Changes: Convert Gemfile to read from .ruby-version Drop 3.3 and 3.4 support from Gemfile/rubocop/readme Reduce/remove CI version matrix Run rubocop autocorrect (just the anon kwargs thing) after ...

Failure from here - https://github.com/mastodon/mastodon/actions/runs/39264027692/job/118098815026?pr=41146 This was likely caused by #40603 moving the ruby version in the Gemfile to read from the ...

🧠 Your Database Is Already a Vector Database Most RAG tutorials start the same way: "First, spin up a vector database." But Stop. If you're on Rails, you already have PostgreSQL. With the pgvector extension it can store and search embeddings and for most applications, that's the whole answer. 🐘 Setup is one migration `enable_extension "vector" add_column :document_chunks, :embedding, :vector, limit: 1536` 💎 And one line in your model # Gemfile `gem "neighbor"` `class DocumentChunk < ApplicationRecord has_neighbors :embedding, dimensions: 1536, normalize: true end` 🔍 Searching is just ActiveRecord `DocumentChunk .where(tenant: Current.tenant) .nearest_neighbors(:embedding, query_vector, distance: "cosine") .limit(6)` Scoped, chainable, joinable. A normal Rails query. 🚀 Why this beats a separate vector DB 1️⃣ No new infrastructure Nothing extra to deploy, monitor, back up, or upgrade. 2️⃣ Transactional consistency Embeddings commit in the same transaction as the record. Two systems can't drift apart. 3️⃣ Authorization you already trust This is the big one. Retrieval almost always needs scoping by tenant, project, or permission. In Postgres that's a WHERE clause. In an external store it's metadata filtering you have to keep in sync with your auth model. Get it wrong, and one customer's documents land in another customer's LLM prompt. 4️⃣ Real joins Chunks plus their documents, authors, and timestamps in one query. ⚠️ Three things that will bite you ❌ Index opclass mismatch vector_cosine_ops goes with cosine distance. Mismatch them and Postgres silently skips your index and sequential-scans the table. ❌ No similarity floor Nearest neighbours are nearest, not relevant. Without a threshold, an unrelated question still returns chunks — which the model will happily use to hallucinate. ❌ Pure vector search Embeddings are weak at exactly what users type literally: error codes, SKUs, invoice numbers. ERR_4012 and ERR_4013 are nearly identical in vector space. Fix: hybrid search — pgvector + Postgres full-text, fused with Reciprocal Rank Fusion. 🎯 When to actually leave Postgres Past roughly 5–10 million chunks, or when the vector workload starves your transactional workload for memory. Until then, a dedicated vector database buys you one more service to operate and a second place for your authorization logic to be wrong. Your database stays the source of truth. The vector index is a lookup layer on top of it. 💬 If you've shipped RAG in Rails — what pushed you off Postgres, if anything?

Introducing Rails Hyperdrive: a development-only Rails engine that gives AI coding agents live answers from your booted app and lets any gem in your bundle ship guidance gated to your Gemfile. Convention over configuration, applied to agent knowledge.

I'm Hiroshi Shibata (hsbt), a Ruby committer and the lead maintainer of RubyGems and Bundler. ...