Meilisearch 1.8
Starting with Meilisearch 1.8, you can use any embedder accessible via a REST API. Here’s how to configure an OpenAI embedder with the rest source:
Depending on the embedding model, vector embeddings are not always uniformly distributed within the vector space. When vectors are overly clustered, semantic search scores can be very closely ranked. As a result of semantic scores being packed, hybrid results might have sub-optimal relevancy.
To address this issue, you can now shift the distribution of results with an affine transformation. This transformation normalizes semantic scores to prevent them from clustering too high or too tightly, making them more comparable to the keyword scores.
This allows for a more effective comparison of _rankingScore between semantic and keyword search results, leading to improved results ranking.
To speed up the search response and reduce bandwidth usage, Meilisearch v1.8 no longer returns the following fields in the search responses:
