> blog --category
Vector Databases
12 posts2024–2026
Vector Databases
- Vector Compression and Quantisation: Fitting Billions of Vectors in Memory (opens on Medium)
A billion 768-dimensional float32 vectors take about 3 terabytes just for the raw numbers.
- Indexing Deep Dive: IVF and IVF-PQ (opens on Medium)
HNSW buys speed and recall by keeping a graph, and every vector it touches, resident in RAM — IVF and IVF-PQ are what cluster-based systems reach for when that stops fitting.
- Indexing Deep Dive: HNSW, Under the Hood (opens on Medium)
How the multi-layer proximity graph is actually built and searched, and where the real trade-offs live.
- The Curse of Dimensionality: Why Exact Nearest-Neighbor Search Does Not Scale (opens on Medium)
As dimensionality increases, it becomes effectively impossible to tell the nearest point in a dataset from the farthest one.
- Inside the Encoder: Tokens, Attention, and How a Transformer Actually Works (opens on Medium)
Opening the sealed box: token embeddings, positional encoding, self-attention, multi-head, feedforward, and residuals.
- Distance Metrics and Similarity Search: Cosine, Euclidean, and Dot Product (opens on Medium)
Cosine, Euclidean, and dot product are not interchangeable dropdown options — pick the wrong one and every query still returns a confident, quietly wrong ranking.
- Scaling Contrastive Training: Batch Size, GPU Gathering, and Gradient Caching (opens on Medium)
Why bigger training batches make embedding models better, and how teams build batches too big for any single GPU to hold
- How Embedding Models Actually Learn: The Math Behind Contrastive Training (opens on Medium)
The InfoNCE formula, the pooling code, and the training loop behind every embedding model, worked through with real numbers.
- Embeddings 101: How Text, Images, and Audio Become Vectors (opens on Medium)
How embedding models learn to turn text, images, and audio into vectors, explained with everyday analogies and no jargon.
- What Is a Vector Database? Origins, Use Cases, and How It Differs from Relational and NoSQL Systems (opens on Medium)
Why nearest-neighbor search needed an entirely new kind of database, not just a new column type.
- Embeddings & Vector Databases: Architecture and Trade-offs (opens on Medium)
Inside the index: how embedding choices and ANN architecture decide your RAG system's speed, cost, and recall.
- From Data to Vectors: How Vector Databases Revolutionize Data Storage (opens on Medium)
Master vector databases and how they store text, images, and audio as vectors to enhance search and recommendation systems