif)

[Hugging Face uses Meilisearch](https://meilisearch.com/blog/hugging-face-democratizes-ai) to improve AI model discovery. This integration allows developers and researchers to effectively search over 300,000 AI models, datasets, and demos. By leveraging model card metadata, the enhanced search delivers relevant results even with typos or incomplete queries, increasing AI accessibility.

### Social and visual search: adapting to new user behaviors

The rise of social media has fundamentally changed how people search for information. [45% of Gen Z users](https://nypost.com/2024/09/12/tech/gen-z-ditches-google-for-this-next-most-popular-search-engine/) now turn to platforms like TikTok or Instagram as their primary search engines, particularly for discovery-oriented queries.

This shift has prompted businesses to adapt their search strategies, incorporating visual elements and social proof into their search experiences. Visual search capabilities now allow users to find products by uploading images. Social signals help rank results based on user engagement and relevance.

## Implementing intelligent search: a practical guide

Implementing intelligent search requires careful planning and execution. This ensures it delivers value while minimizing disruption. **Whether you're a large enterprise or a growing business, the key is to approach implementation systematically while keeping your specific needs and resources in mind.**

### Choosing the right search solution

The success of your intelligent search implementation hinges on choosing the right solution for your specific needs. While [Elasticsearch](https://meilisearch.com/blog/meilisearch-vs-elasticsearch) offers comprehensive capabilities for complex data analysis and distributed search, Meilisearch provides lightning-fast search with excellent relevancy out of the box. **Consider your data volume, search complexity, and technical expertise when making this decision.**

Key factors to evaluate include:

- Search relevancy requirements and ranking capabilities
- Integration complexity and API flexibility
- Scalability needs and performance expectations
- Security features and compliance requirements
- Total cost of ownership, including maintenance and hosting

<Callout intent="tip">
	
If you're running an ecommerce site handling thousands of product searches daily, you'll need robust typo tolerance and filtering capabilities. However, if you're implementing search for an internal knowledge base, features like document parsing and metadata extraction might be more critical.
	
</Callout>

### Measuring return on investment

To justify the investment in intelligent search, establish clear metrics aligned with your business objectives. **Track both quantitative and qualitative measures to get a complete picture of the implementation's impact.**

Key metrics to monitor:

- Average time to find information
- Search success rate and abandonment rate
- User satisfaction scores
- Support ticket reduction
- Employee productivity gains
- Revenue impact for customer-facing search

For instance, a manufacturing company implementing intelligent search might track how quickly employees can locate technical documentation. An online retailer might focus on conversion rates from search results to purchases.

### Cost-effective adoption strategies

Small businesses can implement intelligent search without overspending by taking a strategic approach. Start with essential features and scale up as needed. **Open-source solutions like MeiliSearch offer a cost-effective entry point with the flexibility to grow.**

<Callout intent="note">
	
You can easily deploy MeiliSearch on your own infrastructure, even on your local computer, to experiment and test its capabilities before committing to a full-scale implementation.
		
</Callout>

### Success metrics and optimization

To maintain consistently effective search functionality, continuous monitoring and optimization are paramount. Regularly analyzing search patterns and user behavior allows us to pinpoint areas ripe for enhancement. Key metrics to track in this process include:

- Query patterns and popular search terms
- Zero-result searches and failed queries
- Click-through rates on search results
- Time spent on search results pages
- User feedback and satisfaction scores

Use these insights to refine your search algorithms, update relevance settings, and enhance the user experience.

For example, if users frequently search for synonyms of common terms, update your [synonym lists](https://www.meilisearch.com/docs/learn/relevancy/synonyms) accordingly. If certain searches consistently yield no results, consider adding content to address these gaps or adjusting your ranking parameters. Use an [analytics solution](https://www.meilisearch.com/docs/learn/analytics/analytics) to make sure to capture all this data.

## The future of finding: intelligent search as a transformative technology

Intelligent search is more than just a technological upgrade; it's a fundamental **change in how we discover and interact with information**.

These advanced search systems seamlessly blend AI, NLP, and ML. This is revolutionizing user experiences across industries, from ecommerce and SaaS to enterprise knowledge management.

