We're excited to unveil Meilisearch v1.7. In this article, we’ll review the most impactful changes. For an exhaustive listing, check out the [changelog](https://github.com/meilisearch/meilisearch/releases/tag/v1.7.0) on Github.

<Callout>
  Meilisearch 1.7 is available on [Meilisearch Cloud](https://cloud.meilisearch.com/?utm_campaign=release-v1-7&utm_source=blog) too—upgrade now!
</Callout>

Improved hybrid & vector search
-------------------------------

<Callout>
  AI search is an experimental feature, read the docs to [enable AI search](https://meilisearch.dev.org.tw/docs/learn/experimental/vector_search?utm_campaign=release-v1-7&utm_source=blog#activate-vector-search).
</Callout>

### New OpenAI embedding models

Starting with Meilisearch 1.7, you can use OpenAI’s third-generation embedding models:

*   `text-embedding-3-small`
*   `text-embedding-3-large`

Compared to the previous `text-embedding-ada-002` model, these new models offer improvements allowing to balance search results relevancy and cost efficiency.

The `small` model is more cost-effective, generating smaller vector embeddings that require less storage. The `large` focuses on delivering higher precision in search results, making it ideal to optimize relevancy.

### Configuring OpenAI model dimensions

When using the new `text-embedding-3-small` and `text-embedding-3-large` OpenAI models, you can now configure **dimensions** for your model. When not provided, the model's defaults dimensions are used.

You can do so when updating your settings:

```json
{
  // other settings...

  "embedders": {
    "small": {
      "source": "openAi",
      "model": "text-embedding-3-large",
      "dimensions": 512 // must be >0, must be <= 3072 for "text-embedding-3-large"
    },
  }
}

```

Higher dimensions typically offer more complex embeddings which can lead to more accurate search results. However, increased dimensions are more costly to compute and require more storage.

<Callout>
  You cannot customize dimensions when using OpenAI `text-embedding-ada-002`.
</Callout>

### Use AI Search on Meilisearch Cloud

Meilisearch hybrid search and vector search are coming to Meilisearch Cloud. We're rolling out invites every day. Join the beta. 👇

[Get early access](https://share-eu1.hsforms.com/1RN-rGYhHQPu5BNivfknlwAfg3aq?utm_campaign=release-v1-7&utm_source=blog)

GPU support for computing Hugging Face embeddings
-------------------------------------------------

Meilisearch 1.7 comes with the ability to enable GPU support for [self-hosted Meilisearch](https://meilisearch.dev.org.tw/docs/learn/getting_started/installation?utm_campaign=release-v1-7&utm_source=blog) for computing Hugging Face embeddings. This can significantly speed up the embedding generation process.

Find detailed instructions in our dedicated guide on [Using GPU to compute Hugging Face embeddings](https://meilisearch.dev.org.tw/docs/learn/cookbooks/computing_hugging_face_embeddings_gpu?utm_campaign=release-v1-7&utm_source=blog).

Display ranking scores details at search
----------------------------------------

Meilisearch 1.7 stabilizes the `showRankingScoreDetails` search parameter that was introduced in [Meilisearch 1.3](/blog/v1-3-release/?utm_campaign=release-v1-7&utm_source=blog This parameter adds a `_rankingScoreDetails` field to each document in search results, enabling further inspection of the search results.

You can include the parameter when making searches:

```sh
curl \
  -X POST 'https://edge.meilisearch.com/indexes/movies/search' \
  -H 'Content-Type: application/json' \
  --data-binary '{
    "q": "batman",
    "showRankingScoreDetails": true
  }'

```

Learn more about the [`_rankingScoreDetails` object](https://meilisearch.dev.org.tw/docs/reference/api/search#ranking-score-details?utm_campaign=release-v1-7&utm_source=blog) and how to use it with your preferred SDK in the API reference.

Contributors shout-out
----------------------

We want to give a massive thank you to all contributors that made this release possible: [@capJavert](https://github.com/capJavert), [@codesmith-emmy](https://github.com/codesmith-emmy), [@Elliot67](https://github.com/Elliot67) and [@Gosti](https://github.com/Gosti) for their PRs in Meilisearch, and [@agourlay](https://github.com/agourlay), [@choznerol](https://github.com/choznerol), [@ngdbao](https://github.com/ngdbao), [@timvisee](https://github.com/timvisee), and [@xshadowlegendx](https://github.com/xshadowlegendx) for their work on [charabia](https://github.com/meilisearch/charabia).

Special thanks to our SDKs maintainers, thanks to whom Meilisearch is available across so many languages. 🫶

* * *

And that’s a wrap for v1.7! This release post highlights the most significant updates. For an exhaustive listing, read the [changelog on Github](https://github.com/meilisearch/meilisearch/releases/tag/v1.7.0).

Stay in the loop of everything Meilisearch by subscribing to our [newsletter](https://dub.sh/meili-newsletter). To learn more about Meilisearch's future and help shape it, take a look at our [roadmap](https://roadmap.meilisearch.com/?utm_campaign=release-v1-7&utm_source=blog) and come participate in our [Product Discussions](https://github.com/meilisearch/product/discussions).

For anything else, join our developers community on [Discord](https://discord.meilisearch.com/?utm_campaign=release-v1-7&utm_source=blog).

Meilisearch 1.7

On March 7th, we hosted a live showcase session introducing hybrid search and other Meilisearch product updates. Watch a recording and see the hybrid search demo [here](https://www.youtube.com/watch?v=Lgv8iTdWDQc&t=881s).

* * *

AI's influence on search
------------------------

The rapid advancement of AI technology is undeniably reshaping human-machine interactions. Historically, communication with machines necessitated intermediaries like programming languages and structured scripts.

