Retrieval

How does an embedding index differ from a vector database?

A vector database stores vectors and answers similarity queries. An embedding index is that search capability declared on the same table that holds the source pieces.

Updated · Part of What is an embedding index?

How it works

  • The vector database is a product whose rows are vectors plus metadata.
  • The embedding index is a structure on a table that also stores the passage, frame, or file.
  • You pick a separate vector database when something else owns the source of truth. You declare an index when the table already does.

What it is not

Replacing a vector database does not, by itself, give you RAG. Chunking, staying in sync, and calling the model are still separate jobs.

embedding index versus a vector database: this, and the thing it is confused with

embedding index versus a vector database: this, and the thing it is confused with
ThisNot this
Source of truthThe table, if the index is on itThe vector database, if you copied vectors in
SyncThe row updateAn ETL job
RAGStill needs chunks and a model callNot finished when the index exists

Where Pixeltable fits

Pixeltable keeps the index on the table. Pinecone and LanceDB remain options when a separate vector store is the product you want. They are not required for the index itself.

Questions

How does embedding index versus a vector database work?
The vector database is a product whose rows are vectors plus metadata. The embedding index is a structure on a table that also stores the passage, frame, or file. You pick a separate vector database when something else owns the source of truth. You declare an index when the table already does.
What is embedding index versus a vector database often confused with?
Replacing a vector database does not, by itself, give you RAG. Chunking, staying in sync, and calling the model are still separate jobs.