Generative AI

English Channel video titled: "How to Run Qwen 2.5 Locally (Multiple Methods)" Hindi Channel video titled: "How to run Qwen2.5 Locally ?" 🔹 What You'll Learn: ✅ Method 1: Using Hugging Face (transformers) – How to download and load Qwen 2.5 from Hugging Face for local use. ✅ Method 2: Using Ollama + LangGraph – How to run Qwen 2.5 with Ollama and build a chatbot with LangGraph.

English Channel Video titled: "LangGraph + Deepseek R1: How to Build a Local AI Chatbot" HIndi Channel video titled: "Build Chatbot using Deepseek R1 and LangGraph | Local AI Chatbot with Ollama" 🔹 What you'll learn in this video: ✅ How to install and use Ollama to download Deepseek R1 ✅ Connecting Deepseek R1 with LangGraph for chatbot development ✅ Running a local AI-powered chatbot without cloud dependencies

English Channel Video titled: "How to Fine-Tune DeepSeek R1 LLM (Step-by-Step Tutorial)" HIndi Channel Video titled: "Complete Guide: Fine-Tuning DeepSeek R1 LLM (Step-by-Step)" 🔍 What You’ll Learn: 1- What is DeepSeek-R1 and its different model sizes (1.5B to 671B). 2- Hardware requirements for training DeepSeek-R1 (GPU, CPU, RAM, Storage). 3- How to choose an affordable cloud GPU provider (why I chose ThunderCompute ). 4- Step-by-step guide to creating a remote GPU instance. 5- Setting up your Python virtual environment and installing required deep learning libraries. 6- Downloading the DeepSeek-R1 7B model from Hugging Face. 7- Installing and using PEFT and LoRA for efficient fine-tuning. 8- Uploading and running training scripts on remote servers. 8- Downloading your trained model locally for inference.

English Channel Video titled: "How to Use DeepSeek-R1 with LangChain & Streamlit" HIndi Channel Video titled: "Run Deepseek-R1 locally using Langchain" In this video, I have explained how to use the DeepSeek-R1 model with LangChain and Streamlit to build an AI-powered application. I walk you through the step-by-step implementation, from setting up the model to integrating it with LangChain for natural language processing and using Streamlit to create a simple user interface. By the end of this video, you will learn how to: ✅ Set up DeepSeek-R1 with LangChain ✅ Build a chatbot or AI app using Streamlit ✅ Run and test the model easily

L-21 (English Channel) and (Hindi Channel Video titled - Build an AI-Powered Trip Planner Assistant with CrewAI, LangChain & Streamlit | Full Tutorial) In this tutorial, you’ll learn: ✅ How to integrate multiple AI agents for travel planning (local guide, travel expert, itinerary planner) ✅ How to automate trip creation based on user input ✅ Step-by-step coding walkthrough with live demo ✅ Deploying your AI travel assistant using Streamlit

L-20 (English Channel) and (Hindi Channel Video titled - CrewAI for Beginners: Understanding CrewAI and Its Applications) 🔹 What You’ll Learn: ✅ What is CrewAI, and how does it work? ✅ How CrewAI agents mimic real-world teams in an organization. ✅ Setting up AI-powered agents for research, writing, and automation. ✅ Using web search tools to gather information dynamically. ✅ Automating blog writing and structured workflows using CrewAI.

L-19 (English Channel) and (Hindi Channel Video titled - How to Use RAG with LLMs | Make Your AI Smarter & More Accurate) 📌 **What You’ll Learn:** ✅ Why traditional LLMs have limitations (outdated knowledge, hallucinations, expensive retraining) ✅ How RAG helps AI retrieve fresh information from external sources ✅ The three key steps of RAG: **Retrieval, Augmentation, and Generation** ✅ Hands-on tutorial using **LangGraph, RAG, and a Hugging Face LLM** (no API key required!)

L-18 (English Channel) and (Hindi Channel Video titled - Building a Multi-Agent AI System: How to Use Multiple Agents in LangGraph!) In this video, I’ll walk you through how to build a Multi-Agent AI System using LangGraph. We’ll explore how multiple agents can work together efficiently, passing tasks between specialized agents such as: ✅ Reception Agent – Routes tasks to the right agent ✅ Research Agent – Handles general inquiries ✅ Math Agent – Solves mathematical problems ✅ Billing Agent – Manages payment-related queries ✅ Support Agent – Provides customer assistance

L-17 (English Channel) and (Hindi Channel Video titled - AI Chatbot with LangGraph: Tool Integration, LLM Binding & Agents) In this video, I dive deep into **LangGraph** and show you how to build a powerful chatbot using both **readymade tools** and **custom tools**. Learn how to integrate these tools with a **Large Language Model (LLM)** and use an **agent** to create an interactive AI chatbot. This step-by-step tutorial is perfect for beginners and experienced developers alike. 📌 **Topics Covered:** ✅ Using pre-built tools in LangGraph ✅ Creating custom tools from scratch ✅ Binding tools with an LLM ✅ Implementing an agent to power chatbot responses

