---
title: "Ravi Mohta (@ravimohta) | Hashnode"
description: "AI Architect/Engineer | Building private, local AI systems | RAG, LLMs, Vector Databases, Agents. Read the latest articles by Ravi Mohta on Hashnode."
url: "https://hashnode.com/@ravimohta"
---

@ravimohta

# Ravi Mohta

@ravimohta · London, UK · Joined March 2026

AI Architect/Engineer | Building private, local AI systems | RAG, LLMs, Vector Databases, Agents

### [In, Store, Retrieve: The Three Places RAG Quietly Fails — And How We Fixed Each One](https://herald-ai.hashnode.dev/in-store-retrieve-the-three-places-rag-quietly-fails-and-how-we-fixed-each-one?utm_source=hashnode&utm_medium=feed)

What five months of building a private AI document intelligence system taught me about retrieval quality, LLM reliability, and the gap between "it works" and "it works well"

18 min read · [herald-ai.hashnode.dev](https://herald-ai.hashnode.dev/in-store-retrieve-the-three-places-rag-quietly-fails-and-how-we-fixed-each-one?utm_source=hashnode&utm_medium=feed)

[Mar 17](https://hashnode.com/posts/in-store-retrieve-the-three-places-rag-quietly-fails-and-how-we-fixed-each-one/69b94746c22d3eeb8aa93763)

### [NVIDIA NIM vs Ollama — Which Should You Choose for Local LLM Deployment?](https://herald-ai.hashnode.dev/nvidia-nim-vs-ollama-which-should-you-choose-for-local-llm-deployment?utm_source=hashnode&utm_medium=feed)

A practical comparison from someone who has run both in production

9 min read · [herald-ai.hashnode.dev](https://herald-ai.hashnode.dev/nvidia-nim-vs-ollama-which-should-you-choose-for-local-llm-deployment?utm_source=hashnode&utm_medium=feed)

[Mar 12](https://hashnode.com/posts/nvidia-nim-vs-ollama-which-should-you-choose-for-local-llm-deployment/69b207536c896b0519d2e276)