Hybrid Search with Metadata Filtering
The lesson demonstrates filtered vector search that pre-filters on business data such as category and date to speed up queries, and combines vector distance with full-text matching using Reciprocal Rank Fusion (RRF) with configurable weights for keyword-heavy prompts like error codes.
Previous Module
Introducing Azure Cosmos DB
This Module
AI Vector Search on Azure Cosmos DB
Introduction to Integrated Vector Search
Storing and Retrieving Embeddings in Azure Cosmos DB
Executing Vector Similarity Queries
Hybrid Search with Metadata Filtering
Refreshing Embeddings with the Change Feed
Optimizing Query Performance in Azure Cosmos DB for NoSQL
Understanding Index Types in Azure Cosmos DB
Configuring Range and Composite Indexes
Tuning Vector Indexes for Embedding Workloads
Reducing RU Costs with Strategic Indexing