plop
Python, Langchain, OpenAI, & Pinecone stack
What does it do?
Imagine if ChatGPT had context of your specific data and prioritized it while answering. This project allows you to easily take some data that you have (like a Wiki, knowledge base, etc.), and allows you to query OpenAI with the context of your own data.
What do I need to get setup
- Get an
OPENAI_API_KEYfrom your openai.com account. NOTE: You may need to pay $ for this. I tried the free version but it didn't work properly because I kept getting rate limited. - Setup a free Pinecone DB instance and grab the
PINECONE_API_KEYandPINECONE_ENVvariables. - Create a file called
.envwith the environment variables. It should be based on the.env.examplefile. - Install the Dependencies with
pip install -r requirements.txt - Run
python loader.py(one time) to load up some documents into the Pincone Vector DB, and use the Embeddings to save them in a way that can be easily queried later.
How do I use it?
Run python main.py to query the Wiki system with your questions.
What are the peices?
- Python is one of the most popular programming languages and is the de facto Language for AI/ML work.
- Langchain is a framework for developing applications powered by language models.
- OpenAI is an AI research and deployment company. They have amazing tools and an API that allows easy access.
- Pinecone is a cloud hosted Vector Database, which allows your AI to have long-term memory.