To Nha Notes | March 21, 2025, 10:37 p.m.
VectorDB is a type of database that stores and retrieves information based on vectorized embeddings, the numerical representations that capture the meaning and context of text. By using VectorDB, you can perform semantic search and retrieval based on the similarity of meanings rather than keywords. VectorDB can also help LLMs generate more relevant and coherent text by providing contextual understanding and enriching generation results. Some examples of VectorDBs are Chroma, Elasticsearch, Milvus, Pinecone, Qdrant, Weaviate, and Facebook AI Similarity Search(FAISS).
FAISS, developed by Facebook (now Meta) in 2017, was one of the pioneering vector databases. It was designed for efficient similarity search and clustering of dense vectors and is particularly useful for multimedia documents and dense embeddings. It was initially an internal research project at Facebook. Its primary goal was to better utilize GPUs for identifying similarities related to user preferences. Over time, it evolved into the fastest available library for similarity search and can handle billion-scale datasets. FAISS has opened up possibilities for recommendation engines and AI-based assistant systems.
Referenced in the Building LLM Powered Applications ebook by Valentina Alto