Metadata-Version: 2.4
Name: rag-ssistant
Version: 0.1.1
Summary: RAGssistant: A RAG Assistant for your tasks
Requires-Python: >=3.11
Requires-Dist: accelerate>=1.7.0
Requires-Dist: chromadb>=1.0.12
Requires-Dist: gradio>=5.33.1
Requires-Dist: hf-xet>=1.1.3
Requires-Dist: huggingface-hub>=0.31.2
Requires-Dist: langchain-community>=0.3.24
Requires-Dist: langchain-huggingface>=0.2.0
Requires-Dist: langchain-mistralai>=0.2.10
Requires-Dist: langchain-text-splitters>=0.3.8
Requires-Dist: langgraph>=0.4.5
Requires-Dist: pydantic>=2.11.4
Requires-Dist: pypdf>=5.5.0
Requires-Dist: sentence-transformers>=4.1.0
Description-Content-Type: text/markdown

# RAG-Powered-AI-Assistant

Welcome to the RAG-Powered AI Assistant repository! This project demonstrates how to build a Retrieval-Augmented Generation (RAG) powered AI assistant.

## Preparation

1. Clone the repository:

   ```bash
   git clone https://github.com/HiIAmTzeKean/RAG-Powered-AI-Assistant
   ```

2. You will have to download the knowledge base of publications from [Ready Tensor](https://drive.google.com/drive/folders/1HAqLXL2W-sh8hqoBb1iSauJ_0wZVRxB9?usp=sharing) and place it under `/data` directory first.

3. Install the required dependencies using `uv`:

    ```bash
   uv sync
   ```

## Required environment variables

- `MISTRAL_API_KEY`: Your Mistral API key.
- `HF_KEY`: Your Hugging Face API key

## Usage

### CLI

To run the AI assistant, use the following command after ensuring that the environment variables are set:

```bash
uv run cli "What are effective techniques for handling class imbalance?"
```

### Web UI

To run the web UI, use the following command and navigate to [the page](http://127.0.0.1:8000) in your web browser:

```bash
uv run ui
```
