Naveenkrishnan·Aug 14LLM Decision Call — System DesignIn today AI world we know it is quite easy to design a prototype and show this to team or stakeholders the coolness of LLM and AI.
Mindful Money Mentor | Control Cash 📈 Get Freedom·Aug 7I Got Tired of PDF-to-Markdown Tools That Upload My Files. So I Found One That Doesn’tIf you work with Markdown (documentation, static sites, Notion, Obsidian notes, feeding content into an LLM), you’ve probably needed to…
Sudhakar Tripathi·Mar 22Token-Efficient RAG: How TOON and JSON Can Cut Your LLM CostsA practical guide for AI engineers who want to reduce token overhead in Retrieval-Augmented Generation pipelines — without overcomplicating…
Abhishek Tripathi·Mar 21Vector RAG vs. Vectorless RAG — Which One Actually Knows Where It Left Its Keys?Let’s be honest. The first time someone said “Retrieval-Augmented Generation,” half the room nodded like they totally knew what that meant…
Pankaj·Mar 8Stop Chunking, Start Reasoning: How PageIndex Replaces Vector Search with LLM-Driven RetrievalThe standard RAG pipeline chunks documents, embeds them, and searches by similarity. But similarity is not relevance, and for dense…A response icon2
