What are vector databases?

Vector databases store information as numbers:

This enables fast and accurate similarity searches. With a vector database, instead of using conventional database queries, you can search for relevant data based on semantic and contextual meaning.

A simplified example

A vector database could store the sentence "n8n is a source-available automation tool that you can self-host", but instead of storing it as text, the vector database stores an array of dimensions (numbers between 0 and 1) that represent its features. This doesn't mean turning each letter in the sentence into a number. Instead, the vectors in the vector database describe the sentence.

Suppose that in a vector store 0.1 represents automation tool, 0.2 represents source available, and 0.3 represents can be self-hosted. You could end up with the following vectors:

Demonstrating the power of similarity search

Qdrant provides vector search demos to help users understand the power of vector databases. The food discovery demo shows how a vector store can help match pictures based on visual similarities.

For full technical details, refer to the Qdrant demo-food-discovery GitHub repository.

Embeddings, retrievers, text splitters, and document loaders

Vector databases require other tools to function:

• Document loaders and text splitters: document loaders pull in documents and data, and prepare them for embedding. Document loaders can use text splitters to break documents into chunks.
• Embeddings: these are the tools that turn the data (text, images, and so on) into vectors, and back into raw data. Note that n8n only supports text embeddings.
• Retrievers: retrievers fetch documents from vector databases. You need to pair them with an embedding to translate the vectors back into data.