As technology evolves, **intelligent search will be essential in making information retrieval more intuitive, personalized, and efficient**, helping users and organizations easily find information.



Intelligent search: the future of finding relevant results

Our Product Hunt launch made it to the monthly Top 5 in the UX category 🔥

[![Meilisearch is #5 Product of the Month in User Experience](https://unable-actionable-car.media.strapiapp.com/PH_top_5_1_864dcb16f7.png)](https://www.producthunt.com/posts/meilisearch-ai)

## 🚀 Meilisearch AI launch week

[![Meilisearch AI: semantic and hybrid search in GA!](https://unable-actionable-car.media.strapiapp.com/Day_0_0c60c1ece6.png)](https://www.meilisearch.com/blog/launch-week-1)

We organized a Launch Week to celebrate the stabilization of AI-powered search. Read the day-by-day recap of our releases.

[Read the recap](https://www.meilisearch.com/blog/launch-week-1)

## 🔮 Building the future of search

[![Building the future of search with Meilisearch AI](https://unable-actionable-car.media.strapiapp.com/Building_the_future_of_search_with_Meilisearch_AI_e75f1ae673.png)](https://www.meilisearch.com/blog/introducing-meilisearch-ai)

We're transforming how developers build search with Meilisearch AI. No more complex infrastructure—just powerful, intelligent search that works out of the box.

[Learn more](https://www.meilisearch.com/blog/introducing-meilisearch-ai)

## 📰 In the news

### 🔢 What are vector embeddings?

We updated our guide about everything you need to know about using embeddings.

[Read the guide](https://www.meilisearch.com/blog/what-are-vector-embeddings)

### 🛍️ Scaling to billions: how Agora elevates e-commerce search with AI search

Learn how Agora leverages hybrid search across millions of ecommerce products.

[Read the case study](https://www.meilisearch.com/blog/Agora)

### 📐 Rayon chose Meilisearch to help facilitate seamless search UX

Leveraging semantic search to build a platform for architecture and interior design.

[Read the case study](https://www.meilisearch.com/blog/Rayon)

### 🔍 MotionElements: AI-powered discovery for video creators

Read how Meilisearch improved search performance, accuracy, and engagement.

[Read the case study](https://www.meilisearch.com/blog/motionelements)

### 📊 How to choose the best model for semantic search

Compare model performance, cost, and relevancy to build semantic search.

[Read the guide](https://www.meilisearch.com/blog/choosing-the-best-model-for-semantic-search)

## 🤗 Made with Meilisearch

Meilisearch [ecommerce demo](https://ecommerce.meilisearch.com/?utm_campaign=newsletter&utm_source=blog&utm_medium=march-25-updates) is an open-source Nuxt 3 application implementing filters, sorting, facet search, and more to power search across 45k documents.

[![Scrolling on the ecommerce demo](https://unable-actionable-car.media.strapiapp.com/ecommerce_demo_scroll_bc09f703ae.gif)](https://ecommerce.meilisearch.com/?utm_campaign=newsletter&utm_source=blog&utm_medium=march-25-updates)

_We’re always looking to promote new projects from the community. Post yours in the [#built-with-meilisearch](https://dub.sh/meili-discord?utm_campaign=newsletter&utm_source=blog&utm_medium=march-25-updates) Discord channel!_

---

Stay in the loop of everything Meilisearch by subscribing to our [monthly newsletter](https://dub.sh/meili-newsletter?utm_campaign=newsletter&utm_source=blog&utm_medium=march-25-updates). To learn more about Meilisearch's future and help shape it, take a look at our [roadmap](https://roadmap.meilisearch.com/?utm_campaign=newsletter&utm_source=blog&utm_medium=march-25-updates) and participate in our [Product Discussions](https://github.com/orgs/meilisearch/discussions).

For anything else, join our developers community on [Discord](https://dub.sh/meili-discord?utm_campaign=newsletter&utm_source=blog&utm_medium=march-25-updates).