Now, with the arrival of GPTs and AI-assisted bots, machine-learning models are approaching a deeper comprehension of natural human language. This evolution brings humans and machines closer, changing the way we seek and find information.

From keyword-based searches to discovery-driven inquiries, people’s approach to search evolves: we are moving from searching for known items to exploring unknown territories, searching and finding the concepts instead of focusing solely on words.

Take a streaming media company: the searches across their platform might include the inquiry for a specific movie title, such as "Back to the Future," as well as conceptually-driven searches like "Give me recommendations for a feel-good sci-fi movie from the 80s".

Consider everyday scenarios: spotting an item on the street and using an image to search for it, or conducting voice searches instead of typing in words on keyboards. These are manifestations of our changing search behaviors.

The pinnacle: hybrid search
---------------------------

While traditional search methods excel in keyword-based queries, they falter with complex, nuanced requests. This is where Meilisearch’s new hybrid search approach comes into play, enriching the efficiency and precision of our robust full-text search engine with a depth of semantic understanding, catering to a wide array of use cases driven by customer-generated data.

Integrating models from AI giants like [OpenAI](https://meilisearch.dev.org.tw/docs/learn/experimental/vector_search#generate-auto-embeddings-with-openai) (open-source embedders generation feature is set for the next release cycle), Meilisearch enables users to create and fine-tune vector embeddings, tailoring their search engine to specific business needs. Moreover, evolving AI models learn from user interactions, continuously improving search precision.

What‘s included in the new release package?
-------------------------------------------

The AI-enhanced hybrid search from Meilisearch leverages our existing robust search infrastructure, including advanced sorting, filtering, faceting, and geo-sorting capabilities, among others.

New release features
--------------------

*   **Enhanced search relevancy**: The AI-enhanced layers bring a deeper semantic understanding, significantly improving result quality.
*   **AI embedders autogeneration:** Choose between using a third-party solution like OpenAI or your own locally generated embeddings. An open-source embedders generation feature is set for the next release cycle.

![](https://unable-actionable-car.media.strapiapp.com/Group_143725866_7f8309846d.png)

Add a new AI embedder in Meilisearch Cloud.

*   **Improved prompting:** Enhanced to incorporate key information templates, aiding the system in prompt ingestion and relevant metadata interpretation.
*   **Semantic ratio control:** Customize your search to span anywhere from purely keyword-based to entirely semantic.  
    

![](https://unable-actionable-car.media.strapiapp.com/Group_143725865_1_f3910ea1ce.png)

Choose where you want your results to fall on the spectrum from pure keyword-based to fully semantic search.

*   **Multimodal search capabilities:** Expanding search functionality to include image, sound, and video content.

**Democratizing search**
------------------------

At Meilisearch, our journey has always been anchored in simplicity, performance, and out-of-the-box relevancy. Our core mission remains steadfast: make it easy to find anything anywhere by providing a go-to-search solution for every team.

> “Meilisearch's hybrid search will democratize advanced search technology, focusing on simplicity and open-source customizability”  
> \- **Quentin de Quelen, Meilisearch’s CEO and Co-founder.**

As we evolve, our methods become more sophisticated, adapting to the ever-changing needs of businesses and developers alike. In a world brimming with data, effective content discovery is essential, not just a luxury. Our vision combines innovation with accessibility, aiming to make cutting-edge search technology inclusive for all.

The launch of our hybrid search product marks a significant milestone for Meilisearch and the search technology landscape. We invite you to try the new solution and join us in shaping the future of search.

* * *

Our AI-powered hybrid search is currently in beta. Eager to try it out? Sign up for our waitlist by using the link below, and our team will be in contact soon.

[Sign up now](https://share-eu1.hsforms.com/1RN-rGYhHQPu5BNivfknlwAfg3aq?utm_source=Blog&utm_campaign=HybridSearchRelease)

* * *

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

For anything else, join our developer community on [Discord](https://discord.com/invite/hTD5hU2yWV?utm_source=Blog&utm_campaign=HybridSearchRelease).

Introducing hybrid search: combining full-text and semantic search for optimal balance

🥳 Join our launch event
------------------------

[![Meilisearch product update: AI-powered hybrid search, monitoring, and more. Thursday, March 7th 4PM CET | 3PM GMT | 10AM EST](https://unable-actionable-car.media.strapiapp.com/product_launch_march_df203f4787.png)](https://us06web.zoom.us/meeting/register/tZMsdu2gqTooE9AcjcQEzj9uST040tSjWDKn#/registration)

Join us on **March 7th** to discuss our recent releases and get a sneak peak of what’s coming on Meilisearch Cloud. Spoilers—hybrid search, new embedding models, GPU support, and more. 🤫

[Register](https://us06web.zoom.us/meeting/register/tZMsdu2gqTooE9AcjcQEzj9uST040tSjWDKn#/registration)

🤔 Vector embeddings, explained
-------------------------------

[![Vector embeddings](https://unable-actionable-car.media.strapiapp.com/Vector_embeddings_1_3c8b6c87d6.png)](/blog/what-are-vector-embeddings/?utm_campaign=newsletter&utm_source=blog&utm_medium=february-updates-24)

Wondering what are vector embeddings? What is the semantic space? How is it relevant for search? Our very own [@CarolainFG](https://twitter.com/CarolainFG) dug deep into the matter to create this high-level educational piece.

