Building RAG Applications with Azure Cognitive Search and OpenAI
RAG with Azure Cognitive Search and Azure OpenAI is the production architecture I recommend most often for enterprise knowledge retrieval — not because it's…
21 articles
RAG with Azure Cognitive Search and Azure OpenAI is the production architecture I recommend most often for enterprise knowledge retrieval — not because it's…
RAG is the bridge between general-purpose LLMs and your specific enterprise data. Get it right, and you unlock tremendous value.
Azure Cognitive Search can't search vectors in January 2023. Here's how to re-rank its keyword results with Azure OpenAI embeddings, and when not to bother.
Custom skills unlock unlimited possibilities for AI enrichment tailored to your specific business needs.
Skillsets enable powerful AI-driven content enrichment during the indexing process.
Debug sessions are essential for developing and troubleshooting complex AI enrichment pipelines efficiently.
Enrichment cache significantly reduces costs and improves performance for AI-enriched search solutions.
Projections enable flexible storage and querying of AI-enriched content for various downstream use cases.
Knowledge Store enables rich analytics and knowledge graph construction from AI-enriched content.
Hybrid search patterns enable building search systems that handle diverse query types effectively.
Vector search enables powerful similarity-based retrieval that complements traditional keyword search.
Semantic search dramatically improves search relevance by understanding user intent rather than just matching keywords.
Azure Cognitive Search provides enterprise-grade search capabilities with AI enrichment options.
Azure SQL to Cognitive Search is a combination I've set up half a dozen times, and the reason it keeps appearing is that most enterprise organisations…
When indexing blobs, the indexer performs several operations: 1. Enumerate blobs Find blobs matching your criteria 2. Download content Retrieve blob data 3.…
Indexers handle the ETL process for search: Requires a column that increases monotonically: Enable change tracking on your database: Source JSON: Source…
Custom skills are Azure Functions that implement a specific contract.
How to tune Azure Cognitive Search relevance with BM25 settings, custom analyzers, synonym maps, scoring profiles and query syntax, and when to leave defaults.
Indexing PDFs is easy. Indexing PDFs in a way that makes them findable is a different sport. Cognitive Search skillsets are the part I usually sell to…
Most "search" tutorials I see stop at "create an index, push some JSON, query it." That's the easy 10%. The 90% that matters in real projects is the indexer…
How to size an Azure Cognitive Search service, design index fields you won't regret, and query safely with the newly GA Azure.Search.Documents v11 SDK.