Skip to main content

Posts

API Debugging in .NET: 7 Common Problems and How to Fix Them

API Debugging in .NET: 7 Common Problems and How to Fix Them You send a request to an API. The endpoint looks correct, the server is running, and the request payload appears valid. Yet the response is 400 Bad Request , authentication fails, or the application returns an error that provides almost no useful information. Sound familiar? API debugging is an essential part of modern backend and full-stack development. Even experienced developers can spend hours investigating problems that eventually turn out to be a missing JSON property, an incorrect content type, an expired JWT token, or a mismatch between a request payload and a C# model. The real challenge is not just finding the error. It is identifying which layer of the API request is failing and why . In this guide, we'll explore seven common API debugging problems, demonstrate how to troubleshoot them using C# and ASP.NET Core, and explain how to identify the root cause without making unnecessary code changes. We...
Post a Comment
Read more
Recent posts

LLM Metrics: A Practical Guide to Measuring AI Application Quality

LLM Evaluation in .NET: Metrics, RAG, Agents and AI Testing Building an application with a large language model is relatively easy. Making sure that application continues to produce useful, accurate, reliable, safe, and affordable results is much harder. An LLM can generate a response in a few seconds, but the fact that it generated an answer does not tell us whether the answer was good. Was it correct? Did it actually answer the user's question? If the application uses RAG, did the answer come from the retrieved information? If an AI agent was involved, did it select the correct tool? Did the tool receive valid arguments? There are also operational questions: How many tokens were consumed? How much did the request cost? How long did the user wait? Did the system use unnecessary tools or model calls? Did anything get worse after a prompt, model, or retrieval change? These questions make LLM evaluation an important part of production AI engineering. Tradition...
Post a Comment
Read more

Vector Databases in .NET: Embeddings, Semantic Search, RAG & pgvector

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 ...
Post a Comment
Read more