Object oriented programming in Python, clearly explained: We break it down to 6 important concepts:

- Object 🚘
- Class 🏗️
- Inheritance 🧬
- Encapsulation 🔐
- Abstraction 🎭
- Polymorphism 🌀

Let's take them one-by-one... 🚀

Bayes' Theorem clearly explained: Bayes' Theorem is a cornerstone of probability theory!

It calculates the probability of an event, given that another event has occurred.

It's like updating your guess with fresh information!

Before we delve into the details, let's take a quick look at its formula:

Let's build a corrective RAG (CRAG) agentic workflow, step-by-step (100% local): Before we dive in, here's a quick demo of our agentic workflow!

Tech stack:

- @Llama_Index workflows for orchestration
- @Linkup_platform for deep web search
- @Cometml's Opik to trace and monitor
- @Qdrant_engine to self-host vectorDB

Let's go! 🚀

AI Engineering Hub just crossed 3k stars on GitHub!

It’s 100% open-source, packed with 30+ hands-on tutorials that many would charge $1,000+ for...

Here's a small sample of what you get for free: 1️⃣ Multi-agent YouTube Trend Analysis App

Learn to gather trending topics using agents & transform data into actionable insights.

Check this out👇
github.com/patchy631/ai-e…

Let's build a multi-agent best flight finder app, step-by-step (100% local): Before we begin, here's a quick demo of what we're building!

You will learn:

- @CrewAIInc for multi-agent orchestration
- @BrowserbaseHQ's headless browser tool
- @Ollama to locally server DeepSeek-R1

Let's go! 🚀

KV caching in LLMs, clearly explained (with visuals): KV caching is a technique used to speed up LLM inference.

Before diving into the internal details, look at the inference speed difference demonstrated in the video:

- with KV caching → 9 seconds
- without KV caching → 42 seconds (~5x slower)

Let's dive in! 🚀

Let's build a multimodal RAG app using Qwen2.5-VL Max (100% local): Before we begin, here a quick demo of what we're building

We'll use:

- ColPali to process complex docs with text, images and more
- @Alibaba_Qwen 2.5 VL as multimodal LLM
- @qdrant_engine as the vector database

Let's go! 🚀

Let's fine-tune DeepSeek-R1 (distilled Llama) 100% locally: Before we begin, here’s what we’ll be doing:

We’ll fine-tune our private and locally running DeepSeek-R1 (a distilled Llama variant).

Tech stack:

- @UnslothAI for efficient fine-tuning.
- @Ollama to run it locally.

Let’s go! 🚀

10 great Python packages for Data Science not known to many: 1️⃣ CleanLab

You're missing out on a lot if you haven't started using Cleanlab yet!

Cleanlab helps you clean data and labels by automatically detecting issues in a ML dataset.

It's like a magic wand! 🪄✨

Check this out👇
github.com/cleanlab/clean…

Let's build an enterprise-grade, agentic RAG over complex real-world docs, step-by-step: We gonna do RAG over MIG 29 (a fighter aircraft) flight manual, which includes complex figures, diagrams, and more.

(Watch the video below)

Tech stack:

- @CrewAIInc for agent orchestration
- @EyelevelAI's GroundX for SOTA document parsing

Let's go! 🚀

Let's build a trustworthy RAG app that provides a confidence score for each response: Before we dive in, here's a quick demo of what we're building!

Tech stack:

- @Llama_Index for orchestration
- @CleanlabAI's trustworthy LLM
- @Qdrant_engine to self-host a vectorDB
- LlamaParse to make complex docs LLM ready.

You get both score and reasoning! ✨

Let's go! 🚀

Let's build a multi-agent financial analyst, step-by-step: Before we start, here's what we're building today.

Given a query the app analyses and plots stocks gains for the company you specify.

Tech stach:

- @crewAIInc for multi-agent orchestration.
- @SambaNovaAI's fastest inference engine to use DeepSeek-R1 as the LLM.

Let's go! 🚀

4 ways to run LLMs like DeepSeek-R1 locally on your computer: Running LLMs locally is like having a superpower:

- Cost savings
- Privacy: Your data stays on your computer
- Plus, it's incredibly fun

Today, we'll explore some of the best methods to achieve this.

Let's go! 🚀

How LLMs work, clearly explained: Before diving into LLMs, we must understand conditional probability.

Let's consider a population of 14 individuals:

- Some of them like Tennis 🎾
- Some like Football ⚽️
- A few like both 🎾 ⚽️
- And few like none

Here's how it looks 👇

Let's compare OpenAI o3-mini and DeepSeek-R1 using RAG: OpenAI just dropped o3-mini in response to DeepSeek-R1!

Today, we build a Streamlit app to compare and evaluate them using RAG.

Tech stack:

- @Llama_Index for orchestration
- @Cometml Opik for evaluation
- @Streamlit for the UI

Let's go! 🚀

Let's build a text-to-image generation and understanding app, using DeepSeek-Janus (100% local): Before we start, here's a quick demo of what this app does!

It's a 2-in-1:

Tech stack:
- @Deepseek_AI's Janus-pro as LLM
- @Streamlit for UI

1️⃣ Text-to-image generation demo:

Let's build a browser-use agent, similar to OpenAI operator, but utilizing open-source tools: Simply put, browser use is making agents use websites just like us.

Before we start, here's a quick demo of what we're building!

Tech stack:

- @Gradio for the UI
- @browser_use to create the agent
- @Google's latest gemini-2.0-flash-exp as LLM

Let's go! 🚀

Let's compare DeepSeek-R1 and OpenAI-o1 using RAG: DeepSeek-R1 delivers OpenAI-o1 level intelligence at 90% less cost.

Today, we build a Streamlit app to compare and evaluate them using RAG.

Tech stack:

- @Llama_Index for orchestration
- @Cometml Opik for evaluation
- @Streamlit for the UI

Let's go! 🚀

Let's build a multi-agent YouTube video analyst, powered by DeepSeek-R1 (100% local): This app can scrape videos from the multiple YouTube channels and report trends & insights.

Tech stack:

- @crewAIInc for multi-agent orchestration.
- Bright Data for reliable web-scraping at scale.
- @Streamlit for the UI.

Here's a quick demo of what we're building:

Let's build an Agentic RAG app using DeepSeek-R1 (100% local): DeepSeek-R1 delivers OpenAI-o1 level intelligence at 90% less cost.

This agentic app searches your docs and falls back on web search if needed.

In the video, I test it for both types of queries.

Tech stack:

- @CrewAIInc for agent orchestration
- @firecrawl_dev for web search

Let's build a RAG app using DeepSeek-R1 (100% local): DeepSeek-R1 delivers OpenAI-o1 level intelligence at 90% less cost.

Before we dive in, here's a quick demo of what we're building!

Tech stack:

- @Llama_Index for orchestration
- @DeepSeek_AI R1 served as LLM
- @Ollama to locally serve R1
- @Streamlit for the UI

Let's go! 🚀