## What is RAG, and why should you care?

Every day, millions of people interact with ChatGPT, Claude, and other large language models, fundamentally changing how we interact with computers. The appeal is obvious: instead of learning specific interfaces, users can simply communicate in natural language. The machine adapts to the human, not the other way around.

This shift has organizations scrambling to create similar experiences with their own data. Whether it's building a support chatbot that understands product documentation, crafting an assistant that writes personalized emails, or developing an internal tool to help employees access company knowledge, they all require the same foundation: giving LLMs access to proprietary information.

Enter Retrieval Augmented Generation (RAG), a workflow that's deceptively simple in concept:

1. User asks a question
2. The system retrieves relevant documents based on that question
3. LLM generates an answer using those retrieved documents as context

When implemented correctly, RAG provides more accurate, up-to-date responses while reducing hallucinations. But here's where most engineers go wrong: they default to vector databases without considering whether that's actually the optimal approach.

## The engineer's shortcut: Vector databases

The typical RAG implementation looks something like this:

```
User Question → Convert to Embedding → Query Vector DB → Retrieve Similar Documents → Generate Answer

```

It makes intuitive sense. Vector embeddings capture semantic meaning, so similar concepts cluster together in the vector space. By converting questions and documents to the same embedding space, you can find relevant information even when the exact keywords don't match.

Engineers love this approach because it seems elegant. You don't need complex query parsing or keyword matching – just transform everything to vectors and let similarity algorithms do the work.

But this shortcut creates two critical problems that significantly degrade the quality of the results.

## Problem 1: Unrefined queries lead to irrelevant results

The first major issue occurs at the initial step: we take the raw user query, convert it directly to an embedding, and use that to retrieve documents.

Think about what happens when you use Google. You don't always search with your actual question – you distill it to key terms that are more likely to yield relevant results. If you want to know "What's the best way to organize React components in a large project?", you might search for "React component organization best practices large applications."

LLMs excel at this kind of query refinement, but in the standard vector DB approach, we skip this crucial step. The embedding captures the semantic meaning of the original question, but that doesn't always align with the optimal search query.

## Problem 2: Vector search sacrifices precision for recall

The second problem is more fundamental: vector similarity search is strong at recall but often weaker at precision compared to traditional full-text search.

Vector search excels at finding conceptually related content (recall) - documents that discuss similar topics, even if they use different terminology. However, it's less effective at pinpointing exactly what you need (precision).

Full-text search, on the other hand, prioritizes precision. When exact keyword matches exist, they're usually highly relevant. The trade-off is that full-text search might miss conceptually similar content that uses different terminology.

This explains why many RAG systems that rely exclusively on vector databases end up implementing additional re-ranking steps after initial retrieval. It's also why vector databases increasingly add full-text capabilities – they recognize the inherent limitations of pure vector search.

## A more human approach to RAG

Since we're trying to build systems that mimic human intelligence, shouldn't we structure our RAG pipelines to mirror how humans actually search for information?

When people need to find information, they:

1. Reframe their question into effective search terms
2. Use search engines optimized for retrieving relevant information
3. Scan results to identify the most useful content

A better RAG design would follow this pattern:

```
User Question → LLM Refines Into Search Query → Hybrid Search (Combining Full-text and Semantic) → Retrieve Relevant Documents → LLM Generates Answer

```

This approach addresses both problems:

1. The LLM refines the user's original question into an optimized search query
2. Hybrid search combines the precision of full-text search with the recall of semantic search

## The solution: Simpler (and better) RAG with search engines

Here's my contrarian take: instead of jumping to vector databases for RAG, start with a quality search engine that combines full-text and semantic capabilities.

Modern search engines like Meilisearch offer hybrid search functionality that delivers better overall relevance than pure vector retrieval. They're also:

- Easier to deploy and maintain
- Optimized for fast queries at scale
- Designed with relevance as the primary objective
- More intuitive for debugging search results

For most RAG applications, the workflow becomes much simpler:

1. The user submits a question
2. LLM transforms that question into an effective search query
3. The search engine retrieves relevant documents using hybrid search
4. LLM generates a response using those documents as context

This approach aligns with how humans actually search for information, leveraging the strengths of both LLMs and search technology while avoiding unnecessary complexity.

