Meilisearch v1.8 introduces new changes and optimizations related to the Hybrid search with the addition of new models and embedders like REST embedders and the Ollama model. This version also focuses on stability by adding more security around the search requests. Finally, we introduce the negative operator to exclude specific terms from a search query.

🧰 All official Meilisearch integrations (including SDKs, clients, and other tools) are compatible with this Meilisearch release. Integration deployment happens between 4 to 48 hours after a new version becomes available.

Some SDKs might not include all new features. Consult the project repository for detailed information. Is a feature you need missing from your chosen SDK? Create an issue letting us know you need it, or, for open-source karma points, open a PR implementing it (we'll love you for that ❤️).

This release introduces a few changes to hybrid search.): a new distribution embedder setting, support for two new embedder sources, and breaking changes to hybrid and semantic search ranking score.

🗣️ This is an experimental feature and we need your help to improve it! Share your thoughts and feedback on this GitHub discussion.

Done by @dureuill and @jakobklemm in #4456, #4537, #4509, #4548, #4549.

To increase search response times and reduce bandwidth usage:

• Meilisearch no longer returns the vector field will in the search response
• Meilisearch no longer returns the _semanticScore in the search response. Use _rankingScore in its place
• Meilisearch no longer displays the query vector and its value when"showRankingScoreDetails": true

Ollama is a framework for building and running language models locally. Configure it by supplying an embedder object to the /settings endpoint:

"default": {
  "source": "ollama",
  "url": "http://localhost:11434/api/embeddings",  // optional, fetched from MEILI_OLLAMA_URL environment variable if missing
  "apiKey": "<foobarbaz>",  // optional
  "model": "nomic-embed-text",
  "documentTemplate": "A document titled '{{doc.title}}' whose description starts with {{doc.overview|truncatewords: 20}}"
}

Meilisearch now also supports any embedder with a RESTful interface. Configure it by supplying an embedder object to the /settings endpoint:

"default": {
  "source": "rest",
  "url": "http://localhost:12345/api/v1/embed", //Mandatory, full URL to the embedding endpoint
  "apiKey": "187HFLDH97CNHN", // Optional, passed as Bearer in the Authorization header
  "dimensions": 512, // Optional, inferred with a dummy request if missing
  "documentTemplate": "A document titled '{{doc.title}}' whose description starts with {{doc.overview|truncatewords: 20}}"
  "inputField": ["data", "text"], // Optional, defaults to []
  "inputType": "text", // Optional, either "text" or "textArray", defaults to text
  "query": { // Optional, defaults to {}
    "model": "MODEL_NAME",
    "dimensions": 512
  },
  "pathToEmbeddings": ["data"], // Optional, defaults to []
  "embeddingObject": ["embedding"] // Optional, defaults to []
}

Use distribution to apply an affine transformation to the _rankingScore of semantic search results. This can help to compare _rankingScores of semantic and keyword search results and improve result ranking.

"default": {
  "source": "huggingFace",
  "model": "MODEL_NAME",
  "distribution": {  // describes the natural distribution of results
    "mean": 0.7, // mean value
    "sigma": 0.3 // variance
  }
}

• Hide the API key in settings and task queue (#4533) @dureuill
• Return keyword search results even in case of a failure of the embedding when performing hybrid searches (#4548) @dureuill
• For hybrid or semantic search requests, add a semanticHitCount field at the top of the search response indicating the number of hits originating from the semantic search (#4548) @dureuill

Search queries can now contain a negative keyword to exclude terms from the search. Use the - operator in front of a word or a phrase to make sure no document that contains those words are shown in the results:

curl \
  -X POST 'http://localhost:7700/indexes/places/search' \
  -H 'Content-Type: application/json' \
  --data-binary '{ "q": "-escape room" }'

• -escape returns any document that does not contain escape
• -escape room returns documents containing room but not escape
• -"on demand" returns any document that does not contain "on demand"

Done by @Kerollmops in #4535.

To avoid crashes and performance issues, Meilisearch now interrupts search requests that take more than 1500ms to complete.

Use the /settings endpoint to customize this value:

curl \
  -X PATCH 'http://localhost:7700/indexes/movies/settings' \
  -H 'Content-Type: application/json' \
  --data-binary '{
    "searchCutoffMs": 150
  }'

The default value of the searchCutoffMs setting is null and corresponds to a 1500ms timeout.

Done by @irevoire in #4466.

This release introduces a limit for concurrent search requests to prevent Meilisearch from consuming an unbounded amount of RAM and crashing.