Meilisearch March updates

10 Best Typesense alternatives: Full comparison [2025]

Imagine searching billions of images, documents, or products and finding exactly what you need in milliseconds. **Similarity search makes this possible, transforming how we interact with massive, complex datasets.**

It doesn't rely on matching exact words. Instead, it understands the deeper meaning behind your query.

This technology translates abstract concepts into mathematical representations. Computers can then instantly compare and retrieve these representations. From recommendation engines to medical research, this technique is reshaping how machines understand and navigate information with unprecedented precision and speed.

## Understanding similarity search

When you search for "black leather boots" on an e-commerce website or look for "songs that sound like Taylor Swift" on a music platform, **you're using similarity search without even knowing it.** At its core, similarity search helps find items that are alike.

### What is similarity search and why is it important?

Think of similarity search as a smart librarian. This librarian doesn't just look at book titles, but understands what each book is about. When you ask for "books like Harry Potter," this librarian knows to recommend other fantasy novels.

These novels would have coming-of-age stories and magical schools. **This is exactly what similarity search does – it understands the essence of what you're looking for and finds items that match that essence.**

### How similarity search works with vector embeddings

To understand how computers can find similar items, imagine turning everything into a list of numbers. When you take a photo, write a sentence, or record a song, similarity search converts it into a special list of numbers. This list is called a [vector embedding](https://meilisearch.com/blog/what-are-vector-embeddings).

**These numbers capture the important features of the item.** For a photo, it might include information about colors, shapes, and objects present.

Think of these vectors like coordinates on a map. You can find nearby cities by looking at their location on a map. **Similarity search finds similar items by looking at how close their vectors are to each other.** Items that are similar will have vectors that are close together in this mathematical space.

### Key differences between similarity search and nearest neighbor search

While these terms are often used interchangeably, they serve slightly different purposes. Nearest neighbor search is like using a measuring tape to find the closest points to where you're standing. **It's precise but can be slow if you have to measure the distance to every single point.**

Similarity search, on the other hand, is more like asking for directions. It might not give you the absolute closest match, but it's faster and usually good enough.

### What is the role of similarity search in AI-driven applications?

AI applications rely heavily on similarity search to make sense of vast amounts of information. When you use a chatbot that answers your questions, it's likely using similarity search to find relevant information in its knowledge base.

<Callout intent="note">
	
Curious about how to implement similarity search in a real application? Learn [how to build a RAG system with similarity search](https://www.meilisearch.com/blog/how-to-build-rag) to enhance your AI applications.
	
</Callout>

## Real-world applications of similarity search

Similarity search has changed how we interact with digital content. It powers many features we use daily. Let's explore some practical applications that showcase its impact across different domains.

### Content-based retrieval in multimedia systems

When you upload a photo to Google Images and ask "find similar images", you're experiencing content-based retrieval.

Pinterest, for instance, uses this technology to help users discover visually similar pins. If you find a cozy living room design you like, the platform can instantly show you dozens of similar interior designs by comparing their visual embeddings.

![Green kitchen cabinets interior design](https://unable-actionable-car.media.strapiapp.com/Green_kitchen_cabinets_interior_design_980c857e9b.avif)

These systems break down images and videos into vector embeddings that capture visual elements like colors, shapes, and patterns.

### Making recommendations more personal and accurate

Recommendation systems have come a long way from simple "users who bought X also bought Y" suggestions. **Modern platforms use similarity search to create rich, personalized experiences.**

Take Spotify's Discover Weekly playlist. It combines your listening history, favorite genres, and even the acoustic properties of songs you love to recommend new music you're likely to enjoy.

![Spotify Discover Weekly ad](https://unable-actionable-car.media.strapiapp.com/Spotify_Discover_Weekly_ad_46d6a0219c.avif)

E-commerce sites like Amazon use multi-modal similarity, combining different types of data to improve recommendations. They might consider:

- Product descriptions and reviews (text data)
- Product images (visual data)
- Purchase patterns (behavioral data)
- Price ranges and categories (numerical and categorical data)

By analyzing all these dimensions together, they can suggest products that truly match what you're looking for, rather than just showing popular items in the same category. **This creates a better experience for the user.**

### Real success stories from the field

Similarity search in healthcare, beyond imaging, aids diagnosis. Hospital systems use it to match patients with similar symptoms and histories by vectorizing patient data.

