Meilisearch Files

🐛 Performance improvements

Enhance hybrid search with filter performances

In previous versions of Meilisearch, mixing hybrid search with filters, as shown below, could multiply the search time by hundreds.

:::json
{
  "q": "hello world",
  "limit": 100,
  "filter": "tag=science"
  "hybrid": {
    "semanticRatio": 0.5,
    "embedder": "default"
  }
}

Meilisearch will now directly compute the semantic distance with the filtered candidates if only a few candidates come from the filter, instead of searching for the closest embeddings matching the filter in the vector database.