#PGVector
Set up Discourse for development on Fedora Linux Just tried running a local install and ran into issues with pgvector. On Fedora the packaged version of pgvector is 0.6.2 and it seems I need to com...

Origin | Interest | Match
Set up Discourse for development on Fedora Linux
Just tried running a local install and ran into issues with pgvector. On Fedora the packaged version of pgvector is 0.6.2 and it seems I need to compile from source to get a more recent one. Then ran into conflicts trying to build pgvector, which seems to require postgresql-private-devel package that had conflicting requests with libpq-devel. Resolved it by: * sudo dnf install postgresql-server-devel --allowerasing * Build pgvector * Check installed version sudo -u postgres psql discourse_development -c "SELECT * FROM pg_available_extensions WHERE name = 'vector';" * sudo systemctl restart postgresql
meta.discourse.org
November 12, 2025 at 11:14 AM
It uses semantic searching and storage of all the memories using pgvector... not shown in the screeenshot 🙃
November 10, 2025 at 10:36 PM
Разбираю свой фотоархив Сделал поиск по личному архиву фотографий с применением трех нейросетей, векторно...

#python #django #torch #pgvector #transformers #giga-embeddings #mistral #llava

Origin | Interest | Match
November 10, 2025 at 5:56 AM
rag-memory 0.19.2 PostgreSQL pgvector-based RAG memory system with MCP server

Interest | Match | Feed
Origin
pypi.org
November 10, 2025 at 3:21 AM
rag-memory 0.19.2 PostgreSQL pgvector-based RAG memory system with MCP server

Origin | Interest | Match
Client Challenge
pypi.org
November 10, 2025 at 3:22 AM
今日のGitHubトレンド

simstudioai/sim
本リポジトリは、AIエージェントのワークフローを迅速に構築およびデプロイするためのプラットフォーム「Sim」を提供する。
セルフホスト型(NPM、Docker)またはクラウドホスト型で利用可能であり、OllamaによるローカルAIモデルの実行や、pgvectorを用いたベクトル埋め込みなどの高度なAI機能に対応した開発・実行環境を提供する。
GitHub - simstudioai/sim: Open-source platform to build and deploy AI agent workflows.
Open-source platform to build and deploy AI agent workflows. - simstudioai/sim
github.com
November 8, 2025 at 11:14 AM
Getting Started with Repository Vector Search in Spring Data With Spring Data, vector search is supported via new repository methods, allowing us to define similarity queries using familiar reposit...

#Enterprise #Java #AI #MongoDB #PGVector #Semantic […]

[Original post on javacodegeeks.com]
Original post on javacodegeeks.com
www.javacodegeeks.com
November 6, 2025 at 4:47 PM
AFAIK:
pgvector handles storage & search - not embedding gen.
Want “in-SQL” embeddings like SQL Server 2025? Use pgml or pgai extensions, or call an API from your app.
November 5, 2025 at 2:09 PM
In comparison to the #PostgreSQL pgvector extension, the vector support in SQL Server 2025 is - let's say "rudimentary"... pgvector has much more querying and indexing functionality than SQL Server 2025... github.com/pgvector/pgv...
GitHub - pgvector/pgvector: Open-source vector similarity search for Postgres
Open-source vector similarity search for Postgres. Contribute to pgvector/pgvector development by creating an account on GitHub.
github.com
November 5, 2025 at 12:13 PM
November 5, 2025 at 8:33 AM
Production-ready RAG with Spring AI: ETL, PGVector, query rewriting, metadata filters, and tuning tricks for real-world retrieval workflows. #ai
Spring AI RAG, Demystified: From Toy Demos to Production-Grade Retrieval
hackernoon.com
November 5, 2025 at 3:13 AM
This is an extremely interesting article looking at the tradeoffs of using #pgvector in production, including the different vector indexing algorithms, metadata filtering, and hybrid search. I'm not sure about its conclusions yet, but definitely food for thought! alex-jacobs.com/posts/the-ca...
The Case Against pgvector | Alex Jacobs
What happens when you try to run pgvector in production and discover all the things the blog posts conveniently forgot to mention
alex-jacobs.com
November 4, 2025 at 12:55 PM
Optimization techniques like quantization and pre/post-filtering can boost PGVector performance. However, these involve trade-offs, such as potential precision loss. Careful tuning is essential to achieve optimal results. #Optimization 4/5
November 4, 2025 at 11:00 AM
Operational complexity with PGVector can be high. It requires significant PostgreSQL expertise for index builds, query planning, and filtering. Dedicated vector DBs often automate these, potentially saving development time and resources. #PostgreSQL 3/5
November 4, 2025 at 11:00 AM
PGVector is a strong contender for small-to-medium workloads, especially if your team has existing PostgreSQL expertise. It's an excellent starting point, but dedicated vector databases often outperform it for large-scale or complex needs. #VectorSearch 2/5
November 4, 2025 at 11:00 AM
Hacker News debated PGVector vs. dedicated vector DBs for production. Discussion covered scalability, operational complexity, performance, and required expertise. It's a good start for small/medium, but larger scales pose challenges. #PGVector 1/5
November 4, 2025 at 11:00 AM
The Case Against PGVector
View Article | Join the HN Conversation

Summary of HN discussion 🧵👇 #hacker-news
The Case Against pgvector | Alex Jacobs
What happens when you try to run pgvector in production and discover all the things the blog posts conveniently forgot to mention
alex-jacobs.com
November 4, 2025 at 11:00 AM
https://alex-jacobs.com/posts/the-case-against-pgvector/
pgvectorはPostgresにベクトル類似性検索をもたらす便利な拡張機能です。
しかし、本番環境でのシステム構築には、デモとの間に大きな隔たりがあります。
この記事では、pgvectorを本番環境で使用する際の課題と、専用のベクトルデータベースの利点について解説します。
The Case Against pgvector | Alex Jacobs
What happens when you try to run pgvector in production and discover all the things the blog posts conveniently forgot to mention
alex-jacobs.com
November 4, 2025 at 8:51 AM
November 4, 2025 at 8:33 AM
November 4, 2025 at 6:03 AM
The Case Against pgvector | Alex Jacobs nveniently forgot to mention October 29, 2025 2599 words 13 min Table of Contents Everyone Loves pgvector (in theory) If you’ve spent any time in the vecto...

#pgvector #postgresql #databases #sql #indexing #performance

Origin | Interest | Match
The Case Against PGVector
Comments
alex-jacobs.com
November 4, 2025 at 6:38 AM