Customers Meilisearch is a partner of choice for OCTO Technology. The OCTO team chose Meilisearch for its client's complex needs due to the compatibility with the techstack and ease of implementation.
Release Meilisearch 1.8 Meilisearch 1.8 brings negative keyword search, improvements in search robustness and AI search, including new embedders.
Engineering How Meilisearch updates a database with millions of vector embeddings in under a minute How we implemented incremental indexing in our vector store.
State of search Full-text search vs vector search A comparative analysis of full-text search, vector search, and hybrid search.
Using Meilisearch Meilisearch 1.7 Meilisearch 1.7 stabilizes ranking score details, adds GPU support for Hugging Face embeddings, and integrates the latest OpenAI embedding models.
Company news Introducing hybrid search: combining full-text and semantic search for optimal balance Meilisearch's AI journey began last summer with vector search and storage. Today, we unveil hybrid search with autogenerated embedders, advancing our AI capabilities.
Company news Meilisearch February Updates 🥳 Join our launch event Join us on March 7th to discuss our recent releases and get a sneak peak of what’s coming on Meilisearch Cloud. Spoilers—hybrid search, new
State of search What are vector embeddings? In machine learning and AI, vector embeddings are a way to represent complex data, such as words, sentences, or even images as points in a vector space, using vectors of real numbers.
State of search What is a vector database? Vector databases are specialized systems to store, manage, and query data in the form of vector embeddings. They are optimized for similarity search, which involves finding the most similar items to a given query vector.
