Daily tutorials and insights on DS, ML, LLMs, and RAGs • Co-founder @dailydoseofds_ • IIT Varanasi • ex-AI Engineer @ MastercardAI
3 subscribers
Jul 3 • 10 tweets • 4 min read
uv in Python, clearly explained (with code):
uv is incredibly fast.
- Creating virtual envs. using uv is ~80x faster than python -m venv.
- Package installation is 4–12x faster without caching, and ~100x with caching
Today, let's understand how to use uv for Python package management.
Let's dive in!
Jun 29 • 8 tweets • 3 min read
MCP & A2A (Agent2Agent) protocol, clearly explained (with visuals):
Agentic applications require both A2A and MCP.
- MCP provides agents with access to tools.
- A2A allows agents to connect with other agents and collaborate in teams.
Today, let's clearly understand what A2A is and how it can work with MCP.
Jun 26 • 13 tweets • 7 min read
10 GitHub repos that will set you up for a career in AI engineering (100% free):
1️⃣ ML for Beginners by Microsoft
A 12-week project-based curriculum that teaches classical ML using real-world datasets using Scikit-learn.
Includes quizzes, R/Python lessons, and hands-on projects. Some of the lessons are available as short-form videos.
Check this👇
Jun 25 • 9 tweets • 3 min read
How Agents test Agents, clearly explained (with code):
Today, we'll learn Agent Testing by building a pipeline to test Agents with other Agents using Scenario.
Our open-source tech stack:
- @crewAIInc for Agent orchestration.
- @LangWatchAI Scenario to build the eval pipeline.
- @pytestdotorg as the runner.
Let's begin!
Jun 24 • 10 tweets • 3 min read
Let's fine-tune DeepSeek-R1 (distilled Llama) 100% locally:
Before we begin, here's what we'll be doing.
To do this, we'll use:
- @UnslothAI for efficient fine-tuning.
- @ollama to run it locally.
Let's begin!
Jun 22 • 14 tweets • 5 min read
Let's build an MCP server (100% locally):
Before diving in, here's what we'll be doing today:
- Understand MCP with a simple analogy.
- Build a local MCP server and interact with it via @cursor_ai.
- Integrate @Stagehanddev MCP and interact with it via Claude Desktop (shown in the video).
Let's dive in!
Jun 19 • 12 tweets • 6 min read
AI Engineering Hub is about to cross 10k GitHub stars!
It’s 100% open-source and hosts 70+ free hands-on demos.
Here are 10 MCP, RAG, and AI Agents projects for AI engineers:
1️⃣ MCP-powered RAG over videos
Learn how to build a video RAG that ingests a video and lets you chat with it. It also fetches the exact video chunk where an event occurred.
Let's build an MCP-powered RAG over videos, step-by-step:
Below, we have an MCP-driven video RAG that ingests a video and lets you chat with it. It also fetches the exact video chunk where an event occurred.
Our tech stack:
- @ragieai for video ingestion and retrieval.
- @cursor_ai as the MCP host.
Let's build it!
Jun 14 • 10 tweets • 3 min read
Transformer vs. Mixture of Experts in LLMs, clearly explained (with visuals):
Mixture of Experts (MoE) is a popular architecture that uses different experts to improve Transformer models.
The visual below explains how they differ from Transformers.
Let's dive in to learn more about MoE!
Jun 12 • 8 tweets • 3 min read
ML researchers just built a new ensemble technique.
It even outperforms XGBoost, CatBoost, and LightGBM.
Here's a complete breakdown (explained visually):
For years, gradient boosting has been the go-to for tabular learning.
TabM is a parameter-efficient ensemble that provides:
- The speed of an MLP.
- The accuracy of GBDT.
The visual below explains how it works.
Let's dive in!
Jun 10 • 11 tweets • 6 min read
9 MCP projects for AI engineers (with code):
1️⃣ 100% local MCP client
An MCP client is a component in an AI app (like Cursor) that establishes connections to external tools. Learn how to build it 100% locally.
Let's build an MCP-powered voice Agent using Qwen3 (running locally):
Today, we are building an MCP-driven voice Agent that queries a database and falls back to web search if needed using:
- @AssemblyAI for Speech‐to‐Text.
- @firecrawl_dev for web search.
- @supabase for a database.
- @livekit for orchestration.
- Qwen3 as the LLM.
Let’s go!
May 29 • 8 tweets • 3 min read
3 techniques to unlock reasoning in LLMs, clearly explained (with visuals):
Today, let’s look at three popular prompting techniques that help LLMs think more clearly before they answer.
- Chain of Thought (CoT)
- Self-Consistency (or Majority Voting over CoT)
- Tree of Thoughts (ToT)
Let's dive in!
May 26 • 9 tweets • 4 min read
I have tested 100+ MCP servers in the last 2 months!
Here are 6 must-use MCP servers for all developers (open-source):
1️⃣ Bright Data MCP server
This MCP server provides 30+ tools to access, search, crawl, and interact with the web without getting blocked.
Unlike typical scrapers, it dynamically picks the most effective tool based on the target site's structure.
Check this 👇
May 25 • 9 tweets • 3 min read
5 LLM fine-tuning techniques, clearly explained (with visuals):
Traditional fine-tuning is infeasible with LLMs since they have billions of parameters (and 100s of GBs in size).
Not everyone has access to such computing infrastructure.
The visual depicts 5 optimal ways to fine-tune LLMs.
Let's understand them one by one below!
May 23 • 14 tweets • 5 min read
Let's build a multi-agent network with Agent2Agent Protocol (100% local):
Before diving in, here's what we'll be doing:
- We'll understand A2A in simple terms.
- Next, we'll build three Agents and serve them locally.
- Finally, we'll talk to them via the Agent2Agent protocol by Google.
Let's dive in 🚀!
May 21 • 10 tweets • 3 min read
How LLMs train LLMs, clearly explained (with visuals):
LLMs don't just learn from raw text; they also learn from each other.
- Llama 4 Scout & Maverick were trained using Llama 4 Behemoth.
- Gemma 2 and 3 were trained using Gemini.
Distillation helps us do so, and the visual explains 3 popular techniques.
Covers:
- Notations & general concepts
- Linear regression
- Generalised linear models
- Gaussian discriminant analysis
- Tree-based & ensemble methods
Check this👇
May 7 • 9 tweets • 3 min read
5 Agentic AI design patterns, clearly explained (with visuals):
Agentic behaviors allow LLMs to refine their output by incorporating self-evaluation, planning, and collaboration!
The visual depicts the 5 most popular design patterns for building AI Agents.
Let's understand them below!
May 6 • 12 tweets • 4 min read
Let's generate our own LLM fine-tuning dataset (100% local):
Before we begin, here's what we're doing today!
We'll cover:
- What is instruction fine-tuning?
- Why is it important for LLMs?
Finally, we'll create our own instruction fine-tuning dataset.
Let's dive in!
May 4 • 11 tweets • 3 min read
Let's fine-tune Qwen 3 (100% locally):
Before we begin, here's what we'll be doing.
We'll fine-tune our private and locally running Qwen 3.
To do this, we'll use:
- @UnslothAI for efficient fine-tuning.
- @huggingface transformers to run it locally.