pgvector

Do you have LongMemEval numbers for pgvector vs pgvector+ hybrid search?

Workers run 24/7, remember what they've learned (pgvector semantic memory), create tickets for each other, and coordinate autonomously.

Drupal 11 with ai_provider_ollama and custom provider ai_provider_llama (heavily derived from ai_provider_ollama) with PostreSQL and pgvector.

Rivestack gives you sub-4ms pgvector queries at a fraction of what you'd pay for alternatives.

Currently building AI-powered enterprise solutions — recently architected a multi-tenant RAG platform with AI agents and third-party integrations (Python, pgvector, OpenAI/Claude/Gemini APIs).

Saw Vectree on HN—love the pgvector + semantic search approach for the concept graph.

Most recent: built the matching layer for a funded recruitment marketplace (10k+ live profiles, pgvector, nearest-neighbor search, LLM summarization).

Relevant: GraphRAG demo — hybrid BM25+RRF retrieval on unstructured text, NetworkX entity graph, Claude for extraction, pgvector for embeddings.

Also: DocExtract AI (production, live) — async document pipeline, pgvector + Claude + ARQ worker, 234 tests.

I've been doing some RAG prototypes with hybrid search using pg_textsearch plus pgvector and have been very pleased with the results.

Relevant: Chatbot Widget SaaS — Next.js 15 + TypeScript + Supabase + pgvector + Shadow DOM widget, real-time WebSocket streaming, full auth + Stripe billing.

Are there similar efforts for PgVector, the PostgreSQL extension.

Something like "find invoices from Q1 similar to 'billing dispute'" where the date filter is SQL and the similarity part is pgvector.

The "zero-config" angle is strong here — the biggest friction with pgvector is the manual pipeline: choose an embedding model, write the chunking logic, create the index, tune the distance metric.