[Research shows its utility in predictive analytics](https://pmc.ncbi.nlm.nih.gov/articles/PMC5357318/), improving accuracy in areas like diabetes prediction. This supports personalized treatment and outcome prediction for more effective care.

### Powering modern AI applications

The rise of LLM and retrieval-augmented generation (RAG) systems has created new applications for similarity search. When you chat with an AI assistant that needs to pull relevant information from a knowledge base, similarity search is working behind the scenes to find the most relevant content to inform its responses. **This is a game changer for AI applications.**

![RAG workflow diagram explanation](https://unable-actionable-car.media.strapiapp.com/RAG_workflow_diagram_explanation_53f23eb06c.avif)

For example, when a customer service chatbot needs to answer a specific question about a product, it uses similarity search to find the most relevant product documentation, support tickets, and FAQ entries. This helps the bot provide accurate, contextual responses rather than generic answers.

## Distance metrics: the heart of similarity search

When searching for similar items, we need a way to measure how close or far apart vectors are from each other. This is like using a ruler to measure physical distances.

### Understanding the main distance metrics

The choice of distance metric can make or break your similarity search. Think of it like choosing the right tool for the job. You wouldn't use a hammer to cut wood, right? **The three most popular distance metrics each have their sweet spots.**

![Euclidean distance diagram](https://unable-actionable-car.media.strapiapp.com/Euclidean_distance_diagram_e711c166fc.avif)

Euclidean distance works like a straight line between two points. It's the distance "as the crow flies". This metric shines when working with physical measurements or when the magnitude of your vectors matters. For example, if you're building a system to find similar house prices, Euclidean distance would be a great choice because the actual numerical differences matter.

![Cosines distance illustration](https://unable-actionable-car.media.strapiapp.com/Cosines_distance_illustration_f59696183b.avif)

Cosine similarity, on the other hand, cares about the angle between vectors, not their length. It's perfect for text search because it can tell if two documents are about the same topic even if one is much longer than the other. It helps deliver more relevant results regardless of text length.

![Manhattan distance L1 distance](https://unable-actionable-car.media.strapiapp.com/Manhattan_distance_L1_distance_828cda7a2a.avif)

Manhattan distance (also called L1 distance) measures distance as if you're walking through city blocks. You can only move horizontally or vertically. It's particularly useful when dealing with grid-like data or when you want to give equal weight to all differences between vectors.

### Choosing the right metric for your data

| Metric | Use Case | Key Benefit |
| --- | --- | --- |
| Cosine Similarity | Text Search | Handles varying document lengths; focuses on meaning. |
| Euclidean Distance | Image Search, Sensor Data | Measures numerical differences; scale is meaningful. |
| Manhattan Distance | Categorical Data (User Preferences, etc.) | Treats each dimension independently; robust to outliers in features. |

Here's a practical way to think about it.

For text search, cosine similarity is usually your best bet. It handles documents of different lengths well and focuses on the meaning rather than the size. This is especially important when searching through articles, product descriptions, or user queries.

For image search, Euclidean distance often works better because the actual numerical differences between pixel values or image features matter. The same goes for sensor data or any numerical measurements where the scale is meaningful.

For categorical data (like user preferences or product attributes), Manhattan distance can be more appropriate. It treats each dimension independently and doesn't get thrown off by large differences in individual features.

### Handling mixed data types

Real-world applications often deal with multiple types of data at once. For instance, an e-commerce search might need to consider both product descriptions (text) and product images. **In these cases, you can use hybrid approaches.**

1. Calculate similarities separately using appropriate metrics for each data type
2. Combine the results using weighted averages
3. Normalize the scores to ensure fair comparison

This flexible approach allows you to fine-tune the importance of different features. You might want product images to carry more weight than text descriptions when searching for clothing items.

