Atlas Vector Search Overview

What is Vector Search?

Vector search is a search method that returns results based on your data's semantic, or underlying, meaning. Unlike traditional full-text search which finds text matches, vector search finds vectors that are close to your search query in multi-dimensional space. The closer the vectors are to your query, the more similar they are in meaning.

By interpreting the meaning of your search query and data, vector search allows you to consider the searcher's intent and search context to retrieve more relevant results.

For example, if you searched for the term "red fruit," full-text search returns only data that explicitly contains these keywords. However, semantic search might return data that is similar in meaning, such as fruits that are red in color like apples or strawberries.

Atlas Vector Search Indexes

To perform vector search on your data in Atlas, you must create an Atlas Vector Search index. Atlas Vector Search indexes are separate from your other database indexes and are used to efficiently retrieve documents that contain vector embeddings at query-time. In your Atlas Vector Search index definition, you index the fields in your collection that contain your embeddings to enable vector search against those fields. Atlas Vector Search supports embeddings that are less than and equal to 4096 dimensions in width.

You can also pre-filter your data by indexing any boolean, string, and numeric fields in your collection that you want to run your Atlas Vector Search queries against. Filtering your data narrows the scope of your search and ensures that certain vector embeddings aren't considered for comparison.

To learn how to index fields for Atlas Vector Search, see How to Index Fields for Vector Search.

Atlas Vector Search Queries

Atlas Vector Search supports approximate nearest neighbor (ANN) search with the Hierarchical Navigable Small Worlds algorithm. ANN optimizes for speed by approximating the most similar vectors in multi-dimensional space without scanning every vector. This approach is particularly useful for retrieving data from large vector datasets.

Atlas Vector Search queries consist of aggregation pipeline stages where the $vectorSearch stage is the first stage in the pipeline. The process for a basic Atlas Vector Search query is as follows:

1. You specify the query vector, which is the vector embedding that represents your search query.

2. Atlas Vector Search uses ANN search to find vector embeddings in your data that are closest to the query vector.

3. Atlas Vector Search returns the documents that contain the most similar vectors.

To customize your vector search query, you can pre-filter your data on fields that you've indexed by using an MQL match expression with supported comparison or aggregation operators, or you can add additional aggregation stages to further process and organize your results.

To learn how to create and run Atlas Vector Search queries, see Run Vector Search Queries.

Use Cases

Atlas Vector Search supports the following types of vector search queries:

• Semantic Search: Query your vector embeddings based on semantic similarity by using the ANN search algorithm.

  To learn more, see How to Perform Semantic Search and Run Vector Search Queries.

• Hybrid Search: Combine results from both semantic search and full-text search queries. To learn more, see How to Perform Hybrid Search.

By using Atlas as a vector database, you can use Atlas Vector Search to build natural language processing (NLP), machine learning (ML), and generative AI applications.

Specifically, you can implement Retrieval-Augmented Generation (RAG) by storing data in Atlas, using Atlas Vector Search to retrieve relevant documents from your data, and leveraging an LLM to answer questions on your data. You can implement RAG locally or by integrating Atlas Vector Search with popular frameworks and services. To learn more, see AI Key Concepts.