[Read blog post](/blog/what-are-vector-embeddings/?utm_campaign=newsletter&utm_source=blog&utm_medium=february-updates-24)

🚀 Upgrade to 1.6
-----------------

![Meilisearch 1.6 release notes](https://unable-actionable-car.media.strapiapp.com/1_6_release_0a6958f6c2.jpeg)

We released Meilisearch 1.6 in January. Upgrade to benefit from **hybrid search**, **indexing speed improvements**, and further **customization of proximity** ranking rule. It’s time to upgrade. 👇

[Read release notes](/blog/meilisearch-1-6/utm_campaign=newsletter&utm_source=blog&utm_medium=february-updates-24

* * *

🖇️ Links, links, links
-----------------------

### 💡 [Indexing best practices](https://meilisearch.dev.org.tw/docs/learn/cookbooks/indexing_best_practices?utm_campaign=newsletter&utm_source=blog&utm_medium=february-updates-24)

All our tips to index data efficiently and speed up the indexing process.

### 🔄 [Syncing with your Postgres database](https://meilisearch.dev.org.tw/docs/learn/cookbooks/meilisync_postgresql?utm_campaign=newsletter&utm_source=blog&utm_medium=february-updates-24)

Learn how to keep your Meilisearch in sync with a Postgres database.

### 🐬 [Add search to your Appwrite application](https://appwrite.io/blog/post/add-a-search-function-to-your-app)

Learn how to add a search function to your Appwrite application.

### 🐇 [Meilisearch v1.7 release candidate](https://github.com/meilisearch/meilisearch/releases/tag/v1.7.0-rc.0)

Get a preview of what’s coming next (and give your feedback!)

### 🟧 [Laravel Scout guide](https://meilisearch.dev.org.tw/docs/learn/cookbooks/laravel_scout?utm_campaign=newsletter&utm_source=blog&utm_medium=february-updates-24)

Learn how to use Meilisearch in your Laravel 10 application.

* * *

🥰 Made with Meilisearch
------------------------

**Rerun.io** added a search bar to allow users to search through all their documentation and SDKs API references. The site is built with **React** and uses [Analytics](https://meilisearch.dev.org.tw/docs/learn/cloud/analytics?utm_campaign=newsletter&utm_source=blog&utm_medium=february-updates-24) to allow them to improve the docs content.

[![rerun.io search interface](https://unable-actionable-car.media.strapiapp.com/Capture_2024_02_27_155651_1_62b82f8316.png)](https://rerun.io/)

[rerun.io](https://rerun.io)

_We’re always looking to promote new projects from the community. Post yours in the_ [_#built-with-meilisearch_](https://discord.meilisearch.com/) _Discord channel!_

🤓 Life at Meili
----------------

Our engineer [@dureuill](https://github.com/dureuill) wrote about how dynamic management of virtual memory enabled us to remove limitations in Meilisearch indexing policy. Attention, this one is technical.

[![Squeezing millions of documents in only 128 TB of virtual memory](https://unable-actionable-car.media.strapiapp.com/squeezing_d635cb5972.png)](/blog/dynamic-virtual-address-management/?utm_campaign=newsletter&utm_source=blog&utm_medium=february-updates-24)

[Read blog post](/blog/dynamic-virtual-address-management/?utm_campaign=newsletter&utm_source=blog&utm_medium=february-updates-24)

🦸 We're hiring!
----------------

See our open positions:

*   [Head of Developer Marketing](https://meilisearch.dev.org.tw/careers?utm_campaign=newsletter&utm_source=blog&utm_medium=february-updates-24)

Meilisearch February Updates

What is a vector?
-----------------

Vectors are mathematical entities that possess both **magnitude** and **direction**. This ability to not only convey how much (magnitude) but also in which direction, makes them powerful tools for representing and manipulating different types of complex data. 

Vectors are often pictured as **arrows** pointing in a certain direction **within a space**, but they can also be translated into numbers. Representing vectors as **numerical values** makes it easier to work with them mathematically. 

Vectors are a broad mathematical concept used for various purposes across multiple fields.

Vector embeddings are a particular application of vectors in the domain of [machine learning](https://en.wikipedia.org/wiki/Machine_learning) and AI.

What is the purpose of vector embeddings?
-----------------------------------------

Machine learning models are designed to uncover patterns and relationships. They **map complex entities**, like text or images, **to points within a** [**vector space**](https://en.wikipedia.org/wiki/Vector_space). We call these vector embeddings. 

Vector embeddings, also called just embeddings, represent non-numeric data in a numerical format while **preserving the semantic meaning and relationships** of these non-numeric entities. Their goal is to allow computational models in machine learning and natural language processing (NLP) to **"understand" similarities and differences** between entities.

What is vector space embedding?
-------------------------------

In a vector space, similar entities are **positioned closely together**, indicating their semantic or contextual similarity. For instance, in the context of word embeddings, words with similar meanings are embedded near each other in the vector space. 

This spatial configuration is what enables embeddings to effectively capture and organize the **semantic relationships** between entities, a concept known as the semantic space.

What is the semantic space?
---------------------------

The semantic space is like a **virtual landscape** that each [large language model](https://en.wikipedia.org/wiki/Large_language_model) (LLM) builds as it trains. During this training phase, the model analyzes huge amounts of data to represent and understand language. The diversity and nature of the information it absorbs play a significant role in **shaping this semantic space**, which in turn influences how the LLM interprets and generates language.

Given the intricate nature of the data to be transformed, vector embeddings require **multidimensional spaces** to encompass the depth of these relationships and nuances. Depending on the **complexity of the features** they are meant to capture and the size of the dataset involved, these spaces can span a wide range, from dozens to thousands of dimensions.

This multi-dimensional space allows algorithms to interpret and process complex data in a way that mirrors human intuition and understanding.

### Illustrating the semantic space

Let’s illustrate the semantic space with a very simple example. Consider a diagram with three axes corresponding to the following semantic properties: `feline`, `juvenile`, and `canine`.

