Vector Database Tutorial

What Is a Vector Database A vector database stores embeddings: long lists of numbers that describe the meaning of text, images, audio or any data. Similar items end up close ...

What Embeddings Capture Embedding models map words and sentences to fixed-size vectors while preserving meaning. Two different sentences that mean the same thing produce vectors ...

Dot Product The dot product sums the products of matching dimensions. It is fast and reflects both direction and magnitude, which suits recommendations where popularity matters. ...

Brute Force Isn't Enough Searching millions of vectors linearly costs billions of operations per query. Approximate nearest neighbour (ANN) indexes trade a little recall for ...

Why ChromaDB ChromaDB is an open-source vector database that stores documents, embeddings and metadata together, with a simple Python API and no server needed for small projects. ...

What Is FAISS FAISS is Facebook AI Similarity Search, a library of vector indexes that runs directly on your machine and handles billions of vectors with CPU and GPU support. ...

Why pgvector pgvector adds a vector column type and ANN indexes to your existing PostgreSQL database. You keep vectors next to the rows they describe, so filters and joins work as ...

What Is Qdrant Qdrant is an open-source vector engine with a Python client, REST and gRPC APIs. It runs as a server, but an embedded mode lets you start from a Python process with ...

Pre-Filter vs Post-Filter Pre-filtering narrows the candidate set before the vector search runs, which keeps memory usage low and results consistent. Post-filtering runs the ...

The RAG Pipeline Retrieval-Augmented Generation (RAG) answers questions using your own documents: chunk, embed, store, retrieve, and let the model answer from the retrieved text. ...

Why Writes Need Care Vectors go stale when their source documents change. A knowledge base that never updates quietly answers from old text, so plan deletions and re-embedding ...

Metric Definitions Score your retrieval before tuning it. Recall@k - Of the truly relevant items, what fraction appears in the top k? Precision@k - Of the top k results, what ...

Chunking Strategy Chunk size and overlap shape retrieval quality. Use paragraphs of a few hundred characters with a small overlap so ideas are not split across boundaries. Store ...

Core Questions Q: What is a vector database? A: A database optimized to store embeddings and answer nearest-neighbour queries fast, using ANN indexes and metadata filtering. Q: ...