AI / LlamaIndex Interview Questions
What is a VectorStoreIndex?
A VectorStoreIndex is the most commonly used index type in LlamaIndex. It embeds each Node into a numerical vector using an embedding model, then stores those vectors in a vector store so similar pieces of text can be found through similarity search.
When you build one with VectorStoreIndex.from_documents(documents), LlamaIndex automatically runs the default node parser to chunk your documents, calls the configured embedding model on each chunk, and writes the resulting vectors either in memory or into an external vector database.
At query time, the index embeds the incoming question the same way and returns the Nodes whose vectors are closest to it, which is what makes semantic search possible even when the wording doesn't match exactly.
More Related questions...
