Received: from malur.postgresql.org ([217.196.149.56]) by arkaria.postgresql.org with esmtps (TLS1.3) tls TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384 (Exim 4.94.2) (envelope-from ) id 1tAVG5-00G6Pq-2o for pgsql-announce@arkaria.postgresql.org; Mon, 11 Nov 2024 14:19:12 +0000 Received: from localhost ([127.0.0.1] helo=malur.postgresql.org) by malur.postgresql.org with esmtp (Exim 4.94.2) (envelope-from ) id 1tAVG2-00Ee2t-Gr for pgsql-announce@arkaria.postgresql.org; Mon, 11 Nov 2024 14:19:11 +0000 Received: from magus.postgresql.org ([2a02:c0:301:0:ffff::29]) by malur.postgresql.org with esmtps (TLS1.3) tls TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384 (Exim 4.94.2) (envelope-from ) id 1tAVG1-00Ee2H-L7 for pgsql-announce@lists.postgresql.org; Mon, 11 Nov 2024 14:19:10 +0000 Received: from mahout.postgresql.org ([2001:4800:3e1:1::227]) by magus.postgresql.org with esmtps (TLS1.3) tls TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384 (Exim 4.94.2) (envelope-from ) id 1tAVFx-001N0G-N8 for pgsql-announce@lists.postgresql.org; Mon, 11 Nov 2024 14:19:09 +0000 DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=postgresql.org; s=20171124; h=Message-ID:Date:Reply-To:From:To:Subject: MIME-Version:Content-Type:Sender:Cc:Content-Transfer-Encoding:Content-ID: Content-Description:In-Reply-To:References; bh=wQVEPyZAgyJ3cZi3YE+rQgY8NAnYYWWlj63NAB27tnU=; b=fxmTzFWZxkJa5tHkz8KWI24CAA wyE3HNIvvFn9eIJuN6hnlqoh0AUi2YO81NyBpR8ZXqvF3Fsqg3eStVGLsu6ZZOXoE0WqNYwvgbvOa VW5IghfAhb6qsclvqBzp9Hw9TK9hKz3kzxMKMQUcY1Wj9zI2sbskEj3yEILw8MP08Mgn9LExAD7pg HXPnbgRUHoewf+ob/aQHM+fQ1y1Fsx1JcbyUoFdCNZRDQ3VrFNEYmzReCAuxXPl0W7NxCkqgHnVKI W6KDEu0621O98M/tBk0b58TYk8PbAl2kZ/JZPq6KKNYOR/+wDRUVXoXOlbvp/xysxNyR2vRW6pYdz jJkCoJ/g==; Received: from wrigleys.postgresql.org ([2a02:16a8:dc51::60]) by mahout.postgresql.org with esmtps (TLS1.3) tls TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384 (Exim 4.94.2) (envelope-from ) id 1tAVFw-0041mj-4L for pgsql-announce@lists.postgresql.org; Mon, 11 Nov 2024 14:19:05 +0000 Received: from localhost ([127.0.0.1] helo=wrigleys.postgresql.org) by wrigleys.postgresql.org with esmtp (Exim 4.94.2) (envelope-from ) id 1tAVFu-005kVW-7u for pgsql-announce@lists.postgresql.org; Mon, 11 Nov 2024 14:19:03 +0000 Content-Type: multipart/mixed; boundary="===============1629215360000092767==" MIME-Version: 1.0 Subject: pgvector 0.8.0 Released! To: PostgreSQL Announce From: pgvector via PostgreSQL Announce Reply-To: announce@pgvector.org Date: Mon, 11 Nov 2024 14:18:45 +0000 Message-ID: <173133472572.709.14743591049493026466@wrigleys.postgresql.org> X-Auto-Response-Suppress: All Auto-Submitted: auto-generated X-pglister-tags: related X-pglister-tagsig: e8cbfeb950662eaa0bb756adbece4340565c59a8f51ba97658cdf6a82be002b9 List-Id: List-Help: List-Subscribe: List-Post: List-Owner: List-Archive: Archived-At: Precedence: bulk --===============1629215360000092767== Content-Type: multipart/alternative; boundary="===============8026057826315361756==" MIME-Version: 1.0 --===============8026057826315361756== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable [pgvector](https://github.com/pgvector/pgvector/), an open-source PostgreSQ= L extension that provides vector similarity search capabilities, has releas= ed [v0.8.0](https://github.com/pgvector/pgvector/releases/tag/v0.8.0). This= release includes features that improve query performance and usability whe= n using filters (e.g. the `WHERE` clause), and performance improvements for= searching and building [HNSW](https://github.com/pgvector/pgvector?tab=3Dr= eadme-ov-file#hnsw) indexes. This latest version of pgvector has a variety of improvements for filtering= . This includes an update to how PostgreSQL estimates when to scan a approx= imate nearest neighbor (ANN) index like HNSW and IVFFlat, which could lead = PostgreSQL to select a B-tree or other index that more efficiently executes= the query. If you can achieve the same query performance without using an = ANN index, this is usually preferable as it lets you achieve 100% recall, o= r high relevancy searches. Additionally, this pgvector release adds [iterative index scans](https://gi= thub.com/pgvector/pgvector?tab=3Dreadme-ov-file#iterative-index-scans), whi= ch is a technique to prevent "overfiltering" or not returning enough result= s to satisfy the conditions of a query. You can enable iterative scanning w= ith the `hnsw.iterative_scan` and `ivfflat.iterative_scan` parameters for H= NSW and IVFFlat indexes respectively, and if an initial index scan doesn't = satisfy the query conditions, pgvector will continue to search the index un= til it hits a configurable threshold (`hnsw.max_scan_tuples` and `ivfflat.m= ax_probes`).=20 For more information, please see the [CHANGELOG for 0.8.0](https://github.c= om/pgvector/pgvector/blob/master/CHANGELOG.md#080-2024-10-30): [https://github.com/pgvector/pgvector/blob/master/CHANGELOG.md#080-2024-10-= 30](https://github.com/pgvector/pgvector/blob/master/CHANGELOG.md#080-2024-= 10-30) For more information about pgvector, including how to get started, please v= isit the [project repository on GitHub](https://github.com/pgvector/pgvecto= r): [https://github.com/pgvector/pgvector](https://github.com/pgvector/pgvector) --===============8026057826315361756== Content-Type: text/html; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable pgvector 0.8.0 Released!
 