## The power of simplicity in RAG: Back to search basics

Vector databases certainly have their place in the machine learning ecosystem, but they're not always the best foundation for RAG systems. By taking a step back and considering how humans search for information, we can build more effective, simpler RAG architectures.

The next time you're designing a RAG system, consider whether a good search engine might be the better choice. Your users (and your future self maintaining the system) will thank you.

Why you shouldn't use vector databases for RAG

Think of a digital library where finding a specific book feels like navigating a labyrinth blindfolded.

For many websites, internal search is just that—a frustrating maze. Users often get lost, give up, and leave the site. However, internal search can be a precise tool. It can guide users directly to what they need and offer insights into their behaviors and needs.

Today's internal search is more than a navigation aid. **It's a strategic asset that enhances user experience, boosts conversions, and taps into the intelligence of your data.**

## What is internal search?

Imagine a customer visiting your website to find a specific product, an employee searching your company intranet for a crucial document, or a reader looking for a blog post they remember reading last month. In each case, they probably use your site's internal search function.

### Key differences between internal and external search

Google and other search engines deliver instant, relevant results for any query, setting high expectations. However, internal search operates under different conditions.

External search engines like Google scan the entire web. They use complex algorithms and massive computing resources to rank billions of pages based on numerous factors, including backlinks, page speed, and user behavior.

**Internal search only indexes content within your digital boundaries**. These can include local files, email inboxes, specific software applications, intranets, and different cloud storage solutions.

![](https://unable-actionable-car.media.strapiapp.com/ezgif_com_video_to_gif_bce9ae142e_344cec37b7.gif "Example of customized internal seach from Hugging Face")



The main difference lies in control. Unlike Google's algorithms, you can fully control your internal search experience. This allows you to customize the search function to meet your specific content and user needs.

### Why internal search is essential

#### For websites

When visitors can't find what they're looking for on your site, they often leave. Poor search functionality is a top reason for site abandonment. Internal search acts as both a safety net and an efficiency tool.

**Internal search also generates valuable data about your visitors' intentions.** Every search query is a direct expression of user interest. This information can inform content strategy, product development, and marketing efforts. Crafting relevant keywords and phrases is crucial not only for users but also for structuring and tagging content to make it findable.

#### For SaaS

Internal search is becoming increasingly important in SaaS products to help users quickly find specific features, settings, or information within the application. As SaaS platforms grow in complexity and offer more functionalities, an effective internal search ensures users can easily navigate the system and maximize its value.

![iOS wallpaper search problem](https://unable-actionable-car.media.strapiapp.com/i_OS_wallpaper_search_problem_8067d95edc.avif "Many people are complaining about the search function in the iOS Settings app.")



Just like the complaints about the iPhone settings app's search function, a non-functioning internal search can be incredibly frustrating for users who expect to find what they need quickly and easily.

### How internal search differs across industries

The implementation and importance of internal search vary significantly based on the business model and content type.

![fuzzy search](https://unable-actionable-car.media.strapiapp.com/fuzzy_search_3f79b0e35c.avif)



**E-commerce:** For online retailers, search is often the primary navigation method for product discovery. Search accuracy is directly tied to conversion rates. Users expect advanced features like filtering by price, size, color, and other attributes. Amazon's search functionality predicts intent, [handles misspellings](https://meilisearch.com/blog/fuzzy-search), and [suggests related items](https://meilisearch.com/blog/personalization-recommendations).

![Search query interface social marketing](https://unable-actionable-car.media.strapiapp.com/Search_query_interface_social_marketing_453ab7d512.avif "For example, Slack lets you add filters within the search bar.")



**SaaS platforms:** Software companies need to make complex functionality discoverable. Internal search must span product interfaces, help documentation, community forums, and developer resources. Slack's search function handles conversational language across thousands of messages and respects complex permission structures.

