L4 - Components

Overview

Deep dive into LangChain building blocks: prompts, chat models (Gemini), output parsers, text splitters, embeddings/vector stores, retrievers, LCEL piping, and a tool-using agent.

Contents

• [langchain_components.ipynb]
• [ex1.ipynb]
• [ex2.ipynb]
• [ex3.ipynb]

Setup

• Environment variable: set GOOGLE_API_KEY (e.g., via a local .env).
• Install:
  • pip install langchain langchain-google-genai langchain-text-splitters langchain-community faiss-cpu python-dotenv numexpr pytz

How to Use

• Open notebooks in Jupyter and run cells top‑to‑bottom.
• Start with langchain_components.ipynb, then try ex1 → ex2 → ex3.
• If a cell needs API access, ensure GOOGLE_API_KEY is set and restart the kernel.

Models

• Recommended: gemini-2.5-flash
• Fallbacks (if not enabled): gemini-1.5-pro, gemini-1.5-flash

Exporting (optional)

• HTML: jupyter nbconvert --to html langchain_components.ipynb
• PDF (Chromium): jupyter nbconvert --to webpdf langchain_components.ipynb --WebPDFExporter.allow_chromium_download=True

Developer

• Dr. Partha Majumder