Fareed Khan

train-llm-from-scratch. A straightforward method for training your LLM, from downloading data to generating text.

all-agentic-architectures. 35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.

all-rl-algorithms. Implementation of all RL algorithms in a simpler way

train-deepseek-r1. Building DeepSeek R1 from Scratch

complex-RAG-guide. A step by step implementation of a complex RAG pipeline to solve real world situations

Multi-Agent-AI-System. Building a Multi-Agent AI System with LangGraph and LangSmith

optimize-ai-agent-memory. 9 Different Ways to Optimize AI Agent Memories

KG-Pipeline. Converting Unstructured Data to a Knowledge Graph: An End-to-End Pipeline

rag-ecosystem. Understand and code every important component of RAG architecture

AI-text-to-video-model-from-scratch. In this blog, we will build a small scale text-to-video model from scratch. We will input a text prompt, and our trained model will generate a video based on that prompt.

agentic-rag. Agentic RAG to achieve human like reasoning

create-million-parameter-llm-from-scratch. Building a 2.3M-parameter LLM from scratch with LLaMA 1 architecture.

Building-llama3-from-scratch. LLaMA 3 is one of the most promising open-source model after Mistral, we will recreate it's architecture in a simpler manner.

best-llm-finder-pipeline. Agentic RAG, Multi-Agent Systems, and Vision Reasoning are three pipelines to find the perfect LLM

multi-agent-trading-system. Implementation of Deep Thinking Trading System

rag-with-rl. Maximizing the Performance of a Simple RAG using RL

contextual-engineering-guide. Implementation of contextual engineering pipeline with LangChain and LangGraph Agents

temporal-ai-agent-pipeline. Optimizing Dynamic Knowledge Base Using AI Agent

create-stable-diffusion-from-scratch. Implemented a stable diffusion architecture using PyTorch.

basiclingua-LLM-Based-NLP. LLM Based NLP Library.

Detect-AI-text-Easily. Some words that LLM regularly uses

text2video-from-scratch. A Straightforward, Step-by-Step Implementation of a Video Diffusion Model

google-veo3-from-scratch. A Step-by-Step Implementation of Google Veo 3 Architecture from Scratch

qwen3-MoE-from-scratch. A Step-by-Step Implementation of Qwen 3 MoE Architecture from Scratch

gpt4o-from-scratch. Implementation of a GPT-4o like Multimodal from Scratch using Python

train-llama4. Building LLaMA 4 MoE from Scratch

prompt-engineering-cheatsheet. Different Types of Prompt Engineering Techniques

ai-desktop. AI agent that controls a computer

langchain-graphrag-baml. Improving langchain knowledge graphs using baml

train-tiny-llm. Train a 29M parameter GPT from Scratch

ai-agents-eval-techniques. Implementation of 12 AI agents evaluation techniques

rag-with-raptor. A Step-by-Step Implementation of RAPTOR based RAG implementation

Most-powerful-NLP-library. Gemini, as capable as GPT-4, provides a free API with limited access. I tested it with the help of prompt engineering and found that it can solve almost any NLP task you want to tackle.

llm-scale-deploy-guide. An end-to-end pipeline to optimize and host LLM for 100K parallel queries

Understanding-Transformers-Step-by-Step-math-example. Understanding Large Language Transformer Architecture like a child

ai-debugger. An automated Python tool that uses LLMs and internet to automatically fix your code until it runs perfectly.

big-data-with-KG. Handling Big Data with Knowledge Graph: A Detailed Guide

Gemini-AI-chatbot. This web application is designed to facilitate seamless communication with the Gemini API, and it's available for free.

save-llm-api-cost. A straightforward method to reduce your LLM inference API costs and token usage.

ai-gaming-agent. A step by step implementation of building an AI agent that plays 3d shooting game

agentic-whatsapp-ai. Building an advanced Agentic eCommerce WhatsApp bot

DeepSeek-R1-from-scratch. A straightforward explanation of how DeepSeek R1 works

ai-eval-system. A step by step implementation of a complex AI Evaluation System Designing

gemini-AI-copilot. Intelligent Help for Efficient Programming

ai-vision-dataset-builder. Generating diverse and realistic datasets for computer vision training using AI.

saas-payment-guide. A Beginner's Guide to Monetizing Your Python AI Chatbot

ChatGraph. Talking Graphs: Your Data Speaks Up

qd-langchain-agents. Evolving LangChain agent architectures using the Quality-Diversity (QD) algorithm.

Free-GenAI-APIs-in-2024. We have listed some of the free and powerful GenAI APIs and explore their benefit and usage.

yolov7-face-blur. This repository is created on top of two repositories i.e., yolov7 face detection and yolov7 blurring object

Solve-LLM-Knowledge-Cutoff. A Classification Approach: Making LLM Knowledge-Aware

create-high-quality-dataset-for-computer-vision. This project focuses on generating a diverse and realistic dataset for computer vision training using ChatGPT and a realistic vision image generation model. The process involves dynamically creating prompts, utilizing ChatGPT to generate image descriptions, and generating images based on those descriptions.

Reinforcement-Learning-on-Frozen-Lake-v1-openAI-gym. Using the OpenAI Gym library, I implemented two reinforcement learning algorithms in the Frozen Lake environment.

NLP-1K-Stories-Dataset-Genres-100. This repository hosts a diverse NLP dataset comprising 1,000 stories spanning 100 genres for comprehensive language understanding tasks.

mermaid-to-excalidraw. Generate Excalidraw diagrams from Mermaid

GitHub-Social-Network-Analysis. This project is done using Python library NetworkX, which helps us to analyze the GitHub Social Network Data.

openai-cookbook. Examples and guides for using the OpenAI API

agents-towards-production. This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for real-world launches.

Uber-Movement-Traffic-Flow-Analysis-Python. MS Data Science Social Network Analysis Project

genai-processors. GenAI Processors is a lightweight Python library that enables efficient, parallel content processing.