Do not treat this objective as a recognition exercise. Practise explaining and applying 'Build retrieval and grounding pipelines: Configure semantic search, hybrid search, and vector search for grounding' in a new scenario, then check your reasoning against the official source. Source context: Read in English Implement vector search on Azure Cosmos DB for NoSQL Module 8 Units Feedback Intermediate Developer Azure Cosmos DB Learn how to store vector embeddings, execute similarity queries using the VectorDistance function, combine vector search with metadata filters and hybrid search, and use the change feed to keep embeddings synchronized. Learning objectives After completing this module, you'll be able to: Store and retrieve vector embeddings in Azure Cosmos DB containers with properly configured vector policies Execute vector similarity queries using the VectorDistance function to find semantically similar documents Combine vector search with metadata filters and full-text search using hybrid queries Implement change feed processing to automatically refresh embeddings when source documents change Add Prerequisites Before beginning this module, you should have: Programming experience with languages such as Python, JavaScript, or C# Understanding of Azure Cosmos DB for NoSQL containers, items, and indexing policies Familiarity with vector embeddings and their role in AI applications Experience calling embedding APIs such as Azure OpenAI Introduction min Store and retrieve embeddings in Azure Cosmos DB min Execute vector similarity queries for semantic search min Combine vector similarity results with metadata filtering min Use the change feed to trigger embedding refresh min Exercise - Build a semantic search application with Azure Cosmos DB for NoSQL min Module assessment min Summary min Take the module assessment Module Assessment Results Assess your understanding of this module. Sign in and answer all questions correctly to earn a pass designation on your profile.
Objective
Build retrieval and grounding pipelines: Configure semantic search, hybrid search, and vector search for grounding