![](https://unable-actionable-car.media.strapiapp.com/AD_4n_Xf_R_Ormjkncn9_Uj8i_Un6vaqs_Wi_I_Uln1hutwuz0h_KI_wm_GIA_P_Wry5j_Rj5_R_Altplg_VV_5_Jy_ANKPL_2_Hayt3_Jv_Ku_A_Gw9ou_P8l0va_9f26862acc_ad08c71ee1.gif)



**Content platforms:** Media sites, blogs, and knowledge bases use search to help users find relevant information quickly. Bildhistoria, a Swedish non-profit managing the country's largest collection of historical photographs, uses Meilisearch to [power discovery across their database](https://www.meilisearch.com/blog/powering-bildhistoria-discovery) of 90,000+ images and associated metadata about people, organizations, and locations.

**Corporate intranets:** Search engines within organizations must navigate multiple disconnected systems. [**Enterprise search**](https://meilisearch.com/blog/enterprise-search) **platforms provide a unified search experience** that connects to and indexes data from a wide range of internal systems, including email, cloud storage, and various business applications.

Effective internal search requires understanding both your content structure and your users' search behavior. This challenge grows with the size and complexity of your digital presence.

## Benefits of internal search for businesses and users

Internal search functions as your website's personal concierge. It guides visitors precisely where they need to go while gathering invaluable intelligence about their intentions.

### Boosting conversions through effective internal search

Search-driven visitors aren't casual browsers; they have clear intent. In fact, visitors who use search are a staggering [338% more likely](https://www.hawksearch.com/white-paper/why-do-i-need-site-search) to convert than those who don't. They're actively seeking something specific, demonstrating higher purchase intent.

When someone types "waterproof hiking boots size 10" into your search bar, they're declaring their purchase intention. **By delivering precisely matched results, you facilitate a transaction that might otherwise never happen.**

### Enhancing SEO with internal search data

Your internal search box is a valuable SEO research tool. Each query represents unfiltered customer language—the exact terms your audience uses when thinking about your products or content. This intelligence helps bridge the gap between how you describe your offerings and how customers search for them.

By tracking and analyzing these searches, you can:

- Identify content gaps
- Discover emerging trends
- Refine your external SEO strategy with authentic user language

**When you notice frequent searches for terms you haven't optimized for, you've discovered opportunities to create targeted content that meets demonstrated user needs.**

### Gaining insights into user behavior and preferences

Internal search data reveals not just what users want, but how they think. The patterns in search queries can uncover seasonal trends, regional preferences, and shifts in terminology within your industry. This behavioral intelligence extends beyond marketing—it can inform product development, content strategy, and inventory management decisions.

![Google trends search results](https://unable-actionable-car.media.strapiapp.com/Google_trends_search_results_6a871f670e.avif "You will then be able to have a dashboard like that. This one is Google Trends")



For instance, a sudden spike in searches for "sustainable packaging options" might signal an emerging customer priority that could influence your product roadmap. **These insights allow you to stay aligned with evolving customer expectations.**

### How internal search can reduce bounce rates and improve time on site

When visitors can't find what they're looking for, they often leave your site and head to a competitor. A robust internal search system acts as a safety net, catching potentially lost visitors by providing alternative paths to discovery.

By analyzing search patterns alongside user session data, you can identify which search terms lead to extended site exploration versus immediate exits. **This intelligence helps you prioritize content improvements where they'll have the greatest impact on engagement metrics that directly influence your bottom line.**

## How to implement internal search on your website

In this section, we'll explore how to select the perfect internal search solution that aligns with your platform's unique requirements and user expectations.

### Choosing the right internal search engine for your needs

Different search solutions cater to various needs. Your choice should match your specific requirements. Think of search engines as vehicles: some are fast sports cars, others are sturdy SUVs for varied terrain.

When evaluating options, consider these critical factors:

- **Scale and complexity of your content**: How much data needs indexing? Does it include multiple content types?

- **Technical resources available**: Do you have developers for complex integrations, or do you need a simpler solution?

- **Customization requirements**: Is a standard search interface enough, or do you need a customized experience?

