vector-search
Perform vector-based searches in Meilisearch indexes using a JSON array or text query, with options for hybrid search, filters, and attribute selection to refine results.
Instructions
Perform a vector search in a Meilisearch index
Input Schema
Name | Required | Description | Default |
---|---|---|---|
attributes | No | Attributes to include in the vector search | |
embedder | No | Name of the embedder to use (if omitted, a 'vector' must be provided) | |
filter | No | Filter to apply (e.g., 'genre = horror AND year > 2020') | |
hybrid | No | Whether to perform a hybrid search (combining vector and text search) | |
hybridRatio | No | Ratio of vector vs text search in hybrid search (0-1, default: 0.5) | |
indexUid | Yes | Unique identifier of the index | |
limit | No | Maximum number of results to return (default: 20) | |
offset | No | Number of results to skip (default: 0) | |
query | No | Text query to search for (if using 'embedder' instead of 'vector') | |
vector | Yes | JSON array representing the vector to search for |