Meilisearch

Meilisearch

Meilisearch is a developer-first search engine written in Rust, delivering sub-50ms full-text search responses with typo-tolerance, faceting, filtering, and geosearch out of the box. Its Community Edition is fully open source under MIT. It also supports hybrid (keyword + vector) search, making it a natural fit for RAG and semantic retrieval pipelines.

Key Features

• Instant search — returns results in under 50ms on datasets with millions of documents
• Typo tolerance — handles misspellings, partial matches, and word-order variations natively
• Hybrid search — combine BM25 keyword and vector similarity scores in a single query
• Faceted filtering — structured filters on any attribute with zero extra configuration
• Multi-tenant — built-in API key scoping and index-level access control
• Simple REST API — index documents, run searches, and manage synonyms via a clean HTTP API
• AI embeddings — built-in support for OpenAI, HuggingFace, Ollama, and REST embedder endpoints

Quick Start

curl -L https://install.meilisearch.com | sh
./meilisearch --master-key="masterKey"

from meilisearch import Client
client = Client('http://localhost:7700', 'masterKey')
index = client.index('movies')
index.add_documents([{"id": 1, "title": "2001: A Space Odyssey"}])
results = index.search('spac odyssy')  # typo-tolerant
print(results['hits'])

Install via ai-supply

npx ai-supply add meilisearch-ai-search-engine

Curated mirror of the open-source Meilisearch (MIT). Get it from the source.