The default number of requests in the queue is 1000. Relaunch your self-hosted instance with --experimental-search-queue-size to change this limit:

./meilisearch --experimental-search-queue-size 100

👉 This limit does NOT impact the search performance. It only affects the number of enqueued search requests to prevent security issues.

🗣️ This is an experimental feature and we need your help to improve it! Share your thoughts and feedback on this GitHub discussion.

Done by @irevoire in #4536

• Increase indexing speed when updating settings (#4504) @ManyTheFish
• Update search logs: do not display hits in the search output for DEBUG log level (#4580) @irevoire
• The sortFacetValuesBy setting now impacts the /facet-search route (#4476) @Kerollmops
• Prometheus experimental feature: add status code label to the HTTP request counter (#4373) @rohankmr414
• Tokenizer improvements by bumping charabia to 0.8.8 (#4511) @6543
  • Support markdown formatted code blocks
  • Improve Korean segmentation to correctly use the context ID registered in the dictionary
  • Add \t as recognized separator
  • Make the pinyin-normalization optional - this can be reactivated by enabling the chinese-normalization-pinyin feature

• Fix crash when putting empty separator (#4574) @ManyTheFish
• Stop crashing when panic occurs in thread pool (#4593) @Kerollmops
• Always show facet numbers in alpha order in the facet distribution (#4581) @Kerollmops
• Prometheus experimental feature: fix the HTTP request duration histogram bucket boundaries to follow the OpenTelemetry spec (#4530) @rohankmr414
• Hybrid search experimental feature: fix an error on Windows when generating embeddings (#4549) @dureuill

• Dependency updates
  • Bump mio from 0.8.9 to 0.8.11 (#4457)
  • Upgrade rustls to 0.21.10 and ring to 0.17 (#4400) @hack3ric
• CIs and tests
  • Add automation to create openAPI issues (#4520) @curquiza
  • Add tests to check when the field limit is reached (#4463) @irevoire
  • Allow running benchmarks without sending results to the dashboard (#4475) @dureuill
  • Create automation when creating GitHub milestones to create update-version issue (#4416) @curquiza
  • Fix reason param when benches are triggered from a comment (#4483) @dureuill
• Documentation
  • Fix milli link in contributing doc (#4499) @mohsen-alizadeh
  • Fix some typos in comments (#4546) @redistay
  • Remove repetitive words in Benchmark docs (#4526) @availhang
  • Remove repetitive words in code-base comments (#4491) @shuangcui
  • Update sprint_issue.md (#4516) @curquiza
  • Add documentation for benchmarks (#4477) @dureuill
  • Fix typos (#4542) @brunoocasali
• Misc
  • Update cargo version (#4474) @curquiza
  • Remove useless analytics (#4578) @irevoire
  • Fix milli/Cargo.toml for usage as dependency via git (#4547) @Toromyx

❤️ Thanks again to our external contributors:

• Meilisearch: @availhang, @hack3ric, @jakobklemm, @mohsen-alizadeh, @redistay, @rohankmr414, @shuangcui, @Toromyx, @6543.
• Charabia: @Gusted, @mosuka, @6543

⚠️ Since this is a release candidate (RC), we do NOT recommend using it in a production environment. Is something not working as expected? We welcome bug reports and feedback about new features.

• Remove useless analytics by @irevoire in https://github.com/meilisearch/meilisearch/pull/4578
• Stop crashing when panic occurs in thread pool by @Kerollmops in https://github.com/meilisearch/meilisearch/pull/4593
• Fix embedders api by @ManyTheFish in https://github.com/meilisearch/meilisearch/pull/4600
• Fix embeddings settings update by @ManyTheFish in https://github.com/meilisearch/meilisearch/pull/4597

• Avoid clearing db in transform by @ManyTheFish in https://github.com/meilisearch/meilisearch/pull/4504
• Update the search logs by @irevoire in https://github.com/meilisearch/meilisearch/pull/4580
• Always show facet numbers in alpha order in the facet distribution by @Kerollmops in https://github.com/meilisearch/meilisearch/pull/4581
• increase the default search time budget from 150ms to 1.5s by @irevoire in https://github.com/meilisearch/meilisearch/pull/4576
• Update charabia v0.8.9 by @ManyTheFish in https://github.com/meilisearch/meilisearch/pull/4583

Full Changelog: https://github.com/meilisearch/meilisearch/compare/v1.8.0-rc.0...v1.8.0-rc.1

⚠️ Since this is a release candidate (RC), we do NOT recommend using it in a production environment. Is something not working as expected? We welcome bug reports and feedback about new features.

