Avi Chawla (@_avichawla)

The growth of LLM context length with time: - GPT-3.5-turbo → 4k tokens - OpenAI GPT4 → 8k tokens - Claude 2 → 100k tokens - Llama 3 → 128k tokens - Gemini → 1M tokens Let's understand how they extend the context length of LLMs:...

A new embedding model cuts vector DB costs by ~200x. It also outperforms OpenAI and Cohere models. Here's a complete breakdown (with visuals):...

An MCP server that makes anyone a database engineer (open-source)! @MongoDB just released an MCP Server that lets AI tools like Claude, Cursor, and GitHub Copilot talk directly to a MongoDB deployment. That means anyone (technical or non-technical) can now say: - “Show me the most active users” -...

A simple technique makes RAG ~32x memory efficient! - Perplexity uses it in its search index - Azure uses it in its search pipeline - HubSpot uses it in its AI assistant Let's understand how to use it in RAG systems (with code):...

Andrew Ng's team once made a big mistake in a research paper. And it happened due to randomly splitting the data. Here's what happened:...

Naive RAG vs. Agentic RAG, clearly explained (with visuals):...

uv in Python, clearly explained (with code):...

Let's generate our own LLM fine-tuning dataset (100% local):...

INCREDIBLE!!! Gemini did 6 hours of manual data analysis work in just 2 mins. Gemini in a Colab notebook now lets you plan, analyze, and visualize your data. I used a dataset of 100k rows and didn't write or execute a single line of code. Completely hands-off! ...