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

> Source: <https://dev.to/sanikolaev/manticore-search-2844-faster-knn-better-conversational-search-easier-installs-and-more-32pf>
> Published: 2026-07-14 11:24:55+00:00

[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.

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](https://manual.manticoresearch.com/Searching/KNN#KNN-vector-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](https://manual.manticoresearch.com/Searching/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](https://manual.manticoresearch.com/Searching/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'](https://manual.manticoresearch.com/Creating_a_table/Local_tables/Plain_and_real-time_table_settings#profile), 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](https://manual.manticoresearch.com/Server_settings/Searchd#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](https://manual.manticoresearch.com/Changelog#Version-28.4.4).
