varkrish / qa-pilot Goto Github PK

QA-Pilot can chat with github repository or a compressd file(e.g. xz, zip) and using the online/local LLM.

• Chat with github public repository with git clone way
• Chat with compressed file(directories, e.g. xz, zip) with upload way
• Store the chat history
• Select the different LLM models
  • ollama
  • openai

• This is a test project to validate the feasibility of a fully local solution for question answering using LLMs and Vector embeddings. It is not production ready, and it is not meant to be used in production.
• Do not use models for analyzing your critical or production data!!
• Do not use models for analyzing customer data to ensure data privacy and security!!

To deploy QA-Pilot, you can follow the below steps:

1. Clone the QA-Pilot repository:

git clone https://github.com/reid41/QA-Pilot.git

2. Install conda for virtual environment management. Create and activate a new virtual environment.

conda create -n QA-Pilot python=3.10.14
conda activate QA-Pilot

3. Install the required dependencies: NOTE: you might need to re-install the pytorch with cuda pytorch

pip install -r requirements.txt

4. Setup ollama website and ollama github to manage the local LLM model. e.g.

ollama pull <model_name>

ollama list

5. Setup OpenAI, add the key in .env

6. Set the related parameters in config/config.ini, e.g. model provider, model, variable

7. Run the QA-Pilot:

streamlit run qa_pilot.py

• Do not use url and upload at the same time.
• The remove button cannot really remove the local chromadb, need to remove it manually when stop it.
• Switch to New Source Button to add a new project