![](https://unable-actionable-car.media.strapiapp.com/semantic_space_56a01e7496.png)

*   On the `feline` axis, we have the `cat`
*   On the `juvenile` axis, the `baby`
*   On the `canine` axis, we have the `dog`

By combining these axes, we can find intersections that give us more specific entities:

*   `Feline` and `juvenile` combined give us the `kitten`
*   `Juvenile` and `canine` combined give us the `puppy`

![](https://unable-actionable-car.media.strapiapp.com/semantic_pets_9d93f8fecc.png)

By assigning numerical values to these properties, we can construct a simple semantic space:

| word   | canine | feline | juvenile |
|--------|--------|--------|----------|
| dog    | 1      | 0      | 0        |
| cat    | 0      | 1      | 0        |
| baby   | 0      | 0      | 1        |
| kitten | 0      | 1      | 1        |
| puppy  | 1      | 0      | 1        |

### Embedding vectors in the semantic space

In reality, **the semantic space is more complex**, and properties are not always clearly defined. We don’t know if this is actually the `canine` property, but it’s correlated to something `canine`, and the `dog` ranks very high on this property. The numbers are not `1` or `0` but some real numbers. This complexity allows for a nuanced understanding of how words and concepts relate to each other. The actual semantic space could look like the following:

| word   | ??canine?? | ??feline?? | ??juvenile?? |
|--------|------------|------------|--------------|
| dog    | 0.95973    | 0.12       | 0.22         |
| cat    | 0.05       | 0.99954    | 0.08         |
| baby   | 0.001      | 0.002      | 0.8973       |
| kitten | 0.02       | 0.9212     | 0.8647       |
| puppy  | 0.897      | 0.04       | 0.8834       |


From these detailed values, vector embeddings are created, capturing the essence of each word in a multidimensional vector, such as `[0.95973, 0.12, 0.22]` for `dog`. These vectors do more than just position words in a space; they build a **detailed network of meanings**, with each aspect designed to reveal a bit of what the word really means. The specific dimensions and what they represent can **vary from one model to another**, reflecting the complexity of the semantic meanings they encapsulate. 

Conclusion
----------

Vector embeddings are numerical representations of complex, non-numerical data. They are generated by machine learning models using vectors of real numbers. Embedded in a high-dimensional space, these vectors encapsulate the original data’s relationships and characteristics in a format suitable for computation. 

[**Vector databases**](/blog/what-is-a-vector-database/?utm_source=blog&utm_medium=embeddings-content&utm_campaign=vector-search like Meilisearch, are the go-to for working with embeddings, as they facilitate **similarity searches**, also known as semantic searches, which allow identification of items that are semantically similar based on their vector representations.

AI Search is coming to Meilisearch Cloud, join the waitlist:

[Join now](https://share-eu1.hsforms.com/1RN-rGYhHQPu5BNivfknlwAfg3aq?utm_source=blog&utm_medium=embeddings-content&utm_campaign=vector-search)

* * *

[Meilisearch](https://meilisearch.dev.org.tw/?utm_source=blog&utm_medium=embeddings-content&utm_campaign=vector-search) is an open-source search engine that not only provides state-of-the-art experiences for end users but also a simple and intuitive developer experience. 

A long-time actor in keyword search, Meilisearch enables users to address search use cases by building upon AI-powered solutions, not only supporting vector search as a vector store but also by providing hybrid search. This hybrid approach blends full-text search with semantic search, enhancing both the accuracy and comprehensiveness of search results.

For more things Meilisearch, you can join the community on [Discord](https://discord.meilisearch.com/?ref=blog.meilisearch.com) or subscribe to the [newsletter](https://dub.sh/meili-newsletter?utm_source=blog&utm_medium=embeddings-content&utm_campaign=vector-search). You can learn more about the product by checking out the [roadmap](https://roadmap.meilisearch.com/?utm_source=blog&utm_medium=embeddings-content&utm_campaign=vector-search) and participating in [product discussions](https://github.com/orgs/meilisearch/discussions?utm_source=blog&utm_medium=embeddings-content&utm_campaign=vector-search).

What are vector embeddings?

Understanding vector databases
------------------------------

Vector databases are the go-to for performing searches based on similarity, which plays a key role in **AI-driven applications** like recommending your next favorite movie, identifying someone in a photo, or digging up texts that resonate with your search. At the core of these applications are **vector embeddings**, complex data forms that exceed the storage and retrieval capabilities of traditional databases. 

### The role of vector embeddings

[Vector embeddings](/blog/what-are-vector-embeddings/?utm_source=blog&utm_medium=vector-db-content&utm_campaign=vector-search are a way to **transform complex non-numeric data**, such as words, sentences, or even images, **into a numerical format** while preserving their semantic **meaning** and relationships. 

Embeddings are **multidimensional objects** generated by machine learning models where each dimension represents a different feature or aspect of the data. To properly capture the data complexity, vectors can range from dozens to thousands of dimensions, depending on the size and nature of the data. 

### Vector databases vs traditional databases

This complexity makes **traditional databases**–designed to store structured data in tables– unfit to handle embeddings. The volume and complexity of these vectors, each potentially containing thousands of dimensions, challenge the row-and-column format. This mismatch necessitates alternative storage and retrieval solutions tailored to the requirements of vector data.

This is where **vector databases** like [Meilisearch](https://meilisearch.dev.org.tw/?utm_source=blog&utm_medium=vector-db-content&utm_campaign=vector-search) come into play. They are designed to address the unique demands of vector embeddings, facilitating efficient storage and retrieval of the information they contain. In particular, they enable performing **similarity searches**, also called semantic searches, which are central to leveraging embeddings effectively. 