pgvector 0.8.0 Released!

pgvector, a= n open-source PostgreSQL extension that provides vector similarity search c= apabilities, has released v0= .8.0. This release includes features that improve query performance and= usability when using filters (e.g. the WHERE clause), and per= formance improvements for searching and building HNSW indexes.

This latest version of pgvector has a varie= ty of improvements for filtering. This includes an update to how PostgreSQL= estimates when to scan a approximate nearest neighbor (ANN) index like HNS= W and IVFFlat, which could lead PostgreSQL to select a B-tree or other inde= x that more efficiently executes the query. If you can achieve the same que= ry performance without using an ANN index, this is usually preferable as it= lets you achieve 100% recall, or high relevancy searches.

Additionally, this pgvector release adds iterati= ve index scans, which is a technique to prevent "overfiltering" or not = returning enough results to satisfy the conditions of a query. You can enab= le iterative scanning with the hnsw.iterative_scan and i= vfflat.iterative_scan parameters for HNSW and IVFFlat indexes respec= tively, and if an initial index scan doesn't satisfy the query conditions, = pgvector will continue to search the index until it hits a configurable thr= eshold (hnsw.max_scan_tuples and ivfflat.max_probes).

For more information, please see the CHANGELOG for = 0.8.0:

https://github.com/pgvector/pgvector/blob/master/CH= ANGELOG.md#080-2024-10-30

For more information about pgvector, includ= ing how to get started, please visit the project= repository on GitHub:

https://github.c= om/pgvector/pgvector
This email was sent to you from pgvector. It was delivered on their behalf = by the PostgreSQL project. Any questions about the content of the message shou= ld be sent to pgvector.

You were sent this email as a subscriber of the pgsql-announce mai= linglist, for the content tag Related Open Source. To unsubscribe from further emails, or change which emails you want to receive, please click th= e personal unsubscribe link that you can find in the headers of this email, or visit https://lists.postgresql.org/unsubscribe/.
 
--===============8026057826315361756==-- --===============1629215360000092767==--