Embedding

An embedding is a numeric vector that captures the meaning of a piece of text, letting a docs search system match questions to relevant passages by semantic similarity rather than keywords.

In docs search, every chunk of documentation is converted into an embedding and stored in a vector index. A user's question is embedded the same way, and the system returns the chunks whose vectors sit closest to the question's.

This is what lets semantic search connect "how do I revoke a token" to a page titled "Deleting API credentials". Keyword search would miss it; embeddings capture that the two phrasings mean the same thing.

Embeddings are the retrieval half of RAG, and their usefulness depends on chunking. Embed a whole page and the vector blurs many topics together; embed a focused section and matches are precise.

Frequently asked questions

What does an embedding actually look like?

A list of hundreds or thousands of floating-point numbers produced by an embedding model. Texts with similar meaning produce vectors that sit close together.

Do embeddings go stale when docs change?

Yes. When a page changes, its chunks must be re-embedded and re-indexed, which is why docs AI systems recrawl the site periodically.

Your docs already have the answers. Make them work.

Join the waitlist

Be the first to know when this integration launches.

By clicking “Join waitlist” you agree to our Terms and Privacy Policy.
14-day free trialNo credit card required
Try me ↓