<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LangChain &amp; LangGraph on DATATWEETS</title><link>https://datatweets.com/courses/generative-ai/langchain-and-langgraph/</link><description>Recent content in LangChain &amp; LangGraph on DATATWEETS</description><generator>Hugo</generator><language>en</language><copyright>Copyright (c) 2025 Datatweets</copyright><lastBuildDate>Sun, 28 Jun 2026 09:00:00 +0200</lastBuildDate><atom:link href="https://datatweets.com/courses/generative-ai/langchain-and-langgraph/index.xml" rel="self" type="application/rss+xml"/><item><title>Lesson 1 - Why Frameworks</title><link>https://datatweets.com/courses/generative-ai/langchain-and-langgraph/lesson-1-why-frameworks/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/langchain-and-langgraph/lesson-1-why-frameworks/</guid><description>You&amp;rsquo;ve built chains, RAG, and agents by hand. Learn what LangChain and LangGraph provide as building blocks, see a working LangChain chain in a few lines, and learn when to reach for a framework and when not to.</description></item><item><title>Lesson 2 - LangChain Basics</title><link>https://datatweets.com/courses/generative-ai/langchain-and-langgraph/lesson-2-langchain-basics/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/langchain-and-langgraph/lesson-2-langchain-basics/</guid><description>Get hands-on with LangChain&amp;rsquo;s essentials: call the ChatAnthropic model, use prompt templates with variables, parse outputs to clean strings, and compose everything into a chain with the LCEL pipe operator.</description></item><item><title>Lesson 3 - RAG with LangChain</title><link>https://datatweets.com/courses/generative-ai/langchain-and-langgraph/lesson-3-rag-with-langchain/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/langchain-and-langgraph/lesson-3-rag-with-langchain/</guid><description>Recreate the Module 7 RAG pipeline using LangChain in a fraction of the code: split a document with a text splitter, store it in a Chroma vector store with local embeddings, and compose a grounded retrieve-and-generate chain with the LCEL pipe.</description></item><item><title>Lesson 4 - Agents with LangGraph</title><link>https://datatweets.com/courses/generative-ai/langchain-and-langgraph/lesson-4-agents-with-langgraph/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/langchain-and-langgraph/lesson-4-agents-with-langgraph/</guid><description>The think-act-observe loop you wrote by hand is built into LangGraph. Define tools with @tool, spin up an agent with create_agent, read its message trajectory, and give it memory across turns with a checkpointer and a thread id.</description></item><item><title>Lesson 5 - Guided Project: LangGraph Agent</title><link>https://datatweets.com/courses/generative-ai/langchain-and-langgraph/lesson-5-guided-project-langgraph-agent/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/langchain-and-langgraph/lesson-5-guided-project-langgraph-agent/</guid><description>The capstone: rebuild the Module 8 research assistant on LangGraph. Combine a retrieval tool over a Chroma vector store, a calculator, a planning system prompt, and checkpointer memory into an agent that plans, retrieves, computes, and answers multi-step questions from your docs.</description></item></channel></rss>