- **Budget constraints**: Enterprise solutions offer robust features but are more expensive, while open-source alternatives like Meilisearch provide powerful capabilities at a lower cost.

Meilisearch is often an ideal choice, offering the speed and relevance of commercial solutions with the flexibility and affordability of open-source software. Its typo-tolerance and minimal configuration requirements make it appealing for teams seeking powerful search capabilities without extensive implementation effort.

<Callout intent="note">
	
	Want to dive deeper into how different search solutions compare? Check out our [comprehensive comparison of Meilisearch and Algolia](https://www.meilisearch.com/blog/meilisearch-vs-algolia) to understand the nuances of modern search technologies.
	
	
</Callout>

### Setting up internal search tracking in Google Analytics

**Tracking search behavior is crucial** for understanding user needs and identifying content gaps. Here’s how to set up search tracking in Google Analytics 4:

- **Identify your search query parameter**: Perform a search on your site and check the URL. For instance, if the URL is `www.example.com/search?q=analytics`, "q" is your query parameter.
- **Navigate to your GA4 account settings**: Go to Admin &gt; Data Collection and Modification &gt; Data Streams, and select your web data stream.
- **Enable Enhanced Measurement** and access the settings by clicking the gear icon.
- **Activate Site Search** and click "Show advanced settings."
- **Enter your specific query parameters** if they differ from the default ones (q, s, search, query, keyword).

To analyze this data effectively, create a custom report:

- Go to the Library section in GA4.
- Choose "Create New Report" &gt; "Create detail report."
- Select "Events" as your dimension.
- Choose "Search Term" as your primary dimension.
- Add metrics like "Event Count" and "Total Users."
- Include an event filter: Event name exactly matches 'view_search_results'.

This configuration will transform raw search data into actionable intelligence. It helps you understand not just what users are searching for, but also their behavior patterns. This insight is invaluable for guiding content creation and product development. The search data you collect offers a direct glimpse into your users' needs, preferences, and challenges.

<Callout intent="tip">

Unlock advanced search potential with customizable relevancy, typo tolerance, and more. Enhance your search strategy with powerful search capabilities.
[Explore Features](https://www.meilisearch.com/solutions/hybrid-search)

</Callout>

## Leveraging internal search data for business growth

Internal search reveals customer intent, a goldmine for forward-thinking companies. Every query highlights user needs. Optimize the search experience, then leverage that data to refine content, products, and overall strategy.

### Using search data to refine content and product offerings

Focus on high-volume/low-result queries – these pinpoint unmet needs. One content platform, spotting frequent searches for "beginner tutorials" despite having only advanced content, created a successful intro series. Search data shows *what* users want and *how* they ask for it. A monthly cross-functional "search insights review" can ensure data influences business-wide decisions.

### Identifying trends and gaps in user needs

Search data flags emerging trends. Monitor seasonal patterns to predict demand. Meilisearch offers powerful analytics, capturing subtle shifts in user language using natural language processing.

### Integrating internal search insights with marketing strategies

Use internal search insights to:

- Tailor marketing messages with **relevant keywords and promotions**
- Base campaigns on user search behavior
- Target specific user needs identified through search data

### Measuring the ROI of internal search improvements

Link search behavior to business outcomes to see real ROI.

Search users often convert 2-3x higher than non-search users, justifying search investments. E-commerce sites see higher average order values from search-initiated purchases.

### How to use internal search data to personalize user experiences

Search history: a behavioral fingerprint. Prioritize recent searches for content recommendations. Tailor navigation menus based on common searches. Strive for helpful, not intrusive, personalization. Consider context: a "lightweight jacket" search in September vs. March implies different needs.

Treat each query as customer intelligence to build responsive products, relevant content, and personalized experiences driven by user language.

## Key features of an effective internal search engine

The difference between a basic search box and a truly effective internal search system lies in its ability to understand user intent and deliver relevant results instantly. Let's explore the essential components that transform ordinary search functionality into an exceptional user experience.

### Fast and accurate search results

**Users expect near-instantaneous results—anything over 300 milliseconds feels sluggish.** But speed without accuracy creates frustration. The most effective search engines balance both, delivering relevant results at lightning speed.

