Skip to content

This LlamaIndex-based RAG system offers a simple approach to combining retrieval accuracy with generative capabilities, enabling dynamic, knowledge-augmented responses in real time.

Notifications You must be signed in to change notification settings

frezazadeh/Put-Retrieval-Augmented-Generation-RAG-into-Production

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Project Setup Instruction

Follow these steps to set up your environment and install all necessary dependencies:

  1. Install pipenv, the Python virtual environment management tool:

    pip3 install pipenv
  2. Activate the pipenv shell to create a new virtual environment:

    pipenv shell
  3. Install primary dependencies (llama-index and python.env):

    pipenv install llama-index python.env
  4. Install additional packages for HTTP requests and HTML parsing:

    pipenv install requests beautifulsoup4
  5. Run the document downloader script:

    python3 dl-docs.py
  6. Reinstall or update llama-index if necessary:

    pipenv install llama-index
  7. Install the OpenAI API client:

    pipenv install openai
  8. Install the Pinecone client for vector storage:

    pipenv install pinecone-client
  9. Install python-dotenv to manage environment variables:

    pipenv install python-dotenv
  10. Install the Pinecone plugin for llama-index:

    pipenv install llama-index-vector-stores-pinecone
  11. Install unstructured for handling complex data inputs:

    pipenv install unstructured
  12. Install the code formatter black:

    pipenv install black
  13. Install tqdm for progress bars and black (if not installed):

    pipenv install tqdm black
  14. Run the ingestion script:

    python3 ingestion.py
  15. Install streamlit for building web applications:

    pipenv install streamlit
  16. Install streamlit for building web applications:

    streamlit run main.py

Now you are all set up! 🎉

About

This LlamaIndex-based RAG system offers a simple approach to combining retrieval accuracy with generative capabilities, enabling dynamic, knowledge-augmented responses in real time.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages