A RAG assistant to allow you to chat with any github repo. Learn fast. The default repo is AdalFlow github repo.
- Install dependencies:
poetry install
- Set up OpenAI API key:
Create a .streamlit/secrets.toml
file in your project root:
mkdir -p .streamlit
touch .streamlit/secrets.toml
Add your OpenAI API key to .streamlit/secrets.toml
:
OPENAI_API_KEY = "your-openai-api-key-here"
Run the streamlit app:
poetry run streamlit run app.py
-
Clearyly structured RAG that can prepare a repo, persit from reloading, and answer questions.
DatabaseManager
insrc/data_pipeline.py
to manage the database.RAG
class insrc/rag.py
to manage the whole RAG lifecycle.
-
Conditional retrieval. Sometimes users just want to clarify a past conversation, no extra context needed.
-
Create an evaluation dataset
-
Evaluate the RAG performance on the dataset
-
Auto-optimize the RAG model