Software Engineer
Dmitrii Kuzmenkov is a Software Engineer contributing technical and product-oriented content for Manticore Search, covering topics such as AI-assisted search, fuzzy search, image search, demos, and practical search applications.
We tested full-text, vector, hybrid, image, geo, and AI search on 82,524 products. Here's where they go wrong, what they find, and the SQL behind the results.
An embedding model reads only the first few hundred tokens of a document and silently drops the rest. Manticore Search now splits long documents for you at INSERT time: add chunk_strategy to the vector column and pick one of five chunking strategies. No ingest pipeline, no text splitter library. On our own manual, recall@5 for deep content went from 55% to ...
Install Manticore Search with one command that sets up package sources, installs the package, and starts the service.
Meilisearch published a comparison of Meilisearch and Manticore Search. We tested the claims against the latest versions of both engines — here's what a fresh look shows, with reproducible commands.
How sharding and replication work in Manticore Search, from splitting a table across CPU cores on a single node to automatic multi-node distribution that maintains a replication factor on its own.
Released in Manticore Search 27.1.5, the new ONNX Runtime backend makes auto-embeddings ~14× faster on average than the previous SentenceTransformers/Candle path on the same hardware, same model, same weights — and the margin holds whether you run 1 client thread or 32.
Indexfox is an AI search widget that any website can drop in with a single .
Learn how Manticore Search streams backups directly to AWS S3 and S3-compatible storage without intermediate files or extra local disk space. The article covers multipart uploads, compression, encryption, restores, required permissions, and Kubernetes automation.
Learn how the MCP-Manticore server helps Cursor, Claude Code, and other AI assistants generate correct Manticore Search queries, create proper schemas, and explore your data without syntax errors.
Learn how to build fast, production-ready search autocomplete with Manticore Search using CALL AUTOCOMPLETE, CALL KEYWORDS, infix tricks, and integration patterns.
Install Manticore Search in one command on Linux or macOS:
curl https://manticoresearch.com | sh
For advanced installation options, see the full installation guide and the manual .