Blog

Vector search engineering

Engineering

Why storing vectors in S3 is 10x cheaper than traditional vector databases

A detailed cost breakdown comparing Pinecone, Weaviate, and Qdrant against object-storage-native vector search. The math is uncomfortable for the incumbents.

2026-07-15 12 min read Read →
Engineering

The anatomy of a RAG pipeline

A detailed look at every component in a production retrieval-augmented generation pipeline — chunking, embedding, retrieval, re-ranking, and generation — with practical tradeoffs at each stage.

2026-07-12 13 min read Read →
Engineering

HNSW explained: the algorithm powering sub-10ms vector search

A ground-up explanation of Hierarchical Navigable Small World graphs — why they work, how they achieve 90%+ recall at sub-10ms latency, and what the tuning parameters actually do.

2026-07-08 14 min read Read →
Engineering

Understanding cosine similarity vs dot product in vector search

The practical difference between cosine similarity and dot product for vector search — when they're equivalent, when they diverge, and how to choose the right metric for your embedding model.

2026-07-08 8 min read Read →
Engineering

BM25 vs vector search: which one should you use?

A practical comparison of BM25 and vector search — when each excels, where they fail, and why hybrid search (RRF) outperforms either approach alone for most production workloads.

2026-07-05 9 min read Read →
Engineering

Copy-on-write namespaces: Git for your vector database

How copy-on-write branching lets you fork a 100M-vector namespace in milliseconds, run embedding model evals without duplicating data, and roll back cleanly when experiments go wrong.

2026-07-01 10 min read Read →
Engineering

What is a vector embedding? A practical guide

Vector embeddings explained from first principles: what they are, how they're generated, why they enable semantic search, and how to choose the right embedding model for your workload.

2026-07-01 10 min read Read →
Engineering

Hybrid search with RRF: why combining vector and BM25 beats either alone

A practical guide to Reciprocal Rank Fusion — the algorithm that combines vector and keyword search scores. With benchmark data showing when hybrid consistently outperforms pure vector retrieval.

2026-06-24 11 min read Read →
Engineering

Building production RAG pipelines on object storage

A complete architecture guide for RAG pipelines that use object storage as the retrieval layer — covering chunking, embedding, indexing, retrieval, and operational concerns at production scale.

2026-06-17 15 min read Read →
Engineering

The hidden cost of in-memory vector databases

RAM-first vector databases look affordable on the pricing page. Here's what the pricing page doesn't show: idle RAM tax, replication multipliers, scaling cliffs, and the egress bills that compound over time.

2026-06-10 9 min read Read →
Engineering

Migrating embedding models with zero downtime using namespace branching

A step-by-step playbook for switching embedding models in production — from evaluation to rollout to rollback — without taking your RAG pipeline offline or duplicating 200GB of vectors.

2026-06-03 11 min read Read →
Engineering

Metadata filtering in vector search: pre-filter vs. post-filter and why it matters

The difference between filtering before and after vector search is not just semantic — it fundamentally changes recall, latency, and correctness. Here's when to use each and why HNSW pre-filtering is harder than it looks.

2026-05-27 10 min read Read →
Engineering

Scaling to a billion vectors: lessons from building on object storage

What breaks at 1B vectors that works fine at 1M — memory management, HNSW graph traversal time, compaction, and multi-namespace serving. A technical deep-dive on the engineering challenges of billion-scale vector search.

2026-05-20 13 min read Read →

Start searching every vector today.