<Callout>
  Learn more about [how Meilisearch built Arroy in Rust](/blog/spotify-inspired-hybrid-search-and-rust/?utm_source=blog&utm_medium=vector-db-content&utm_campaign=vector-search) an open-source vector store.
</Callout>

In other words, vector databases allow us to interact easily and efficiently with vector embeddings, making them essential for applications that require semantic understanding and similarity matching.

What is similarity search?
--------------------------

If we think of **vector embeddings** as stars in vast cosmic constellations, similarity search, or **vector search**, would be like trying to **find the nearest** stars to your current position in space. In practical terms, this means finding the most relevant documents, images, or products based on your search query.

To do so, you need to **measure the distance** between the **query** **vector** and other **vectors in the database**, typically using methods like [cosine similarity](https://en.wikipedia.org/wiki/Cosine_similarity) or [Euclidean distance](https://en.wikipedia.org/wiki/Euclidean_distance). These are just different techniques for determining how close or distant other data points are from your query, much like gauging the **proximity** of stars in the night sky. 

### The role of machine learning models

However, the **success** of this search isn't just about mathematical calculations; it's highly dependent on the **machine learning model** used to generate and query the vectors. Each vector's meaning is intrinsically tied to the semantic space of the model that created it. Consistency here is crucial, ensuring that all vectors 'speak the same language' and adhere to the same contextual rules, making searches **meaningful and accurate**. That is to say, to achieve relevant search results, it's essential to **use the same model** for generating and querying the embeddings.

**Similarity search** is where vector databases like **Meilisearch** truly shine, as they allow for a wide array of applications such as face recognition, movie recommendations, and personalized content discovery. By allowing users to store vector embeddings alongside their documents, Meilisearch not only facilitates similarity searches but also introduces **hybrid search** capabilities, expanding its potential applications. Through the integration of models from various AI solution providers, Meilisearch enables users to **refine vector embeddings** to better suit their specific needs.

In summary, the ability of these databases to analyze and compare complex data patterns allows for highly relevant and accurate results across diverse fields, enhancing user experiences and operational efficiency.

AI Search is coming to Meilisearch Cloud, join the waitlist:

[Join now](https://share-eu1.hsforms.com/1RN-rGYhHQPu5BNivfknlwAfg3aq?utm_source=blog&utm_medium=vector-db-content&utm_campaign=vector-search)

* * *

[Meilisearch](https://meilisearch.dev.org.tw/?utm_source=blog&utm_medium=vector-db-content&utm_campaign=vector-search) is an open-source search engine that not only provides state-of-the-art experiences for end users but also a simple and intuitive developer experience. 

A long-time actor in keyword search, Meilisearch enables users to address search use cases building upon AI-powered solutions, not only supporting vector search as a vector store but also by providing hybrid search. This hybrid approach blends full-text search with semantic search, enhancing both the accuracy and comprehensiveness of search results.

For more things Meilisearch, you can join the community on [Discord](https://discord.meilisearch.com/) or subscribe to the [newsletter](https://dub.sh/meili-newsletter?utm_source=blog&utm_medium=vector-db-content&utm_campaign=vector-search). You can learn more about the product by checking out the [roadmap](https://roadmap.meilisearch.com?utm_source=blog&utm_medium=vector-db-content&utm_campaign=vector-search) and participating in [product discussions](https://github.com/orgs/meilisearch/discussions?utm_source=blog&utm_medium=vector-db-content&utm_campaign=vector-search).

What is a vector database?

The new dashboard incorporates a set of metrics providing insights into your project’s performance. We want to help engineers move faster by making it easier to spot issues during implementation and having better visibility on your Meilisearch database health.

What metrics can you expect?
----------------------------

This first iteration comes with:

*   30 days of data retention
*   Real-time mode

**Search performance metrics**

*   Search latency
*   Maximum search queries per second

**Operations metrics**

*   Bandwidth (in/out)
*   API Calls — Succeeded/Failed

The default view combines the data from the indexes per project, but it’s also possible to filter out the insights for a specific index of your choice. The dashboard also allows you to select a custom range using a date picker or get real-time data insights:

![](https://unable-actionable-car.media.strapiapp.com/monitoring_metrics_custom_gif_gif_382681a817.jpg)

Why use monitoring**?**
-----------------------

With our brand-new dashboard, you can:

*   Ensure your users are getting lightning-fast search responses for every query
*   Monitor how your search functionality holds up under varying loads, not only during peak traffic conditions but also while indexing
*   Identify and rectify any performance bottlenecks or errors
*   Proactively maintain and optimize your project

**Availability and plans**
--------------------------

The new Cloud monitoring metrics are available for all Cloud users across all pricing tiers. Each tier has access to the same metrics and chart functionalities of the monitoring metrics dashboard.

[Try it in Meilisearch Cloud](https://cloud.meilisearch.com/?utm_campaign=monitoring-v1&utm_source=blog)

Learn how to [get started with Meilisearch Cloud](https://meilisearch.dev.org.tw/docs/learn/getting_started/cloud_quick_start?utm_campaign=monitoring-v1&utm_source=blog) and read the [Monitoring documentation](https://meilisearch.dev.org.tw/docs/learn/cloud/monitoring#requirements?utm_campaign=monitoring-v1&utm_source=blog).

* * *

Stay in the loop by subscribing to our [newsletter](https://meilisearch.us2.list-manage.com/subscribe?u=27870f7b71c908a8b359599fb&id=79582d828e&utm_campaign=monitoring-v1&utm_source=blog). To learn more about Meilisearch's future and help shape it, take a look at our [roadmap](https://roadmap.meilisearch.com/?utm_campaign=monitoring-v1&utm_source=blog) and participate in our [Product Discussions](https://github.com/meilisearch/product/discussions/?utm_campaign=monitoring-v1&utm_source=blog).