Modern search platforms like Meilisearch achieve this balance through sophisticated indexing techniques. These systems prioritize both performance and relevance. They deliver results in milliseconds while maintaining high accuracy—even with typos or partial queries.

### Intuitive and user-friendly interface

The search interface should be immediately recognizable and accessible from any page. Effective implementations feature prominent placement, clear visual cues, and thoughtful placeholder text that guides users on how to search effectively.

![predictive search](https://unable-actionable-car.media.strapiapp.com/predictive_search_847ae3d9ef.gif)



[Auto-suggest](https://meilisearch.com/blog/predictive-search) functionality transforms the search experience from a guessing game into a guided journey. As users type, seeing relevant suggestions not only speeds up their search process but also helps them discover options they might not have considered. **This subtle guidance can significantly improve discovery and engagement.**

### Advanced filtering and sorting options

Once results appear, users need ways to refine them based on their specific needs. [Effective filtering options](https://meilisearch.com/blog/filter-scoring-guide) might include:

- Date ranges for content searches
- Price ranges for product searches
- Specific metadata fields relevant to your content type

**The key is balancing comprehensiveness with simplicity.** Offer enough filtering power without overwhelming users with too many options. Effective implementations adapt their filtering options contextually based on the search query and available results.

### AI-powered personalization and recommendations

Modern search engines incorporate machine learning to understand context and user preferences. This intelligence allows the system to personalize results based on previous interactions, location, or other relevant factors.

Recommendation engines extend this capability by suggesting related items that might interest the user based on their search behavior and the collective intelligence gathered from all site visitors.

### Access to actionable search analytics

Behind every great search implementation is a [robust analytics system](https://meilisearch.com/blog/search-analytics-release). It tracks what users search for, which results they click, and where the system fails to deliver relevant results. These insights drive continuous improvement of both the search functionality and your overall content strategy.

Platforms that provide visualizations of search trends, zero-result queries, and user paths after searching give you the intelligence needed to refine your approach over time.

<Callout intent="tip">
	
	Capturing zero-result searches can highlight content gaps and unmet user needs, guiding future improvements.
	
	
</Callout>

## Enhancing digital success with internal search

Internal search serves as a strategic tool that **transforms user experience and drives business intelligence**. It connects user intent with digital content effectively.

By implementing intelligent search technologies such as Meilisearch, organizations can develop dynamic, responsive platforms. These platforms not only meet but also anticipate user needs. This shift turns the search function from a basic navigation tool into a powerful engine of engagement and insight.



Internal search: the key to better user experience and SEO  

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

Federated search allows fetching information from several data sources with a single search query, which triggers an engine that seamlessly aggregates the information and outputs the key results.

This technology is helpful for enterprises that often use several databases and other storage solutions and require an internal search engine that guarantees fast and unified information retrieval.

In this piece, we will examine federated search's workings and applications in greater detail, highlighting its benefits and potential challenges.

## What is federated search?

Federated search is a search system that uses a single query to retrieve information simultaneously across multiple indices, such as databases, APIs, and cloud storage solutions.

Unlike searching on a single index, which grabs only the most accurate results for that document, federated search aggregates information from all available sources and outputs the most relevant results from the aggregated dataset.

This information retrieval mechanism is a crucial feature for SaaS applications, where users frequently need to search through all available resources regardless of type. An example you might be familiar with is searching in Slack—a single search bar to find users, messages, and shared documents.

