When we began architecting DevSecOps at Evanke, our goal was straightforward yet ambitious: establish an AI development environment that integrates security at every stage without sacrificing scalability or performance. Our approach had to go beyond standard DevOps practices, embedding security deeply…
Building Explainable AI at Evanke: A Journey of Transparency and Trust
When we first set out to integrate Explainable AI into our MLOps workflow, it wasn’t just about implementing a set of tools. It was about solving a deeper challenge: ensuring that our AI models were not only powerful but also transparent…
Empowering CONVAID with Palantir Ontology
Introduction As part of my work on CONVAID, a powerful text-to-SQL system, I had the opportunity to enhance its capabilities by integrating Palantir Ontology as the vector database. This transformation introduced a more structured and streamlined approach to SQL query generation….
Naive RAG vs Self-RAG vs Graph RAG: A Comprehensive Overview
Introduction In my journey of building and refining Retrieval-Augmented Generation (RAG) pipelines, I’ve encountered multiple approaches—Naive RAG, Self-RAG, and Graph RAG—each addressing distinct challenges in AI-powered question answering. While working on projects such as CONVAID (my text-to-SQL project) and document Q&A…