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

Cloud monitoring metrics have arrived!

**🚀 Announcing Meilisearch 1.6**
---------------------------------

[![Meilisearch 1.6 release notes](https://unable-actionable-car.media.strapiapp.com/meilisearch_1_6_1_25b4cb0c21.jpg)](/blog/meilisearch-1-6/?utm_campaign=newsletter&utm_source=january-news-24&utm_medium=blog)

Meilisearch 1.6 brings **hybrid search**, significant **improvements in indexing speed**, and a new API to **customize the proximity** ranking rule. Read the release notes to get the full picture.

[Read release notes](/blog/meilisearch-1-6/?utm_campaign=newsletter&utm_source=january-news-24&utm_medium=blog)

🔍 Typesense comparison
-----------------------

[![Meilisearch vs Typesense](https://unable-actionable-car.media.strapiapp.com/meilisearch_vs_typesense_cover_1_3b17eec4c2.jpg)](/blog/meilisearch-vs-typesense/?utm_campaign=newsletter&utm_source=january-news-24&utm_medium=blog)

We sat down to compare the key features between Meilisearch and open-source search engine **Typesense**. You can read the comparison on our blog.

[Read comparison](/blog/meilisearch-vs-typesense/?utm_campaign=newsletter&utm_source=january-news-24&utm_medium=blog)

🤗 New docs home
----------------

![Meilisearch documentation](https://unable-actionable-car.media.strapiapp.com/Screenshot_2024_01_23_at_17_16_39_e046f3c318.png)

We spent some time reworking our **docs home page** to make it more welcoming for developers. We also made **example apps** easier to find. Let us know what you think!

[View documentation](https://meilisearch.dev.org.tw/docs?utm_campaign=newsletter&utm_source=january-news-24&utm_medium=blog)

🖇️ Links of the month
----------------------

🔒 [Master key and API keys](https://meilisearch.dev.org.tw/docs/learn/security/master_api_keys?utm_campaign=newsletter&utm_source=january-news-24&utm_medium=blog)  
Learn to secure your Meilisearch instance and manage public API keys.

⚡ [Meilisearch indexes documents 2x faster](https://twitter.com/StriftCodes/status/1747566185791553639)  
Take a look at the performance boosts in Meilisearch 1.6.

🐬 [MySQL Full-Text Search Limits and New Alternatives Solutions](https://data-sleek.com/blog/the-limits-of-mysql-full-text-search-and-the-quest-for-alternative-solutions/)  
Comparing MySQL full-text search features with other search engines.

🎓 [Dropdown Autocomplete Search Anything in Laravel](https://codecourse.com/watch/dropdown-autocomplete-search-anything-in-laravel)  
Learn to build instant dropdown search with Laravel and Meilisearch.

⚛️ [The Two Reacts](https://overreacted.io/the-two-reacts/)  
Dan Abramov writes on components state, server data, and React.

🥰 Made with Meilisearch
------------------------

**YoungCapital NEXT** introduced their new website with a fresh branding and design. Built with **Next.js** and **Vercel**, their [job portal search](https://next.youngcapital.nl/vacatures) is powered by Meilisearch.

[![YoungCapital NEXT](https://unable-actionable-car.media.strapiapp.com/Screenshot_2024_01_23_at_17_34_37_1_552b1d480f.png)](https://next.youngcapital.nl/vacatures)

_We’re always looking to promote new projects from the community. Post yours in the_ [_#built-with-meilisearch_](https://discord.meilisearch.com/) _Discord channel!_

🏡 Life at Meili
----------------

[![Discord](https://unable-actionable-car.media.strapiapp.com/discord_2yf3soo8o238y21k_2d54bc8412.jpg)](/blog/from-slack-to-discord-our-migration/?utm_campaign=newsletter&utm_source=january-news-24&utm_medium=blog)

Our team wrote a blog post explaining our reasons for migrating our community to a Discord server, how we went about it, and why we shut down our public Slack.

[Read blog post](/blog/from-slack-to-discord-our-migration/?utm_campaign=newsletter&utm_source=january-news-24&utm_medium=blog)

🦸 We're hiring!
----------------

See our open positions:

*   [Head of Developer Marketing](https://meilisearch.dev.org.tw/careers?utm_campaign=newsletter&utm_source=january-news-24&utm_medium=blog)

* * *

Get these monthly updates straight to your inbox by subscribing to our [newsletter](https://meilisearch.us2.list-manage.com/subscribe?u=27870f7b71c908a8b359599fb&id=79582d828e&ref=blog.meilisearch.com).

For more things Meilisearch, join our developers community on [Discord](https://discord.meilisearch.com/). You can learn more about the product by checking out the [roadmap](https://roadmap.meilisearch.com/?ref=blog.meilisearch.com) and participating in [product discussions](https://github.com/meilisearch/product/discussions?ref=blog.meilisearch.com).

Until next time.

Meilisearch January Updates

Meilisearch vs Typesense

We’re announcing the release of Meilisearch 1.6. Let’s dive into some of the most important changes. You can also view the [full changelog](https://github.com/meilisearch/meilisearch/releases/tag/v1.6.0) on GitHub.

<Callout>
  Meilisearch 1.6 is also available on [Meilisearch Cloud](https://cloud.meilisearch.com/login?utm_campaign=release-v1-6&utm_source=blog), including all experimental features.
</Callout>

Experimental feature: hybrid search
-----------------------------------

Meilisearch introduces hybrid search. It combines full-text and semantic search to enhance the accuracy and comprehensiveness of search results. Picture a movie app like [where2watch](https://where2watch.meilisearch.com/?utm_campaign=release-v1-6&utm_source=blog). Now, your users will be able to find those movies they can't quite name but remember the story.

