Quickstart: Vector search using Gemini Embeddings and Elasticsearch

This tutorial demonstrates how to use the Gemini API to create embeddings and store them in Elasticsearch. Elasticsearch will enable us to perform vector search (Knn) to find similar documents.

setup

• Elastic Credentials - Create Cloud deployment to get all Elastic credentials (ELASTIC_CLOUD_ID, ELASTIC_API_KEY).

• GOOGLE_API_KEY - To use the Gemini API, you need an API key. Follow to create a key with one click in Google AI Studio.

Install packages

Import packages and credentials

Embedding generation

Connecting Elasticsearch

Index document with Elasticsearch

Searching for document with Elasticsearch