cd /news/developer-tools/manticore-search-28-4-4-faster-knn-b… · home topics developer-tools article
[ARTICLE · art-58746] src=dev.to ↗ pub= topic=developer-tools verified=true sentiment=↑ positive

Manticore Search 28.4.4: Faster KNN, better conversational search, easier installs and more faceting controls

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.

read3 min views1 publishedJul 14, 2026

Manticore Search 28.4.4 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.

This post is a catch-up for everything shipped from 27.2.0 through 28.4.4.

Please review these before upgrading:

SPH_UDF_VERSION

to 12.dict=keywords_32k

embeddings_threads

KNN search now batches distance calculations during the rescore

pass. 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.

For 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.

Conversational search is now available through the /search

JSON API as well as SQL CALL CHAT

. 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.

CREATE CHAT MODEL

also gained custom_prompt

support, 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.

The quick-start install path is now simpler:

curl https://manticoresearch.com | sh

The 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.

For all options, run:

curl https://manticoresearch.com | sh -s help

Faceted search now supports zero-count facet buckets through SQL ZEROES

and JSON "zeroes": true

.

This 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

. Combined with max

-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.

Manticore now supports CREATE TABLE ... profile='relevance', plus stored per-table defaults for

ranker

boolean_mode

Based on our search quality tests, profile='relevance'

and 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.

embeddings_threads caps the CPU threads used for auto-embedding inserts,

ALTER TABLE ... REBUILD KNN

, 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.

This release includes 17 bug fixes. The most important ones are:

COUNT(DISTINCT ...)

GETFIELD

fetch errors or malformed replies instead of returning apparently successful rows with empty or untrusted stored-field values..tmp.spc.*

files from breaking later table rename, attach, or drop operations.SELECT

queries.SET

statements no longer fail under auth.здоров'ям

match здоров'я

under lemmatize_uk_all

.blend_mode

, restoring separator-stripped variants consistently for indexing and keyword extraction.percentiles

aggregations together with terms aggregations in the same /search

request on multi-chunk RT tables was fixed.For the complete list, see the changelog.

── more in #developer-tools 4 stories · sorted by recency
── more on @manticore search 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/manticore-search-28-…] indexed:0 read:3min 2026-07-14 ·