A repository for learning LlamaIndex by building a generative ai RAG application.
This is a web application is using a Pinecone as a vectorstore and answers questions about LlamaIndex (sources from LlamaIndex official documentation).
To run this project, you will need to add the following environment variables to your .env file
PINECONE_API_KEY
PINECONE_ENVIRONMENT_REGION
OPENAI_API_KEY
Clone the project
git clone https://github.com/emarco177/llamaindex-documentation-helper.git
Go to the project directory
cd llamaindex-documentation-helper
Download LlamaIndex Documentation
python download_docs.py
Install dependencies
pipenv install
Start streamlit
streamlit run main.py
To run tests, run the following command
pipenv run pytest .