README.md

RAG Step-by-Step

This is a working example of Frank Denneman's article RAG Architecture Deep Dive which defines the Load-Transform-Embed-Store workflow. For building RAG applications.

get_transcript.py: retrieves transcripts from Youtube videos
create_embeddings.py: splits the transcripts in chunks and creates vectors from the data
upsert-serverless.py: creates a Pincone index and upserts the embeddins to a serverless vector database
app.py: a Streamlit client for querying the Pinecone database and prompting OpenAI

To run the exanples:

python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

To run the client application:

streamllit run app.py