Building Generative AI Apps with Azure Cosmos DB
summary
Claims that Azure Cosmos DB stores vectors and documents together and runs high‑scale vector search (Cosmos DB for MongoDB today, Cosmos DB NoSQL vector indexing via DISN in May), and shows concrete tooling: Python + LangChain, Azure OpenAI embeddings and completions, Semantic Kernel, Gradio. Builds a RAG chatbot over a movie dataset with a vector index and conversational retrieval chain, demonstrates a top‑5 similarity query returning Toy Story hits, and a semantic caching result that cuts response time from ~3.35s to under 500ms.
AI-written summary · about
chapters (4)
related talks
50mHow to design and build AI applications with vector search using Azure OpenAI & Azure Cosmos DB
20mBuilding AI Applications with Azure Cosmos DB JavaScript SDK
17mAzure Cosmos DB in AI Workflows: From Knowledge Retrieval to Microsoft Fabric Integrations
11mScalable RAG with Azure Cosmos DB and DiskANN
01h 16mAzure SQL ❤️ Open AI
19mCosmic Database Powering OpenAI’s ChatGPT
40mUnleashing the Power of Vector Search with Azure SQL Database
48mThe power of AI and Copilot for Azure Databases