Hybrid and semantic search

Hybrid search combines two search strategies: full-text search (matching keywords) and semantic search (matching meaning). This gives users the best of both worlds, returning results that are both textually and conceptually relevant.

Embedding models, not LLMs

Semantic search in Meilisearch relies on embedding models, not large language models (LLMs). This is an important distinction:

• Embedding models convert text into numerical vectors that capture meaning. They are small, fast, and inexpensive to run.
• LLMs (like GPT-4 or Claude) generate text and reason about it. They are much larger, slower, and more expensive.

Meilisearch uses embedding models for hybrid and semantic search, making it orders of magnitude cheaper and faster than LLM-based approaches. For conversational AI features that do use LLMs, see conversational search.

How it works

When you configure an embedder, Meilisearch automatically generates vector embeddings for every document in your index. You don’t need to compute or manage embeddings yourself.

• Batching: documents are grouped and sent to the embedding provider in optimized batches, minimizing API calls and maximizing throughput
• Caching: embeddings are stored and only regenerated when document content changes, so re-indexing unchanged documents costs nothing. Note that changing your embedder configuration (switching model, provider, or document template) triggers a full re-embedding of all documents, which may incur significant API costs for large indexes
• Rate limit handling: Meilisearch automatically retries when providers return rate limit errors, with no configuration needed
• Document templates: you control exactly which fields are embedded using Liquid templates, so the embedding captures the most relevant parts of each document

Automatic embedding generation

Updating embedder settings may trigger a full reindex. When you partially update an index’s embedder settings (for example, changing model, source, documentTemplate, dimensions, or pooling), Meilisearch may reindex all documents and regenerate their embeddings. For large indexes this can take a long time and, with paid providers, incur significant API costs.distribution is a notable exception: changing it does not trigger a reindex.

Smart result ranking

When you perform a hybrid search, Meilisearch does not simply concatenate keyword and semantic results. It uses a scoring system that automatically determines, for each query, whether full-text or semantic results are more relevant:

• A precise query like "iPhone 15 Pro Max 256GB" will favor keyword matches, because the exact terms appear in matching documents
• A descriptive query like "lightweight laptop for travel" will favor semantic matches, because the meaning matters more than the exact words
• Ambiguous queries get a balanced mix of both strategies

You can influence this balance with the semanticRatio parameter, but the default (0.5) works well for most use cases because Meilisearch’s scoring handles the blending intelligently.

When to use hybrid search

Supported embedder providers

Meilisearch supports a wide range of embedding providers. Some have native integrations, while others are available through the flexible REST embedder that works with any API.

Native integrations

Available via REST embedder

User-provided embeddings

If you pre-compute embeddings externally (for example, for images or audio content), you can supply them directly. See search with user-provided embeddings.

Embedder field compatibility

Different embedder sources accept different configuration fields. Setting an invalid field for a given source returns an error on settings update.