![image1.png](https://unable-actionable-car.media.strapiapp.com/image1_14270ba4b3.png)

## What are the benefits of federated search?

Federated search brings overall efficiency in retrieving information for organizations. Some of the key benefits associated with this technology are:

* **Search across multiple sources:** With only one search bar, companies can query key information from all their data sources, including databases, Google Sheets, APIs, and cloud solutions.
* **Enhance user experience:** Since federated search requires only one widget or input to fetch all relevant data, there’s no need for multiple menus or filters to enhance the federated search results. Making the search experience and the overall interface more straightforward.
* **More relevant results:** The system matches the query against a large dataset of aggregated data sources. Therefore, the engine will look for the most relevant results across all enterprise data instead of returning lists of relevant results from separate sources.
* **Find forgotten content:** Sometimes, with such diverse data sources, the user may struggle to know precisely where they saved the meeting minutes or what folder has that great resume someone sent a few months ago. Federated search fixes this with a single search input that, with the right keywords, can fetch this information or even essential items they hadn’t initially considered. 
* **Increased productivity:** Time spent looking for the correct information in emails, databases, etc., can be drastically reduced, allowing users to concentrate on more productive tasks.

## What are the different types of federated search?

There are four different types of federated search. You should carefully choose them according to your company’s needs. 

![image2.png](https://unable-actionable-car.media.strapiapp.com/image2_08f34eb71a.png)

Now that we've quickly reviewed their pros and cons, let's explore each of these federated search types individually.
 
### Search-time merging

Search-time merging dynamically queries multiple indices in real-time, combining the results of different data sources. This approach involves maintaining a separate index instead of a unified one.

The main perk of search-time merging is that you don’t need to create a new system that aggregates all data sources into one dataset. 

In addition, you can rely on up-to-date information from constantly updated data sources. Therefore, this search type is ideal for real-time databases or live web sources.

The main drawback of this technology is its dependency on the system’s response times, which creates latency and returns outputs slower than other search types.

### Index-time merging

Index-time merging aggregates the different enterprise data sources in one centralized index before the queries occur. This architecture makes data retrieval much faster since a single source provides the results list. 

While this method is fast and does not require an index for each separate data source, it may not output the most updated enterprise information. Constant synchronization is necessary to maintain accuracy and mitigate this problem. 

This search type can be handy for companies that manage data sources that are not updated frequently and where real-time information is not a required feature.

### Federated search interface

The federated search interface is similar to the search-time merging method. Users can retrieve results from diverse systems through a unified interface instead of querying a centralized index.

This solution's front-end layer abstracts the back-end complexity and presents the results as lists indicating their source. 

This interface provides a better customer experience, allowing users to query various sources simultaneously. Advanced features, such as faceted search and relevance ranking, can also be added to the interface.

The challenges with this technology are mostly related to the complexity of creating the abstraction mechanism, and [many websites](https://www.meilisearch.com/solutions/site-search) are not prepared to incorporate this design.

### Hybrid federated search

Hybrid federated search combines search-time and index-time merging. It uses a centralized approach, aggregating data sources in one index while querying other indices separately. 

This dual approach optimizes performance and speed by querying less frequently updated information using the centralized index while obtaining real-time data.

The system unifies the relevant outputs from the centralized and remaining sources into one final output list. Therefore, while this solution is faster than search-time merging, it can still lead to latency and slow performance.

## How does federated search work?

Here’s a breakdown of how federated search works. 

![image4.png](https://unable-actionable-car.media.strapiapp.com/image4_31706cba6b.png)

**Query submission:** The user starts by [typing terms or keywords](https://www.meilisearch.com/blog/semantic-search) into a single search bar or interface. This interface hides the complexity of searching many sources behind the scenes.

**Routing:** Once the user enters the query, the search tool identifies which databases, APIs, cloud services, and other data sources are relevant to tackle. Once identified, the same query is sent to all these sources simultaneously.

**Query processing:** The search begins for each target index. Depending on the search type, there can be a centralized index or multiple. This choice also influences the response time and accuracy.

**Obtaining relevant results:** Depending on the search type, a single or several lists are obtained with the most relevant results across multiple data sources. 

When the architecture uses multiple lists, merging data requires more preprocessing steps. This is due to duplicate results and formatting, such as converting DateTime elements and strings to numbers. 

Also, ensuring accuracy in the final data is vital since each index sorts the relevancy depending on its information. One data source may display three results as the most relevant, while similar results are placed last on the list in another and more extensive source.

**Final output**: The system displays the final results in a single list, often with labels showing where each result came from.

