Day 76 of #100DaysOfDataScience Continued LangGraph >Implemented persistence with checkpointers >Enabled resuming workflows >Added short-term memory for chatbots >Integrated human-in-the-loop interaction >Used thread IDs for parallel execution >Enabled checkpoint replay #AI

Day 77 of #100DaysOfDataScience Continued LangGraph >Built a simple chatbot UI with Streamlit >Used st.chat_message & st.chat_input >Managed state with session_state >Integrated LangGraph backend with thread IDs #AI #LangGraph

Day 78 of #100DaysOfDataScience Continued LangGraph >Enabled streaming in chatbot >Switched invoke with stream (Python generator) for faster, human like replies >Used Streamlit’s write_stream for typewriter effect with mid stream cancel + token savings #AI #LangGraph

Day 79 of #100DaysOfDataScience Continued LangGraph >Built on yesterday’s streaming work >Added buffering for cleaner message flow >Improved mid stream cancel handling >Optimized token usage for better efficiency #AI #LangGraph

Day 80 of #100DaysOfDataScience Continued LangGraph >Replaced in-memory saver with SQLite for persistent chat history >Enabled multi threaded sessions stored in DB >Synced backend checkpoints with Streamlit UI >Verified stored chats using SQLite viewer #AI #LangGraph

- you are - a random CS grad with 0 clue how LLMs work - get tired of people gatekeeping with big words and tiny GPUs - decide to go full monk mode - 2 years later i can explain attention mechanisms at parties and ruin them - here’s the forbidden knowledge map - top to bottom,

Dear Data Analyst/Scientist. Read these books and you'll be miles ahead in your Data journey. To get it: 1. Follow me (so I can DM you) 2. Like and retweet 3. Reply with "Data"

We've all dealt with activation functions while working with neural nets. - Sigmoid - Tanh - ReLu & Leaky ReLu - Gelu Ever wondered why they are so important❓🤔 Let me explain... 👇

Best thing to learn in 2025: AI & ML And, Best place to learn it: - 100 Days of ML - 100 Days of DL - Math for ML - Generative AI - Agentic AI - MCP

Microsoft literally dropped the best free Generative AI course you’ll ever see

Day 81 of #100DaysOfDataScience Intro to LangSmith >why observability is critical in LLM apps >how LangSmith traces every step in LangGraph workflows >walked through projects, traces & runs for debugging >covered monitoring, evaluation & prompt experimentation basics #AI

A youtube playlist so goated that it beats all your university courses

Engineers need to communicate effectively when building AI Systems. These terms will help you use a shared vocabulary. This is useful when discussing concepts, reading papers, or collaborating with teammates. Listed in order. 00:00 Agenda 00:28 1. Large Language Model 01:28

8 RAG architectures for AI engineers:

Introduction to various #ReinforcementLearning #Algorithms: bit.ly/2UPHbSj ————— #DataScience #AI #MachineLearning #ML #DeepLearning #DataMining #Mathematics #Gamification ————— + See this foundational book (2nd edition): amzn.to/3UtbeAa

Day 82 of #100DaysOfDataScience Continued LangGraph >brought observability into the chatbot with LangSmith >tracked token usage, latency & full conversation flow >made chat traces clearer with threads & easy to read names #AI #LangSmith #LangGraph

20+ AI Agent apps built with Google ADK. It covers everything from a single agent academic researcher to multi-agent data scientist. 100% Opensource with step-by-step instructions.

Day 83 of #100DaysOfDataScience Continued LangGraph >integrated tools into the chatbot ( calculator, web search & stock prices) >added Tool Node and Tools Condition for smart routing >enabled multi-step queries by refining tool outputs via LLM #AI #LangGraph #LangSmith

𝗔𝗜, 𝗠𝗟, 𝗮𝗻𝗱 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝗰𝗲 AI, ML, and Data Science are some of the most trending technologies to learn in today’s digital era. Access a complete collection of 𝗔𝗿𝘁𝗶𝗳𝗶𝗰𝗶𝗮𝗹 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲, 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴, 𝗮𝗻𝗱 𝗗𝗮𝘁𝗮