Furthermore, Meilisearch now streamlines the creation of vector embeddings. Choose your preferred embedders and Meilisearch will handle all interactions with external tools for you.

### Configuring embedders

You can [configure the embedders](https://meilisearch.dev.org.tw/docs/learn/experimental/vector_search?utm_campaign=release-v1-6&utm_source=blog#generate-vector-embeddings) in your index settings. Select from three types of embedders for your needs:

`openAI`:

*   Uses the [OpenAI](https://openai.com/) API for computing embeddings
*   Requires an OpenAI API key for operation

`huggingFace`:

*   Enables local computation of embeddings by downloading models from the [HuggingFace Hub](https://huggingface.co/models)
*   Operates on your CPU–not your GPU–which may impact indexing performance

`userProvided`:

*   Functions similarly to Meilisearch v1.3, with a key difference: you must define a specific embedder
*   Allows you to add pre-computed embeddings into your documents. You perform searches using vectors instead of text.

To use hybrid search, define at least one embedder in the index settings:

```JSON
{
  "embedders": {
    "default": {
      "source":  "openAi",
      "apiKey": "<your-OpenAI-API-key>",
      "model": "text-embedding-ada-002",
      "documentTemplate": "A movie titled '{{doc.title}}' whose description starts with {{doc.overview|truncatewords: 20}}"
    },
    "image": {
      "source": "userProvided",
      "dimensions": 512
    },
    "translation": {
      "source": "huggingFace",
      "model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
      "documentTemplate": "A movie titled '{{doc.title}}' whose description starts with {{doc.overview|truncatewords: 20}}"
    }
  }
}

```

The `documentTemplate` field acts as a blueprint for creating your document's embedding. It uses the [Liquid template language](https://shopify.dev/docs/api/liquid). While its inclusion is optional, it is highly recommended, especially since embedding models are optimized for concise texts. It keeps only the necessary content, excluding non-essential data like `id`, and helps in adding context to increase relevancy.

### **Hybrid search**

To [perform a hybrid search](https://meilisearch.dev.org.tw/docs/learn/experimental/vector_search?utm_campaign=release-v1-6&utm_source=blog#vector-search-with-auto-embeddings), use the hybrid field within the `POST /index/:index_uid/search` route.

```JSON
{
    "q": "Plumbers and dinosaurs",
    "hybrid": {
        "semanticRatio": 0.9,
        "embedder": "default"
    }
}

```

`embedder`: an embedder from the options configured in your index settings.

`semanticRatio`: a floating value ranging from `0` to `1`; `1` is a  fully semantic search; `0` is an exact, match-focused full-text search; the default is `0.5` which mixes both methods.

Your control over the semantic ratio directly influences how search results are ranked. A higher semantic ratio shifts the focus towards the context and meaning behind your query, ranking results that are more semantically relevant higher. 

On the other hand, a lower semantic ratio increases the weight given to keyword accuracy in the ranking process, bringing results that closely match your specific search terms to the forefront.

### **Breaking changes in the experimental vector search API**

Meilisearch v1.6 introduces some breaking changes in the vector search API.

Previously, you could send vectors without specifying a model. Now, you must define a model in the settings:

```JSON
"embedders": {
    "default": {
      "source": "userProvided",
      "dimensions": 512
    }
}

```

Because Meilisearch now supports multiple embedders, it has updated the vector submission format from arrays to JSON objects.

*   Previews format: `“_vectors”: [[0.0, 0.1]]`
*   New format: `“_vectors”: {“image2text”: [0.0, 0.1, …]}`

For detailed information on these updates, refer to the [documentation](https://meilisearch.dev.org.tw/docs/learn/experimental/vector_search?utm_campaign=release-v1-6&utm_source=blog).

For in-depth technical information, explore the [series of articles](/blog/spotify-inspired-hybrid-search-and-rust/?utm_campaign=release-v1-6&utm_source=blog on [Arroy](https://github.com/meilisearch/arroy), an open-source repository based on [Spotify’s Annoy](https://github.com/spotify/annoy) and developed in Rust. This library, created and maintained by the Meilisearch engine team, specializes in searching for vectors in a space that are near a specified query vector.

**Performance optimization**
----------------------------

### Improved indexing speed

We're thrilled to share a major enhancement in Meilisearch's indexing performance. Our recent tests, including scenarios with frequent and partial document updates, have shown impressive results: **a reduction in indexing time by up to 50%**, and in some cases, **even as much as 75%**. 

Thanks to our latest optimizations, Meilisearch now **stores and pre-computes less data**. Additionally, during document updates, it **re-indexes or deletes only the necessary data**. For instance, in an e-commerce dataset, updating the stock level of a product results in re-indexing just the 'stock' field, rather than the entire product document.

### Disk space usage reduction

Meilisearch reduces internal data storage, leading to a more **compact database size** on your disk. With a dataset of approximately 15Mb, we observed a **40% to 50% reduction in database size**.

This enhancement not only reduces the database size, but also **improves its stability**, making the space savings more evident as the number of documents increases.

**New feature: customize proximity precision**
----------------------------------------------

To further reduce indexing speed, Meilisearch now allows you to tailor the accuracy of the [proximity ranking rule](https://meilisearch.dev.org.tw/docs/learn/core_concepts/relevancy?utm_campaign=release-v1-6&utm_source=blog#3-proximity) to your specific needs.

The proximity ranking rule is computationally demanding and may lead to longer indexing times. Reducing its accuracy can greatly enhance performance, and in most scenarios, it will not substantially affect the relevancy of the results.

