Explore retrieval-augmented generation and embeddings in .NET, including vector search, semantic retrieval, and grounding techniques for C# applications.
Learn RAG access control and data lifecycle patterns for .NET: server-derived scopes, tenant filters, provenance, revisions, deletion, caches, and audit trails.
Learn RAG prompt injection .NET defenses for hostile retrieved content: source admission, provenance, delimiters, least privilege, scanning limits, and tests.
Learn OpenTelemetry RAG .NET tracing to connect retrieval, generation, latency, and cost boundaries with privacy-minimizing telemetry and evaluation signals.
Build a trustworthy RAG golden dataset in .NET with versioned evidence, synthetic-case review, human sentinel calibration, and drift-driven refreshes.
Learn RAG evaluation metrics in .NET with Precision@K, Recall@K, MRR, nDCG, groundedness, and answer relevance for clearer, repeatable offline RAG diagnostics.
Learn RAG query transformation in .NET through baseline retrieval, HyDE, step-back abstraction, decomposition, candidate merging, and retrieval evaluation.
See how semantic reranking for RAG in .NET applies Azure AI Search semantic ranking after retrieval, with configuration, scores, captions, and limits.
Learn how hybrid search RAG .NET combines lexical BM25 and dense vector candidates in one Azure AI Search request with reciprocal rank fusion.
Learn Azure AI Search vector search .NET query mechanics, including vector fields, dimension alignment, top-k results, filters, scores, and stable C# APIs.
Learn how Microsoft.Extensions.AI embeddings .NET pipelines use batching, vectors, caching, telemetry, and decorators to keep retrieval work observable.
Learn a stable architecture for RAG and embeddings in .NET, connecting ingestion, retrieval, citations, authorization, evaluation, observability, and deletion.