Additionally, the system must be **optimized and maintained:** adding new indices or simply optimizing the capabilities requires updates and maintenance. 

In the steps involving the federated search workflow, it is key to maintain strong security measures throughout the process, apply preprocessing functions, and manage latency when some sources may take more time to deliver results.

## What are common use cases for federated search?

Federated search can serve various applications and company profiles. These are some of the most common use cases.

* **Enterprise search:** Large organizations can easily access their different data sources of information (emails, chats, CRMs, cloud storage, and databases) with a single input widget or interface. This enhances their productivity across several departments.
* **E-commerce and marketplaces**: E-commerce websites have high standards for delivering fast and accurate information. Therefore, federated search allows these companies to retrieve information in real-time from product listings, reviews, inventory data, and more, ensuring a better user experience and increasing customer satisfaction.
* **Academic and research portals:** Researchers rely on journals, institutional repositories, and databases. This technology can provide scholars with a unified research experience that accelerates knowledge discovery.
* **Healthcare and medical records:** Federated search enables instant retrieval of relevant medical information from patients, medical notes, and medical databases, enhancing diagnosis accuracy and treatment speed. It also supports compliance with privacy regulations by ensuring security and access control.
* **Government and legal systems**: Governments manage extensive records, from public policies to legal case files. Federated search makes fetching access to legal precedents, statutes, and regulatory documents easy, helping law firms, policymakers, and public agencies make informed decisions. It also enhances transparency and improves citizen access to public records.
* **Media and publishing:** Journalists and content creators do extensive research across multiple content sources, such as archives, news wires, social media, and internal databases. Therefore, they need a tool that helps them find articles, blogs, or archives faster, resulting in improved productivity.
* **Customer support and help desks:** Support teams need quick answers from knowledge bases, support tickets, and FAQs. You can consolidate these resources with federated search and decrease the response times, which improves customer satisfaction while reducing operational costs.

Depending on the application, you should carefully consider the right federated search type. For instance, e-commerce companies require real-time data, while government and legal systems may need to retrieve information quickly. Therefore, the former can leverage a hybrid system, while the latter can use a unified index approach.

## What are the challenges of federated search?

Several challenges arise during the federated search process. The main ones are:

* **Data structure:** Different indices have different data sources, such as text files, JSON, CSVs, and databases. Therefore, you must consider preprocessing steps and natural language processing (NLP) techniques to merge data from various structures and grasp their relevance.
* **Sorting and scoring results:** Indices output the relevant results using mathematical functions like cosine similarity, often used in [machine learning (ML)](https://www.meilisearch.com/blog/neural-search). Smaller datasets may return less accurate results. When merged with more extensive data sources, extra preprocessing steps are needed to avoid noise and irrelevant results.
* **Language nuances:** International companies often have departments in different countries that use their native languages. Querying indices, primarily written in a specific dialect, must be translated into a unified language for the final results. 
* **Query robustness:** Search engines do not always recognize special characters like quotes or hyphens to refine queries.
* **Availability and timeout:** Federated search engines that offer [real-time data](https://www.meilisearch.com/blog/vector-search) may take longer than expected to respond after the user submits the query. This can increase the bounce rate and make users less prone to revisit the website.
* **Data pipeline:** The efficiency and quality of the data pipeline are key to ensuring seamless connection of all indices and error-free application of data preprocessing steps. Therefore, these pipelines can become very robust, requiring third parties for monitoring and security.

A good team of experts is key to creating a robust federated search engine that ensures seamless connections between different sources, security, high performance, and ease of use.

## How federated search improves developer experience

Implementing federated search leads to a more streamlined search implementation process. With federated search, results are delivered in a unified list, simplifying front-end development. This goes beyond multi-index search because it comes without the added complexity of implementing front-end logic to merge, sort, and paginate the results.

In this setup, the relevance of documents can be further fine-tuned thanks to granular, per-index configuration. This allows tailoring the relevancy settings to specific data types (a specific index) rather than the entire dataset (all indices). As a federated search request comes in, the search engine can ensure that the most relevant information rises to the top.

