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...

Retrieval-Augmented Generation in .NET: A Practical RAG Guide If you're building AI applications with .NET, there is a point where simply sending a prompt to an LLM stops being enough. Generating a summary is easy. Generating an answer from your company's documents, policies, product information, support knowledge, database records, or internal documentation is a different problem. The model does not automatically know your private data. And even when information is available somewhere in a model's training data, you generally do not want an application to depend on the model remembering it correctly or knowing the latest version of a business policy. This is where Retrieval-Augmented Generation (RAG) becomes useful. Instead of asking an LLM to answer entirely from its general knowledge, your application first retrieves relevant information from an external knowledge source and provides that information to the model as context. RAG = retrieve releva...