Transitioning to AI: Engineering the Next Paradigm

Vector Databases in .NET: RAG, pgvector, HNSW and Production Design If you are building AI features in a .NET application, calling an LLM is often the easy part. The harder problem starts when the model needs information that is specific to your application. That information might be stored in an internal policy document, product catalog, support ticket, technical manual, compliance document, source repository, or company knowledge base. An LLM does not automatically know how to search those systems simply because your application can access them. Your application needs a retrieval layer that can identify useful information and provide it to the model. This is where embeddings, vector search, and vector databases become useful. A vector database stores numerical representations of information called embeddings and provides mechanisms for retrieving records according to vector similarity. This makes vector search an important building block for RAG applications, semantic ...

Understanding Embeddings in RAG with .NET This article focuses on the practical engineering side of embeddings, semantic retrieval, and RAG applications built with .NET. If you've started building Retrieval-Augmented Generation (RAG) applications, you've probably heard the word embedding more times than you expected. Documents become embeddings. Questions become embeddings. A vector database stores those embeddings, and a similarity search retrieves vectors that are close to the vector representing the user's question. The workflow looks simple when drawn as a diagram. The more interesting engineering question is what happens between the text and the vector: How can a list of numbers represent the meaning of a sentence? That is the question this article focuses on. Rather than treating embeddings as another AI bu...