Atlas Vector Search Tutorials
On this page
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.
The sample data loaded into your Atlas cluster.
One of the following clients to run queries on your Atlas cluster:
Note
You can run Atlas Vector Search queries by using any
MongoDB Driver through the $vectorSearch
aggregation stage. These tutorials includes examples for only
the drivers in the preceding list.
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 Perform Hybrid Search with Atlas Vector Search and Atlas Search tutorial describes how to perform a semantic search against the
sample_mflix.embedded_moviescollection and combine the results with Atlas Search full-text search results by using reciprocal rank fusion.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.