Explore discussions

Why this over that? Real decisions, real constraints, real reasoning.

vector-search×Remove filter

Latest Trending Top voted Most chosen

A vs B trade-offs only

RAG vs fine-tuning vs long context for a customer-support assistant

We're building an assistant that answers customer questions from our help centre: about 4,000 articles, roughly 6M tokens, edited every week by the support team. Volume is 30K questions a day. A: Retrieval-augmented generation. Chunk and embed the articles, retrieve the top…

LLM
RAG
Vector Search
Python

LFLucía Fernández8votes8comments529views2d ago

Answer quality ↔ Freshness

RAG 60%Fine-tuning 10%Long context 30%

10 engineers chose

Database

pgvector or a dedicated vector database for 20M embeddings?

Our RAG product stores document chunks for 600 tenants. We're at 3M embeddings and expect 20M within a year**. Today it's pgvector with an HNSW index on the same RDS instance as everything else. Queries always filter by tenant and by document ACLs. A dedicated vector DB promises…

PostgreSQL
Vector Search
RAG
AWS

KWKenji Watanabe7votes4comments353views1w ago

Simplicity ↔ Search performance

pgvector (Postgres) 60%Dedicated vector DB 40%

10 engineers chose

RAG vs fine-tuning vs long context for a customer-support assistant

pgvector or a dedicated vector database for 20M embeddings?

Popular tags