{"slug": "manticore-search-28-4-4-faster-knn-better-conversational-search-easier-installs", "title": "Manticore Search 28.4.4: Faster KNN, better conversational search, easier installs and more faceting controls", "summary": "Manticore Search released version 28.4.4 with faster KNN rescoring through batched distance calculations, conversational search now available via the JSON API, and a simplified install/upgrade path using a single curl command. The update also adds zero-count facet buckets for faceted search, per-table relevance defaults, and a server-level cap on embedding threads, along with 17 bug fixes.", "body_md": "[Manticore Search 28.4.4](https://manticoresearch.com/install/) has been released. This release brings faster KNN rescoring, more flexible conversational search, a simpler install and upgrade path, better faceting controls, per-table relevance defaults, and fixes across authentication, replication, SQL compatibility, distributed queries, and columnar/KNN internals.\n\nThis post is a catch-up for everything shipped from **27.2.0 through 28.4.4**.\n\nPlease review these before upgrading:\n\n`SPH_UDF_VERSION`\n\nto 12.`dict=keywords_32k`\n\n`embeddings_threads`\n\n[KNN search](https://manual.manticoresearch.com/Searching/KNN#KNN-vector-search) now batches distance calculations during the `rescore`\n\npass. After HNSW returns the candidate set, Manticore recomputes final full-precision distances and re-sorts the results. Batching that work reduces per-candidate overhead in the final stage of vector search.\n\nFor vector-heavy workloads, this takes work out of the part of the query that runs after candidate selection. Results do not change; the final ranking pass just has less overhead when many candidates are rescored.\n\n[Conversational search](https://manual.manticoresearch.com/Searching/Conversational_search) is now available through the `/search`\n\nJSON API as well as SQL `CALL CHAT`\n\n. That makes it easier to use Manticore's chat flow from applications that already talk to the HTTP API and do not want to add a separate SQL path just for chat requests.\n\n`CREATE CHAT MODEL`\n\nalso gained `custom_prompt`\n\nsupport, so answers can follow application-specific instructions such as citation rules, tone, response length, or formatting. The feature is still built on the same Manticore Search flow: retrieve relevant documents from an existing vectorized table, build context, keep conversation history, and return an answer with supporting sources.\n\nThe quick-start install path is now simpler:\n\n```\ncurl https://manticoresearch.com | sh\n```\n\nThe same installer can also upgrade an existing installation, list available versions, switch between stable and development repositories, and install a selected version. Package managers still remain the source of truth for installed files, repositories, services, and dependencies; the new path just removes the manual setup steps around them.\n\nFor all options, run:\n\n```\ncurl https://manticoresearch.com | sh -s help\n```\n\n[Faceted search](https://manual.manticoresearch.com/Searching/Faceted_search) now supports zero-count facet buckets through SQL `ZEROES`\n\nand JSON `\"zeroes\": true`\n\n.\n\nThis is a small but important UI feature. In e-commerce-style filtering, you often want to keep an option visible even when the current filter combination gives it a count of `0`\n\n. Combined with `max`\n\n-mode facet behavior, zero-count buckets make it easier to show selected, available, and currently unavailable choices without hiding part of the filter vocabulary from the user.\n\nManticore now supports [ CREATE TABLE ... profile='relevance'](https://manual.manticoresearch.com/Creating_a_table/Local_tables/Plain_and_real-time_table_settings#profile), plus stored per-table defaults for\n\n`ranker`\n\n`boolean_mode`\n\nBased on our search quality tests, `profile='relevance'`\n\nand the ranking settings it enables improve relevance in many cases. The application also no longer needs to repeat the same ranking parameters in every request.\n\n[ embeddings_threads](https://manual.manticoresearch.com/Server_settings/Searchd#embeddings_threads) caps the CPU threads used for auto-embedding inserts,\n\n`ALTER TABLE ... REBUILD KNN`\n\n, and text-to-vector KNN queries.This matters on shared hosts and mixed workloads. Embedding generation and KNN rebuilds can be CPU-heavy; a server-level cap makes those jobs easier to schedule without letting them take over the whole machine.\n\nThis release includes **17 bug fixes**. The most important ones are:\n\n`COUNT(DISTINCT ...)`\n\n`GETFIELD`\n\nfetch errors or malformed replies instead of returning apparently successful rows with empty or untrusted stored-field values.`.tmp.spc.*`\n\nfiles from breaking later table rename, attach, or drop operations.`SELECT`\n\nqueries.`SET`\n\nstatements no longer fail under auth.`здоров'ям`\n\nmatch `здоров'я`\n\nunder `lemmatize_uk_all`\n\n.`blend_mode`\n\n, restoring separator-stripped variants consistently for indexing and keyword extraction.`percentiles`\n\naggregations together with terms aggregations in the same `/search`\n\nrequest on multi-chunk RT tables was fixed.For the complete list, see the [changelog](https://manual.manticoresearch.com/Changelog#Version-28.4.4).", "url": "https://wpnews.pro/news/manticore-search-28-4-4-faster-knn-better-conversational-search-easier-installs", "canonical_source": "https://dev.to/sanikolaev/manticore-search-2844-faster-knn-better-conversational-search-easier-installs-and-more-32pf", "published_at": "2026-07-14 11:24:55+00:00", "updated_at": "2026-07-14 11:28:59.496446+00:00", "lang": "en", "topics": ["developer-tools", "machine-learning", "natural-language-processing", "ai-infrastructure"], "entities": ["Manticore Search"], "alternates": {"html": "https://wpnews.pro/news/manticore-search-28-4-4-faster-knn-better-conversational-search-easier-installs", "markdown": "https://wpnews.pro/news/manticore-search-28-4-4-faster-knn-better-conversational-search-easier-installs.md", "text": "https://wpnews.pro/news/manticore-search-28-4-4-faster-knn-better-conversational-search-easier-installs.txt", "jsonld": "https://wpnews.pro/news/manticore-search-28-4-4-faster-knn-better-conversational-search-easier-installs.jsonld"}}