Federated search also simplifies extending the search functionality if new types of documents need to be included. Instead of revisiting the relevancy for the entire dataset, you'll only need to focus on configuring the relevancy settings for the new document type.

## What are some examples of federated search tools?

### Meilisearch

![image7.png](https://unable-actionable-car.media.strapiapp.com/image7_a98ee81d11.png)

Source: Meilisearch

Our platform is great if you need speed and ease of use. You can submit data in different formats on the Meilisearch cloud or through an API and easily integrate [hybrid search](https://www.meilisearch.com/solutions/hybrid-search) and other search features into your enterprise infrastructure. All of this is backed by extensive documentation and strong customer support.

**Best for:** Due to its performance and speed for data retrieval, it is best for enterprises that manage various data sources and require typo tolerance, as well as education software companies.

<Callout intent="tip">

#### Easy federated search with Meilisearch 

If you need speed and manage many data sources, Meilisearch is the best way to implement federated search.  

[Get started for free!](https://www.meilisearch.com/cloud)

</Callout>

### Qatalog

![image6.png](https://unable-actionable-car.media.strapiapp.com/image6_37b2442a9a.png)

Source: G2

This solution can access data sources without creating indices. Some connectors are SharePoint, Google Drive, Salesforce, Zendesk, BigQuerry, and Snowflake. The indexless feature helps reduce latency and return real-time data.

**Best for:** Suitable for E-commerce websites and enterprises that require real-time data with zero or almost zero latency.

### Hyland

![image8.png](https://unable-actionable-car.media.strapiapp.com/image8_3ff93be45d.png)

Source: G2

This tool comes with several integrations and allows for creating image indices. It also introduces detectors of confidential information to protect companies from exposing it.

**Best for:** Enterprise search and healthcare companies that often rely on extensive image databases.

### Gosearch

![image10.png](https://unable-actionable-car.media.strapiapp.com/image10_ee2d4deeb0.png)

Source: G2

This tool presents an easy-to-implement unified enterprise search solution that is fast and enhanced with a generative AI chatbot. It also comes with several integrations, such as Zendesk, Slack, OneDrive, Jira, and more. 

**Best for:** IT teams and Human Resources due to its rapid implementation and chatbot integration in the search engine.

## Frequently asked questions (FAQs)

Some of the most common questions involving federated search are the following:

### How does federated search compare to unified search?

Unified search is a subtype of federated search, which uses a centralized pre-built index. It offers faster results but lacks real-time data. Other types of federated search, such as hybrid and search-time merging, use several indices, which make them slower due to the latency of some data sources, but they can deliver real-time results.

### What are the key components of a federated search system?

The federated search system requires a user-friendly interface that allows the user to input a query. The system sends this query to a single index or multiple indices. When numerous indices are involved, each uses its ranking mechanism to sort the most relevant results. The system uses a robust data pipeline to handle syntax, various languages, formats, and other data processing requirements. Finally, security is key to ensuring data protection.

### What are the drawbacks of federated search?

The system can be time-consuming to set up and requires constant optimization. Several experts are involved in creating a seamless user interface that delivers speed and performance while abstracting all the back-end steps, which include cleaning the data, applying strong security measures, and ensuring it displays the most relevant results to the user. 

### What are some open-source federated search solutions?

Some open-source federated search solutions provide a clear view of the system's backbone and allow seamless integration through their API. Meilisearch, for instance, provides extensive [documentation](https://www.meilisearch.com/docs) in several programming languages (Java, PHP, Python, JavaScript, and more). Others, such as Milvus and OpenSearch, also open-source their code on GitHub.

## Cut through the clutter with federated search

Federated search enables performing searches against multiple indices of a search engine and returns a single, consolidated list of results. With a search engine that supports federated search, developers can build more relevant user search experiences without incurring additional complexity.

Overall, this tool boosts productivity and reduces costs across several divisions inside a company while enhancing customer support and user experience.

Federated search is available in Meilisearch 1.10 and higher. The documentation explains how to implement federated search with Meilisearch. 

What is federated search: Complete guide [2025]

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 latest news and company updates