This repository contains various examples of how to use LangChain, a way to use natural language to interact with LLM, a large language model from Azure OpenAI Service. You can discover how to query LLM using natural language commands, how to generate content using LLM and natural language inputs, and how to integrate LLM with other Azure services using natural language connectors. This repository is intended for developers who want to explore the possibilities of using natural language to access and control LLM.
- chat_with_csv.ipynb <-- Example of using LangChain to interact with CSV data via chat. I leveraged a sample dataset of the Sales Performance DQLab Store from Kaggle to chat with data to figure out valuable insight.
- chat_with_csv_verbose.ipynb <-- Example of using LangChain to interact with CSV data via chat, containing a verbose switch to show the LLM thinking process.
- chat_with_multiple_csv.ipynb <-- Example of LangChain (0.0.181 or above) to interact with multiple CSV files data via chat. I leveraged CNBC news data (from data.world, date & title only) and NASDAQ data (from Yahoo Finance) to chat with both datasets to figure out valuable insight.
- chat_with_pdf.ipynb <-- Example of using LangChain to interact with a PDF file via chat (QA Chain). I leverage an awesome book, Machine Learning Yearning, from Andrew Ng to chat with the book.
Enjoy!