To adjust its impact [configure the `proximityPrecision` setting](https://meilisearch.dev.org.tw/docs/reference/api/settings?utm_campaign=release-v1-6&utm_source=blog#proximity-precision):

```JSON
curl \
  -X PATCH 'https://127.0.0.1:7700/indexes/books/settings/proximity-precision' \
  -H 'Content-Type: application/json'  \
  --data-binary '{
    "proximityPrecision": "byAttribute"
  }'
```

The default `proximityPrecision` setting is `byWord`, which calculates proximity based on exact word distances. 

The `byAttribute` setting considers words in the same attribute as proximate, regardless of their exact distance.

Using `byAttribute` can boost the indexing speed, but it might slightly change how relevant the results are. This becomes more noticeable in searches where it's important for words to be close to each other.

For example, when you're looking through song lyrics or long articles, like trying to find 'world war' in a bunch of Wikipedia pages, you might end up with results that contain these words but not necessarily close together or in the desired order. This is also true for [phrase searches](https://meilisearch.dev.org.tw/docs/reference/api/search?utm_campaign=release-v1-6&utm_source=blog#phrase-search) and for searches involving [multi-word synonyms](https://meilisearch.dev.org.tw/docs/learn/configuration/synonyms?utm_campaign=release-v1-6&utm_source=blog#multi-word-synonyms), where the specific combination of words is crucial.

**New feature: task queue webhook**
-----------------------------------

Meilisearch now offers a webhook feature to notify a custom URL when an asynchronous task finishes (either succeeds, fails, or gets canceled).

This feature is particularly useful for streamlining workflows, saving you from polling the tasks route.

Set up your webhook at launch using these environment variables:

```bash
MEILI_TASK_WEBHOOK_URL=https://mywebsite.com/my-super-webhook?user=1234&number=8

MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER='Bearer 12340987546wowowlolol'
```

You can also use the respective command-line options.

Once set up, the webhook sends out a payload in [JSON Lines (ndjson) format](https://meilisearch.dev.org.tw/docs/learn/core_concepts/documents?utm_campaign=release-v1-6&utm_source=blog#ndjson) to your specified URL, containing the list of finished tasks:

```json
//POST HTTP request to https://myproject.com/mywebhook?common=people

{"uid":4,"indexUid":"movie","status":"failed","type":"indexDeletion","canceledBy":null,"details.deletedDocuments":0,"error.message":"Index `movie` not found.","error.code":"index_not_found","error.type":"invalid_request","error.link":"https://docs.meilisearch.com/errors#index_not_found","duration":"PT0.001192S","enqueuedAt":"2022-08-04T12:28:15.159167Z","startedAt":"2022-08-04T12:28:15.161996Z","finishedAt":"2022-08-04T12:28:15.163188Z"}
{"uid":5,"indexUid":"movie","status":"failed","type":"indexDeletion","canceledBy":null,"details.deletedDocuments":0,"error.message":"Index `movie` not found.","error.code":"index_not_found","error.type":"invalid_request","error.link":"https://docs.meilisearch.com/errors#index_not_found","duration":"PT0.001192S","enqueuedAt":"2022-08-04T12:28:15.159167Z","startedAt":"2022-08-04T12:28:15.161996Z","finishedAt":"2022-08-04T12:28:15.163188Z"}
```

**Experimental feature: limit the number of batched tasks**
-----------------------------------------------------------

To speed up the indexing process, Meilisearch processes similar [tasks](https://meilisearch.dev.org.tw/docs/learn/async/asynchronous_operations?utm_campaign=release-v1-6&utm_source=blog#tasks-and-asynchronous-operations) in large batches. However, excessive [queued tasks](https://meilisearch.dev.org.tw/docs/learn/async/asynchronous_operations?utm_campaign=release-v1-6&utm_source=blog#task-queue) can occasionally cause crashes or stalls.

To control the number of batched tasks, set the limit at launch using either the command-line argument `--experimental-max-number-of-batched-tasks`, the `MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS` environment variable, or the [configuration file](https://meilisearch.dev.org.tw/docs/learn/configuration/instance_options?utm_campaign=release-v1-6&utm_source=blog#configuration-file).

**Contributors shout-out**
--------------------------

We are really grateful for all the community members who participated in this release.We would like to thank [@Karribalu](https://github.com/Karribalu) and [@vivek-26](https://github.com/vivek-26) for their help with [Meilisearch](https://github.com/meilisearch/meilisearch). We also want to send a special shout-out to our SDKs maintainers 🦸

* * *

And that’s it for v1.6! This release post highlights the most significant updates. For an exhaustive listing, read the [changelog on Github](https://github.com/meilisearch/meilisearch/releases/tag/v1.6.0).

Stay in the loop of everything Meilisearch by subscribing to [the newsletter](https://meilisearch.us2.list-manage.com/subscribe?u=27870f7b71c908a8b359599fb&id=79582d828e&ref=blog.meilisearch.com). To learn more about Meilisearch's future and help shape it, take a look at our [roadmap](https://roadmap.meilisearch.com/?utm_campaign=release-v1-6&utm_source=blog) and come participate in our [Product Discussions](https://github.com/meilisearch/product/discussions?ref=blog.meilisearch.com).

For anything else, join our developers community on [Discord](https://discord.meilisearch.com/?utm_campaign=release-v1-6&utm_source=blog).

Meilisearch 最新消息和公司動態

Meilisearch 1.7

推出混合搜尋：結合全文和語義搜尋以達到最佳平衡

Meilisearch 二月更新

什麼是向量嵌入？

什麼是向量資料庫？

雲端監控指標已推出！

Meilisearch 一月更新

Meilisearch vs Typesense

Meilisearch v1.6