### Impact on search performance

The choice of distance metric doesn't just affect accuracy. **It can significantly impact search speed too.** Euclidean and Manhattan distances are generally faster to compute than cosine similarity, but modern search engines like Meilisearch optimize these calculations so you rarely need to worry about performance differences.

What matters more is choosing a metric that matches your data and use case. A faster metric that gives less relevant results isn't a good trade-off. Focus first on what makes sense for your users and their search needs, then optimize for performance if necessary.

## Algorithms that power similarity search

Now we understand how distance metrics help measure similarity between vectors. Let's then explore the algorithms that make searching through these vectors efficient and scalable. They are specifically designed to handle vector-based searches while balancing speed and accuracy requirements.

Different search algorithms handle distance calculations in various ways - some compare against every vector for perfect accuracy, while others use clever shortcuts to speed up the process. The choice of algorithm often depends on your dataset size, the dimensionality of your vectors, and whether you need exact or approximate results.

Let's examine the main approaches to similarity search, from basic exact matching to sophisticated approximate methods.

### Exact vs. approximate: finding the best match

![](https://unable-actionable-car.media.strapiapp.com/knn_algorithm_illustration_4f027a5683.avif)

The k-Nearest Neighbors (k-NN) algorithm finds the *exact* closest matches. It compares your search to every single item. While accurate, this is slow with large datasets. **k-NN isn't practical when speed is important.** Imagine comparing one book to millions!

![ANN algorithm illustration](https://unable-actionable-car.media.strapiapp.com/ANN_algorithm_illustration_ad3c4df68e.avif)

Approximate Nearest Neighbors (ANN) algorithms are a faster alternative. They make educated guesses to find good matches quickly. **ANN might miss the *absolute* best match sometimes, but it's much faster and accurate enough for most uses.**

### Space partitioning and graph navigation

Space partitioning methods, like KD-trees and Voronoi diagrams, organize data for faster searching. KD-trees divide the search space into smaller regions. Voronoi diagrams divide space based on proximity to certain points. **These are good for simpler data, but less useful with complex, high-dimensional data.**

[Hierarchical Navigable Small World](https://en.wikipedia.org/wiki/Hierarchical_navigable_small_world) (HNSW) is a cutting-edge algorithm for similarity search. It creates a network of connections between data points. **HNSW is great for complex data used in modern AI.** It can search millions of items quickly while providing relevant results, ideal for things like [semantic search](https://meilisearch.com/blog/semantic-search) and [recommendation systems](https://meilisearch.com/blog/personalization-recommendations).

## The future of search: embracing semantic intelligence

Similarity search is transforming information retrieval by connecting traditional methods with advanced semantic understanding.

**This technology uses vector embeddings and sophisticated algorithms for more intelligent, context-aware search experiences.** As AI evolves, similarity search will be essential in making search more intuitive, precise, and meaningful across many domains and applications.



Similarity search: a guide to vector-based retrieval  

# Meilisearch AI launch week recap

As the first quarter of 2025 closes, we've completed our first [Meilisearch launch week](https://www.meilisearch.com/launch-week), marking our most significant product evolution since introducing Meilisearch Cloud. This update brings comprehensive AI-powered search capabilities to all users.

Traditional keyword search has limits. It matches characters, not intent—often returning results that miss the mark. [AI-powered search changes that](https://www.meilisearch.com/blog/introducing-meilisearch-ai). By understanding meaning, not just words, it delivers smarter, more intuitive results.

## What we announced: Day by day

#### Day 1: Semantic and hybrid search now GA

We kicked off the week by announcing that our AI capabilities, including semantic search and hybrid search, are now generally available:

- **Semantic search**: AI-powered understanding delivers more relevant results beyond simple keyword matching
- **Hybrid search**: Combines traditional full-text reliability with semantic intelligence
- **Performance optimization**: All this intelligence with sub-50ms response time

We launched semantic and hybrid search as generally available on the Meilisearch platform. Now your search results understand context, personalize experiences, and power better recommendations, whether you're building an e-commerce site, a knowledge base, a media and news archive, or a SaaS app.