Meilisearch v1.8 introduces new changes and optimizations related to the Hybrid search with the addition of new models and embedders like REST embedders and the Ollama model. This version also focuses on stability by adding more security around the search requests. Finally, we introduce the negative operator to exclude specific terms from a search query.

Full description of hybrid search changes here.

🗣️ This is an experimental feature and we need your help to improve it! Share your thoughts and feedback on this GitHub discussion.

Done by @dureuill and @jakobklemm in #4456, #4537, #4509, #4548, #4549.

• To ease the search answer speed and bandwidth, Meilisearch no longer returns the query vector in the search response. The vector field will not be displayed.
• _semanticScore is no longer returned in the search response. The _rankingScore field has the same value as the _semanticScore, and should be used in its place. To get the _rankingScore value, add "showRankingScore": true to the search query.
• When adding "showRankingScoreDetails": true to a semantic search query, the vector and its value are no longer displayed to improve the search speed and bandwidth use.

New embedder sources have been added

• ollama source
• rest source

REST embedder

Meilisearch now supports any REST embedder. You can set them up with the following configuration:

"default": {
  "source": "rest", // 👈 Use the REST source
  "url": "http://localhost:12345/api/v1/embed",
  // ☝️ Mandatory, full URL to the embedding endpoint
  "apiKey": "187HFLDH97CNHN",
  // ☝️ optional, will be passed as Bearer in the Authorization header
  "dimensions": 512,
  // ☝️ optional, inferred with a dummy request if missing
  "documentTemplate": "blabla",
  "inputField": ["data", "text"],
  // ☝️ inject texts in data.text in the query
  // Optional, defaults to []
  "inputType": "text", // text or textArray
  // ☝️ inject a single text
  // Optional, defaults to text
  "query": {
    // A JSON object describing other fields to send in a query
    // for example
    "model": "name-of-your-model",
    "dimensions": 512
  },
  // ☝️ A JSON object describing other fields to send in a query
  // Optional, defaults to {}
  "pathToEmbeddings": ["data"],
  // ☝️ look at embeddings in "data" in the response
  // Optional, defaults to []
  "embeddingObject": ["embedding"]
  // ☝️ look at the embedding inside of "embedding"
  // Optional, defaults to []
}

Here is an example of setting OpenAI embedder with the rest source:

{
  "source": "rest",
  "apiKey": "<your-openai-api-key>",
  "dimensions": 1536,
  "url": "https://api.openai.com/v1/embeddings",
  "query": {
    "model": "text-embedding-ada-002"
  },
  "inputField": ["input"],
  "inputType": "textArray",
  "pathToEmbeddings": ["data"],
  "embeddingObject": ["embedding"]
}

Ollama model

Here is how to set up the Ollama model:

"default": {
  "source": "ollama", // 👈 Use the REST source
  "url": "http://localhost:11434/api/embeddings",
  // ☝️ optional, fetched from MEILI_OLLAMA_URL environment variable if missing
  "apiKey": "<foobarbaz>",
  // ☝️ optional
  "model": "nomic-embed-text",
  "documentTemplate": "blabla" // like for openAI and huggingFace sources
}

When setting an embedder, you can now set the distribution shift.

"default": {
  "source": "huggingFace", // supported for any source
  "model": "some/model",
  "distribution": {  // describes the natural distribution of results
    "mean": 0.7, // mean value
    "sigma": 0.3 // variance
  }
}

The “distribution shift” is an affine transformation applied to the _rankingScore of a semantic search result with the aim of making the comparison to the _rankingScore of a keyword search result more meaningful.

• Hide the API key in settings and task queue (#4533) @dureuill
• Return the keyword search results even in case of a failure of the embedding (#4548) @dureuill
• For hybrid or semantic search requests, add a semanticHitCount field at the top of the search response indicating the number of hits originating from the semantic search (#4548) @dureuill

Search queries can now contain a negative keyword to exclude terms from the search. Use the - operator in front of a word or a phrase to make sure no document that contains those words are shown in the results.

• -escape returns a placeholder search without any document contains the escape word.
• -escape room returns only documents containing the room word but not the escape one.
• -"on demand" returns a placeholder search but without any document containing the "on demand" phrase.

Done by @Kerollmops in #4535.

To avoid any crash and performance issues, Meilisearch now stops search requests lasting more than 150ms.

