Elasticsearch is a popular search/analytics engine and vector database. Elasticsearch offers an efficient way to create, store, and search vector embeddings at scale.
For technical details, refer to the Elasticsearch documentation.
elasticsearch-labs repo contains executable Python notebooks, sample apps, and resources for testing out the Elastic platform.
Check out our notebooks in this repo for working with OpenAI, using Elasticsearch as your vector database.
In this notebook you'll learn how to:
- Index the OpenAI Wikipedia embeddings dataset into Elasticsearch
- Encode a question with the
- Perform a semantic search
This notebooks builds on the semantic search notebook by:
- Selecting the top hit from a semantic search
- Sending that result to the OpenAI Chat Completions API endpoint for retrieval augmented generation (RAG)