🦜🔗 LangChain — Basic to Advance

This repository is a step-by-step guide to mastering LangChain, starting from core concepts and progressing to advanced topics like retrievers, tool calling, and agents. Each lesson is self-contained and designed to help you understand not just how LangChain works, but why each part matters.

---

Table of Contents

Lesson	Title	Description	Why This Is Important
L0	LangChain_Introduction.md	Overview of LangChain, its ecosystem, and use cases.	Sets the foundation — understand what LangChain is and where it fits in the LLM application stack.
L1	LangChain_L1_Models.ipynb	Explore LLMs, ChatModels, and their integration with LangChain.	Learn how to connect and run foundational language models — the core of every LangChain app.
L2.1	LangChain_L2.1_Prompts.ipynb	Deep dive into PromptTemplates, few-shot prompts, and prompt engineering.	Master prompt design — a key skill for controlling LLM outputs effectively.
L2.2	LangChain_L2.2_Prompts_app.py	Streamlit app demonstrating prompt templates in action.	Bridges theory and practice — visualize how different prompts change results.
L3	LangChain_L3_Structure_output.ipynb	Learn how to structure and validate LLM outputs.	Ensures your model outputs are predictable and usable for downstream tasks.
L4	LangChain_L4_Structure_output_parser.ipynb	Covers OutputParsers and how to parse structured responses.	Output parsing makes AI responses machine-readable — vital for automation.
L5	LangChain_L5_Chains.ipynb	Introduction to Chains — combining multiple LLM calls logically.	Core LangChain concept — chains enable complex workflows from simple components.
L6.1	LangChain_L6.1_Runnables.ipynb	Understanding Runnables from first principles.	Builds intuition on LangChain's execution model — foundation for advanced orchestration.
L6.2	LangChain_L6.2_Runnables.ipynb	Implementation of sequential, parallel, and conditional runnables.	Demonstrates real-world scenarios where tasks need parallel or conditional flows.
L7	LangChain_L7_Docu_Loader.ipynb	Using document loaders for PDFs, text files, web pages, etc.	Enables dynamic data ingestion — essential for building retrieval systems.
L8	LangChain_L8_Text_Splitting.ipynb	Techniques for text chunking and preprocessing.	Prepares text for embedding/vectorization — ensures better retrieval accuracy.
L9	LangChain_L9_Vector_Store.ipynb	Covers embeddings and vector databases (FAISS, Chroma).	Key to building retrieval-augmented generation (RAG) systems.
L10	LangChain_L10_Retrivers.ipynb	Learn how retrievers work and integrate with vector stores.	Bridges embeddings with LLMs — essential for context-aware chatbots.
L11.1 (Front-end)	LangChain_L11_Chatbot.py	Streamlit chatbot with message store integration.	Build an interactive chatbot UI — connecting LangChain logic with users.
L11.2 (Back-end)	LangChain_L11.2_Chatbot.py	Backend logic for chatbot, conversation handling.	Separates UI from logic — promotes scalable chatbot architecture.
L12.1	LangChain_L12.1_Tools_Calling.ipynb	Introduction to tool calling: what, why, and how it works.	Understand how LLMs can interact with external tools and APIs.
L12.2	LangChain_L12.2_Tools_Calling.ipynb	Practical demo: currency converter tool using LLM tool calling.	Learn by doing — see real examples of LLM + tools integration.
L13	LangChain_L13_Agents.ipynb	Explore Agents, their architecture, and execution flow.	Agents are the heart of autonomous systems — mastering them unlocks advanced LLM use cases.

---

🚀 How to Use This Repo

1. Clone the repository

   git clone https://github.com/shantnu-singh/LangChain-Basic-to-Advance.git
   cd langchain-basic-to-advance

2. Install dependencies

   pip install -r requirements.txt

3. Run notebooks and apps

   • Jupyter notebooks (.ipynb) → Run step-by-step

   • Streamlit apps (.py) →

     streamlit run LangChain_L2.2_Prompts_app.py

---

🧠 What You’ll Learn

• Core LangChain modules: Models, Prompts, Chains, Runnables
• Data ingestion: Document Loaders, Text Splitters, Vector Stores
• Retrieval Augmented Generation (RAG) in details
• Tool calling and integration with external APIs
• Building real chatbots and autonomous agents

---

💡 Author & Credits

Author: Shantnu Singh Repo: LangChain Basic to Advance

If you find this helpful, ⭐ star the repo and share it with others learning LangChain!