These capabilities significantly reduce failed searches and "no results" responses. [E-commerce platforms report higher conversion rates](https://www.meilisearch.com/blog/Agora) as shoppers find products using natural language, while [app builders](https://www.meilisearch.com/blog) see increased engagement as users discover precisely what they need, even with imprecise queries.

**📹 [Watch our Head of Product, Guillaume, explain the release](https://www.youtube.com/watch?v=3JaDBEQNLZc&t).**


#### Day 2: Multiple embedder options and vector storage

On day two, we made vector search more flexible with multiple embedder choices—eliminating the need for separate vector database infrastructure:

- **Choose your embedder**: OpenAI, Hugging Face, Ollama, or bring your own
- **documentTemplate feature**: Better prompting for improved results
- **Binary quantization**: Optimize large databases for speed while maintaining result quality

Our flexible embedder options address critical infrastructure and cost concerns. Organizations can choose solutions that balance budget constraints, performance requirements, and proprietary needs. This approach eliminates the expense of maintaining separate vector databases and reduces operational complexity.

**📹 [Watch the walkthrough – Our Sr. Product Manager, María, explains embedders and best practices.](https://youtu.be/0tPsBrmtf3o?si=6KAyuREv0DYVfCZD).**


#### Day 3: Multi-modal search capabilities

The middle of the week brought multi-modal search, allowing searches beyond just text. This opens new possibilities for industries with diverse content types:

- **Flexible input types**: Search across text, images, and more
- **AI-powered semantics**: Smarter results across content types
- **Real-world implementations**: learn more about how early adopters like [Agora](https://www.meilisearch.com/blog/Agora) and [MotionElements](https://www.meilisearch.com/blog/motionelements) already using these capabilities
    
    ![MotionElements_multimodal.gif](https://unable-actionable-car.media.strapiapp.com/Motion_Elements_multimodal_6cfa386d8d.gif)

#### Day 4: Personalized recommendations

Thursday's focus was on helping users discover relevant content faster:

- **/SIMILAR documents**: Find content similar to what you're viewing
- **Engagement improvements**: Smart, similarity-based product and document recommendations
- **Seamless user experience**: Help users find what they need (and didn't know about)
    
    ![day 4_recommendations.gif](https://unable-actionable-car.media.strapiapp.com/day_4_recommendations_e67bc9c528.gif)

#### Day 5: Wrapping up and looking ahead

https://youtu.be/I42NbytO0hQ

We closed the week with a recap and vision for the future with our CEO, Quentin.

At Meilisearch, our mission is to make the best search experience accessible to everyone. We want to deliver the best technologies and combine them with an amazing user experience. This week, we’ve taken a big step forward and are closer to this vision, helping search results understand context, offer personalized experiences, and enable smarter recommendations.

In the coming months and quarters, you'll see exciting new features—from better search analytics and more insights for taking action on your business, to more customization capabilities for tailored experiences, but also we’ll continue advancing on exclusive capabilities like [built-in RAG](https://www.meilisearch.com/blog/how-to-build-rag?ref=dailydev) or [image search](https://www.meilisearch.com/docs/learn/ai_powered_search/image_search_with_user_provided_embeddings) to make them work out of the box, with little to no configuration required.

**📹 [Watch Meilisearch AI launch week wrap up with CEO](https://youtu.be/0tPsBrmtf3o?si=6KAyuREv0DYVfCZD).**

**📖 Read Quentin’s [blog](https://www.meilisearch.com/blog/introducing-meilisearch-ai) on building the future of search with Meilisearch AI.**
## Join us on this journey

As we celebrate reaching **50,000 GitHub stars,** we're just getting started on our mission to redefine search. Whether you're new to Meilisearch or already part of our community, these new capabilities unlock more intuitive, personalized search experiences.

To mark the occasion, we’re giving new subscribers an exclusive gift: use the code **`MEILIAI`** and **get [2 months of Meilisearch](https://help.meilisearch.com/en/article/meilisearchs-promo-discount-code-program-1ykitx7/), including AI-powered searches, completely free**. It’s the perfect time to start building the search experience you’ve always wanted.

Meilisearch latest news and company updates