If you want to customize this value, you can update the searchCutoffMs settings (value in ms):

curl \
  -X PATCH 'http://localhost:7700/indexes/movies/settings' \
  -H 'Content-Type: application/json' \
  --data-binary '{
    "searchCutoffMs": 50
  }'

The default value of the searchCutoffMs setting is null and corresponds to 150ms.

Done by @irevoire in #4466.

Meilisearch now limits the number of search requests waiting to be processed to avoid consuming an unbounded amount of RAM and crashing. So a queue of search requests waiting to be processed has been introduced.

👉 This change does NOT impact the search performance, but only the number of enqueued search requests to prevent from any security issues.

The default number of requests in the queue is 1000.

To change this limit, use the experimental CLI flag:

./meilisearch --experimental-search-queue-size 100

🗣️ This is an experimental flag and we need your help to improve it! Share your thoughts and feedback on this GitHub discussion.

Done by @irevoire in #4536

• The sortFacetValuesBy setting now impacts the /facet-search route (#4476) @Kerollmops
• Related to Prometheus experimental feature: add status code label to the HTTP request counter (#4373) @rohankmr414
• Tokenizer improvements by bumping charabia to 0.8.8 (#4511) @6543
  • Support markdown formatted code blocks
  • Improve Korean segmentation to correctly use the context ID registered in the dictionary

• Related to Prometheus experimental feature: fix the HTTP request duration histogram bucket boundaries to follow the OpenTelemetry spec (#4530) @rohankmr414
• Related to Hybrid search experimental feature: fix an error on Windows when generating embeddings (#4549) @dureuill

• Dependencies upgrade
  • Bump mio from 0.8.9 to 0.8.11 (#4457)
  • Upgrade rustls to 0.21.10 and ring to 0.17 (#4400) @hack3ric
• CIs and tests
  • Add automation to create openAPI issue (#4520) @curquiza
  • Add tests when the field limit is reached (#4463) @irevoire
  • Allow running benchmarks without sending results to the dashboard (#4475) @dureuill
  • Create automation when creating Milestone to create update-version issue (#4416) @curquiza
  • Fix reason param when benches are triggered from a comment (#4483) @dureuill
• Documentation
  • Fix milli link in contributing doc (#4499) @mohsen-alizadeh
  • Fix some typos in comments (#4546) @redistay
  • Remove repetitive words in Benchmark docs (#4526) @availhang
  • Remove repetitive words in code-base comments (#4491) @shuangcui
  • Update sprint_issue.md (#4516) @curquiza
  • Add documentation for benchmarks (#4477) @dureuill
  • Fix typos (#4542) @brunoocasali
• Misc
  • Update cargo version (#4474) @curquiza
  • Fix milli/Cargo.toml for usage as dependency via git (#4547) @Toromyx

❤️ Thanks again to our external contributors:

• Meilisearch: @availhang, @hack3ric, @jakobklemm, @mohsen-alizadeh, @redistay, @rohankmr414, @shuangcui, @Toromyx, @6543.
• Charabia: @mosuka, @6543

• Update grenad to fix rare DB corruption by @dureuill in https://github.com/meilisearch/meilisearch/pull/4562

After a security flaw has been discovered in the implementation of http2, it’s possible for an attacker to slow down your instance; see this link for more information.

This PR updates our web stack to the latest version containing a fix against this attack.

• update h2 by @irevoire in https://github.com/meilisearch/meilisearch/pull/4553
• Update version for the next release (v1.7.5) in Cargo.toml by @meili-bot in https://github.com/meilisearch/meilisearch/pull/4554

Full Changelog: https://github.com/meilisearch/meilisearch/compare/v1.7.4...v1.7.5

• Fix regression introduced in v1.7.1, where adding sortable and filterable nested attributes would never trigger a reindexing operation by @dureuill in https://github.com/meilisearch/meilisearch/pull/4539

Thanks @curquiza for the report ❤️

This new release doesn’t contain any fixes or features. We make it only because the release-v1.7.2 had an issue and didn’t contain all the required assets (Linux, macOS, and Windows x86 binaries were missing).

• Update version for the next release (v1.7.3) in Cargo.toml by @meili-bot in https://github.com/meilisearch/meilisearch/pull/4519

Full Changelog: https://github.com/meilisearch/meilisearch/compare/v1.7.2...v1.7.3

• Adds a timeout to the webhook in https://github.com/meilisearch/meilisearch/pull/4508

Full Changelog: https://github.com/meilisearch/meilisearch/compare/v1.7.1...v1.7.2

• Skip reindexing when modifying unknown faceted fields by @Kerollmops in https://github.com/meilisearch/meilisearch/pull/4479