pgvector
No written verdict yet. Here is what commenters said.
Why people recommend it
“excellent plugins like pgvector and PostGIS”
“you can use quantized vector indexes[0] (handled by pgvector)”
Show 3 more
“pgvector is great if you're already on postgres and only need text search”
“I just did that myself recently with pgvector for a documentation site.”
“pgvector beats a dedicated vector DB for most use cases”
Caveats and dissent
“scaling semantic search beyond pgvector's main memory limitations”
“pgvector had some perf problems”
Show 2 more
“pushing pgvector with very suspicious benchmarks that turned me off it altogether”
“solved most of the pgvector issues mentioned in this blog”
Often compared with
Who recommends it in their own words
Threads where it came up
- The Case Against PGVector 11 mentions
- Ask HN: Who wants to be hired? (July 2026) 3 mentions
- Ask HN: Who wants to be hired? (October 2026) 2 mentions
- PostgreSQL for Everything 2 mentions
- Ask HN: Who wants to be hired? (August 2026) 2 mentions
- Ask HN: Who wants to be hired? (June 2026) 2 mentions
Data: pgvector.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 40
“pgvector RAG”
“using Python, pgvector, and OpenAI, Claude, and Gemini APIs”
“pgvector, PostgreSQL”
“plpgsql_bm25 + pgvector”
“excellent plugins like pgvector and PostGIS”
“Postgres/pgvector”
“pgvector”
“Postgres + pgvector”
“turn the documents into vectors in say PostgreSQL (with pgvector)”
“PgVector already exists”
“I used this in a different project (halfvec in pgvector) without affecting results.”
“pgVector”
“ChromaDB, pgvector”
Location: Istanbul, Türkiye (relocating to Guildford, UK in Sept 2026) Remote: Yes — full EU overlap; US-East evenings (UTC+3, moving to UTC+0) Willing to relocate: No Technologies: TypeScript, Node.js, NestJS, Fastify, Next.js, React, React Native/Expo, PostgreSQL/Prisma, Redis/BullMQ, Claude API, RAG, tool-calling/MCP, pgvector, Playwright Résumé/CV: https://github.com/denizcakiroglu322 Email: denizcakiroglu322@gma
“you can use quantized vector indexes[0] (handled by pgvector)”
“pgvector”
> ...add something like apache AGE, but arguably that is also a small ecosystem (at least IMHO as I never heard it until I actually started looking for Neo4J alternatives) Outside of the most trivial use cases, I've found that AGE will not get anywhere near Neo4j in terms of performance and there's a lot of edge cases that just flat out won't work. The interesting types of queries you'd want to do in the graph end up
“scaling semantic search beyond pgvector's main memory limitations”
“vector similarity (pgvector) run in parallel”
“Technologies: Python, FastAPI, n8n, CrewAI, LangGraph, LangChain, RAG/pgvector, WhatsApp (Botmaker/Twilio), PostgreSQL, Docker, Coolify/DigitalOcean”
“pgvector + Supabase”
“pgvector cosine similarity on 768-dim embeddings”
“pgvector is great if you're already on postgres and only need text search”
“I just did that myself recently with pgvector for a documentation site.”
“pgvector for semantic search”
“pgvector beats a dedicated vector DB for most use cases”
“Why no benchmarks against pg_vector, DuckDB with extension?”
“i love postgres and pgvector... this is exactly to my tastes”
“PostgreSQL + pgvector for production”
“have seen very fast lookups with pgvector (HNSW index) and sqlite-vec on 20k vectors”
“It’s built with ASP.NET, Postgres/pgvector, and OpenAI embedding/LLMs.”
“You can use pgvector for the vector lookup and paradedb for bm25.”
“It uses PostgreSQL with pgvector, hybrid BM25, multi-query expansion, and reranking.”
“pgvector had some perf problems”
“pgvector for embeddings”
“using PostgreSQL with pgvector”
“combine the pgvector score and the bm25 score”
“comparing well-tuned pgvector to pinecone”
“plpgsql_bm25 + pgvector”
“pgVector is great”