MyGit

v1.7.0-rc.0

meilisearch/meilisearch

版本发布时间: 2024-02-12 19:38:10

meilisearch/meilisearch最新发布版本:v1.10.1(2024-09-02 17:59:14)

⚠️ 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 v1.7.0 mostly focuses on improving v1.6.0 features, indexing speed and hybrid search. GPU computing is now supported.

New features and improvements 🔥

Improve AI with Meilisearch (experimental feature)

🗣️ AI work is still experimental, and we need your help to improve it! Share your thoughts and feedback on this GitHub discussion.

To use it, you need to enable vectorSearch through the /experimental-features route.

💡 More documentation about AI search with Meilisearch here.

Add new OpenAI embedding models & ability to override their models dimensions

When using OpenAi as source in your embedders index settings (an example here), you can now specify two new models:

The new models:

It means that it is now possible to pass the dimensions field when using the OpenAi source. This was previously only available for the userProvided source in the previous releases.

There are some rules, though, which we detail with these examples:

"embedders": {
  "large": {
    "source": "openAi",
    "model": "text-embedding-3-large",
    "dimensions": 512 // must be >0, must be <= 3072 for "text-embedding-3-large"
  },
  "small": {
    "source": "openAi",
    "model": "text-embedding-3-small",
    "dimensions": 1024 // must be >0, must be <= 1536 for "text-embedding-3-small"
  },
  "legacy": {
    "source": "openAi",
    "model": "text-embedding-ada-002",
    "dimensions": 1536 // must =1536  for "text-embedding-ada-002"
  },
  "omitted_dimensions": { // uses the default dimension
    "source": "openAi",
    "model": "text-embedding-ada-002",
  }
}

Done in #4375 by @Gosti.

Add GPU support to compute embeddings

Enabling the CUDA feature allows using an available GPU to compute embeddings with a huggingFace embedder. On an AWS Graviton 2, this yields a x3 - x5 improvement on indexing time.

👇 How to enable GPU support through CUDA for HuggingFace embedding generation:

Prerequisites

Steps

  1. Follow the guide to install the CUDA dependencies
  2. Clone Meilisearch: git clone https://github.com/meilisearch/meilisearch.git
  3. Compile Meilisearch with the cuda feature: cargo build --release --package meilisearch --features cuda
  4. In the freshly compiled Meilisearch, enable the vector store experimental feature:
❯ curl \
  -X PATCH 'http://localhost:7700/experimental-features/' \
  -H 'Content-Type: application/json'  \
--data-binary '{ "vectorStore": true }'
  1. Add an HuggingFace embedder to the settings:
curl \
-X PATCH 'http://localhost:7700/indexes/your_index/settings/embedders' \
-H 'Content-Type: application/json' --data-binary \
'{ "default": { "source": "huggingFace" } }'

Done by @dureuill in #4304.

Improve indexing speed & reduce memory crashes

Stabilize scoreDetails feature

In v1.3.0, we introduced the experimental feature scoreDetails. We got enough positive feedback on the feature, and we now stabilize it, making this feature enabled by default.

View detailed scores per ranking rule for each document with the showRankingScoreDetails search parameter:

curl \
  -X POST 'http://localhost:7700/indexes/movies/search' \
  -H 'Content-Type: application/json' \
  --data-binary '{ "q": "Batman Returns", "showRankingScoreDetails": true }'

When showRankingScoreDetails is set to true, returned documents include a _rankingScoreDetails field. This field contains score values for each ranking rule.

"_rankingScoreDetails": {
  "words": {
    "order": 0,
    "matchingWords": 1,
    "maxMatchingWords": 1,
    "score": 1.0
  },
  "typo": {
    "order": 1,
    "typoCount": 0,
    "maxTypoCount": 1,
    "score": 1.0
  },
  "proximity": {
    "order": 2,
    "score": 1.0
  },
  "attribute": {
    "order": 3,
    "attributes_ranking_order": 0.8,
    "attributes_query_word_order": 0.6363636363636364,
    "score": 0.7272727272727273
  },
  "exactness": {
    "order": 4,
    "matchType": "noExactMatch",
    "matchingWords": 0,
    "maxMatchingWords": 1,
    "score": 0.3333333333333333
  }
}

Done by @dureuill in #4389.

Logs improvements

We made some changes regarding our logs to help with debugging and bug reporting.

Done by @irevoire in #4391

Log format change

⚠️ If you did any automation based on Meilisearch logs, be aware of the changes. More information here.

The default log format evolved slightly from this:

[2024-02-06T14:54:11Z INFO  actix_server::builder] starting 10 workers

To this:

2024-02-06T13:58:14.710803Z  INFO actix_server::builder: 200: starting 10 workers

Experimental: new routes to manage logs

This new version of Meilisearch introduces 3 new experimental routes

💡 More information in the New experimental routes section of this file.

⚠️ Some remarks on this POST /logs/stream route:

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

⚠️ Experimental features may be incompatible between Meilisearch versions.

Other improvements

Misc

❤️ Thanks again to our external contributors:

相关地址:原始地址 下载(tar) 下载(zip)

1、 meilisearch-linux-aarch64 121.03MB

2、 meilisearch-linux-amd64 122.39MB

3、 meilisearch-macos-amd64 114.02MB

4、 meilisearch-macos-apple-silicon 112.48MB

5、 meilisearch-windows-amd64.exe 113.59MB

查看:2024-02-12发行的版本