README.md

LangChain Decoded

A companion guide for the blog post series, LangChain Decoded.

LangChain is an open-source framework created to aid the development of applications leveraging the power of large language models (LLMs). It can be used for chatbots, text summarisation, data generation, code understanding, question answering, evaluation, and more. In this multi-part series, I explore various LangChain modules and use cases, and document my journey via Python notebooks. Feel free to follow along and fork the repository, or use individual notebooks on Google Colab.

Part 1: Models

This notebook is an exploration of LangChain Models. Read this post and follow along!

Part 2: Embeddings

This notebook is an exploration of LangChain Embeddings. Read this post and follow along!

Part 3: Prompts

This notebook is an exploration of LangChain Prompts. Read this post and follow along!

Part 4: Indexes

This notebook is an exploration of LangChain Indexes. Read this post and follow along!

Part 5: Memory

This notebook is an exploration of LangChain Memory. Read this post and follow along!

Part 6: Chains (coming soon)

This notebook is an exploration of LangChain Chains. Read this post and follow along!

Part 7: Agents (coming soon)

This notebook is an exploration of LangChain Agents. Read this post and follow along!

Part 8: Callbacks (coming soon)

This notebook is an exploration of LangChain Callbacks. Read this post and follow along!

All-in-One

This notebook is a consolidation of the individual notebooks above.