L-16 (English Channel) In this video, I’ll walk you through **creating agents in LangGraph**, a powerful framework for building **stateful AI workflows**. Learn how to connect agents with tools and Large Language Models (LLMs) to create intelligent, interactive AI systems. 📌 **What You’ll Learn:** ✅ How to define and set up an Agent in LangGraph ✅ How to connect a tool to the Agent ✅ How the Agent interacts with an LLM to process inputs and generate responses ✅ Hands-on example to understand the complete workflow

L-15 (English Channel) Learn how to build a chatbot using LangGraph in this step-by-step tutorial! This video is perfect for beginners and anyone looking to deepen their understanding of LangGraph and its key components. What you’ll learn in this tutorial: ✅ Introduction to LangGraph and its core concepts ✅ Understanding Nodes, Edges, States, and State Machines ✅ Step-by-step guide to building an interactive chatbot ✅ How all components work together to create a functional AI agent

L-13 (English Channel) and L- Building Agents in LangChain from scratch (Hindi Channel) In this video, I demonstrate how to use different tools in LangChain and showcase how these tools can be combined with LLMs to create various agents. You'll learn: What tools are in LangChain and how they extend the capabilities of LLMs. ✅Step-by-step implementation of tools for tasks like web search, database queries, and more. ✅How to create custom agents in LangChain by integrating multiple tools. ✅Practical examples of how agents can handle real-world tasks by coordinating between LLMs and tools. Whether you're a beginner or an advanced developer, this tutorial will provide you with hands-on knowledge to build intelligent agents using LangChain.

L-12 (English Channel) In this video, we will learn how to build intelligent agents by combining tools and LLMs in LangChain. We start with the theory, explaining the core concepts of LangChain agents and tools, including how they work together to extend the capabilities of LLMs. Next, we move on to practical implementation, where we demonstrate step-by-step how to define and use multiple tools, like a search tool and a calculator, within a LangChain agent. Whether you're a beginner or an AI enthusiast, this video will provide you with a clear understanding of LangChain agents and their powerful integration with tools to solve real-world problems.

L-9 (English Channel) In this video, you'll learn: ✅What Retrieval-Augmented Generation (RAG) is and how it enhances Q&A systems. ✅How to set up and use LangChain to connect various components seamlessly. ✅How to integrate open-source LLMs to build a robust and efficient Q&A app. ✅Step-by-step instructions and code examples to help you follow along.

L-7 (English Channel) We'll explore what RAG is, why it’s an essential tool in the realm of artificial intelligence, and how it functions. Starting with the theory behind RAG, we'll break down its components and explain its significance in enhancing the capabilities of generative models. Then, we'll move on to a practical demonstration, showing you how to implement RAG in real-world scenarios. Whether you're a beginner looking to understand the basics or an enthusiast seeking to deepen your knowledge, this video provides a comprehensive overview of Retrieval-Augmented Generation and its applications.

Meta's latest open-source AI model, Llama 3.1, is here with 405B, 70B, and 8B versions. Key highlights: 405B model rivals the best closed models. Free weights and code, with a license for fine-tuning, distillation, and deployment anywhere. 128k context, multi-lingual, great code generation, and complex reasoning. Llama Stack API. Partners include AWS, NVIDIA, Databricks, Dell, Azure, and Google Cloud. A huge leap for open-source AI! https://llama.meta.com/ https://huggingface.co/blog/llama31

L-5 (English Channel) This tutorial will teach you how to interact with your database using LangChain, LLM and mysql database. We will create a app which will take the input in english which will then be processed by an LLM model to generate SQL queries. These queries will retrieve data from a MySQL database and present the results on our screen. Gemini Pro: https://deepmind.google/technologies/gemini/pro/ ### Get an API key: Head to https://ai.google.dev/gemini-api/docs/api-key to generate a Google AI API key. ### mysql: Ofiicial site link: https://dev.mysql.com/downloads/installer/ ### mysql workbench: Official site link: https://dev.mysql.com/downloads/workbench/

L-4 (English Channel) In this video, you'll learn: ✅How to set up and configure LangChain. ✅How to integrate the OpenAI API for chatbot functionalities. ✅How to use Streamlit to create a user-friendly interface.

L-3 (English Channel) In this video, we will learn about LangChain, a powerful tool for building generative AI applications. I'll guide you through the basics of LangChain and then demonstrate how to use Google's Gemini model to create two exciting applications: a question-answering app and a language translator app. By the end of this tutorial, you'll see how versatile LangChain is and how you can leverage a single model to build multiple AI-driven solutions.