Embedding Fine-Tuning: Training Custom Embeddings for Domain-Specific Retrieval

Introduction: Off-the-shelf embedding models work well for general text, but domain-specific applications often need better performance. Fine-tuning embeddings on your data can dramatically improve retrieval quality—turning a 70% recall into 90%+ for your specific use case. The key is creating high-quality training data that teaches the model what “similar” means in your domain. This guide […]

Read more →

Introduction to NDepend : Static Code Analysis Tool

As a developer, you always have to take the pain of getting adapted to the best practices and coding guidelines to be followed as per the organizational or industrial standards.  Easy way to ensure your coding style follows certain standard is to manually analyze your code or use a static code analyzer like FxCop, StyleCop […]

Read more →

Query Routing: Intelligent Request Distribution for Cost-Efficient AI Systems

Introduction: Not all queries are equal—some need fast, cheap responses while others require deep reasoning. Query routing intelligently directs requests to the right model, index, or processing pipeline based on query characteristics. Route simple factual questions to smaller models, complex reasoning to GPT-4, and domain-specific queries to specialized indexes. This approach optimizes both cost and […]

Read more →

Azure Cosmos DB – Connection Policy – Setting Connection Mode and Connection Protocol

Recently I have been trying multiple ways to optimize CosmosDb SQL.NET SDK integration calls from my web application that sits within a VNET. After carefully analyzing different options available within Cosmos Db SQL API’s have realized there are different aspects we could optimize in achieving minimal turn around time. In this article I am going […]

Read more →

Blazer – The new experimental web framework from Microsoft

In this world of multiple Web frameworks Microsoft would not want to stop experimenting with new frameworks for Web development. Innovation is a key to Microsoft, doesn’t matter the start later than the React(Facebook) and Angular(Google) , but Microsoft has proven most of the times they are good in developing cutting edge frameworks.  That’s how […]

Read more →

LLM Testing Strategies: Building Confidence in Non-Deterministic Systems

Introduction: LLM applications are notoriously hard to test. Outputs are non-deterministic, quality is subjective, and traditional unit testing doesn’t capture the nuances of language generation. Yet shipping untested LLM features is a recipe for embarrassing failures—hallucinations, off-brand responses, or security vulnerabilities. This guide covers practical testing strategies: deterministic unit tests for prompt templates, evaluation suites […]

Read more →