🧠 Vector Databases Flashcards
📌 What is a Vector Database?
A database optimized to store, index, and search high-dimensional vector embeddings used in AI/ML applications.
🔍 How is search done in vector DBs?
Through approximate nearest neighbor (ANN) algorithms, enabling fast similarity search across vectors.
📦 What is an embedding?
A numerical representation of unstructured data (text, image, etc.) used to perform similarity comparisons.
⚡ Why use a Vector DB?
To perform fast semantic search over large unstructured datasets in applications like RAG, chatbots, and recommendation engines.
📚 What is FAISS?
FAISS (Facebook AI Similarity Search) is a popular open-source vector search library for efficient ANN search.
🌲 What is Pinecone?
Pinecone is a managed vector database service offering fast and scalable similarity search with APIs for LLM apps.
🧠 What is ChromaDB?
Chroma is an open-source vector store optimized for local development with LLMs, ideal for lightweight retrieval tasks.
⚙️ Vector DB vs SQL DB?
SQL DBs handle structured, exact-match queries. Vector DBs handle unstructured, similarity-based queries.
🛰️ What is Weaviate?
Weaviate is a GraphQL-powered vector database supporting hybrid search, vectorization, and cloud-native deployment.
🔗 How do LLMs interact with vector DBs?
LLMs use vector DBs in Retrieval-Augmented Generation (RAG) setups to fetch relevant context before generating a response.