Easy RAG with LangChain and OpenAI

Welcome to the first part of the series "Practical RAG with LangChain under 15 Minutes". In this part we implement an easy RAG application with the help of OpenAI API. You can watch the series at the Youtube, this repo belongs to the first video.

Before we start

After cloning the repo, please install the requirements by doing pip install -r requirements.txt . After that do a pip install unstructured[md] for installing processing Markdown dependencies.

You'll also need your OpenAI api key as a environment variable. You can get your key from your OpenAI account, then do a export OPENAI_API_KEY=yourkeystring at least in Linux. For Windows and Mac, please setup this env variable accordingly.

Running the code

First, run make_database.py to create the database. If you wanna play with the embeddings, next you can run embeddings_play.py. You can finally run go_query.py

More of NLP with Duygu

You can access second video and third video on Youtube as well. Github repos links are provided in the videos.

If you would like more content, don't forget to visit finetuning LLM series of mine, Practical LLM Finetuning Recipes.

Thanks for your visit and happy coding!