You can learn how to leverage Atlas Vector Search with our use-case tutorials.
Prerequisites
To complete these tutorials, you must have the following:
An Atlas cluster with MongoDB version v6.0.11, or v7.0.2 or later.
Project Data Access Adminaccess to the project to create Atlas Vector Search indexes.The sample data loaded into your Atlas cluster.
mongoshor a supported MongoDB Driver to run queries on your cluster.
Note
You can run Atlas Vector Search queries by using any driver through the $vectorSearch aggregation stage. These tutorials include examples for a selection of drivers. Refer to the specific tutorial page for details.
You can also complete these tutorials with local Atlas deployments that you create with the Atlas CLI. To learn more, see Create a Local Atlas Deployment.
About the Tutorials
The How to Perform Semantic Search Against Data in Your Atlas Cluster tutorial describes how to index and perform an ANN search on vector embeddings in the
sample_mflix.embedded_moviescollection.The Build a Local RAG Implementation with Atlas Vector Search tutorial describes how to generate embeddings for Atlas Vector Search and implement RAG by using local embedding and generative models, without the need for API keys.
The How to Perform Automatic Quantization with Voyage AI Embeddings tutorial describes how to automatically quantize vector embeddings generated with Voyage AI's
voyage-3-largeembedding model.