EER (Experiencing, Experimenting, Reflecting) Chatbot

Developed with the software and tools below.

---

Overview

This project implements a chatbot utilizing retrieval mechanisms (RAG) to serve as a question-answering assistant. It leverages excerpts from transcripts of Zoom meetings pertaining to the EER project.

NB: For timescale version of app, see here: https://github.com/sabszh/EER-TIMEBOT

---

Repository Structure

└── /

    ├── README.md
    ├── requirements.txt
    └── src
        ├── data_chunking.py
        ├── main.py
        ├── reformatting_data.py
        ├── streamlit_app.py
        └── timescale

---

Modules

.

File	Summary
requirements.txt	This requirements.txt ensures the application's compatibility and functionality by defining necessary Python packages for the data processing and web application modules of the repository.

src

File	Summary
main.py	The main.py within this repository sets up a chatbot leveraging Pinecone index and HuggingFace embeddings for document search, with custom prompt templates for the EER Project's inquiries.
streamlit_app.py	Core interface of the chatbot, allowing user to select AI models and adjust interaction parameters within a Streamlit-based web app.
reformatting_data.py	The script reformatting_data.py within the repo transforms raw transcript files into a structured CSV format, handling various timestamp styles and creating a standardized naming and storage schema.
data_chunking.py	The data_chunking.py module is responsible for extracting and preparing text data from various document types within a document processing pipeline.

---

Getting Started

Requirements

Ensure you have the following dependencies installed on your system:

• Python: version 3.x.x
• API Keys: Obtain API keys for Hugging Face and Pinecone.

Installation

1. Clone the repository:

git clone https://github.com/sabszh/EER-chatbot-UI/

2. Change to the project directory:

cd 

3. Install the dependencies:

pip install -r requirements.txt

4. Create a .env file in the root directory of the project and add the following:

HUGGINGFACE_API_KEY=your_huggingface_api_key
PINECONE_API_KEY=your_pinecone_api_key
TIMESCALE_API_KEY=your_timescale_api_key

Running

Use the following command to run streamlit app locally using Pinecone index:

streamlit run src/streamlit_app.py

Use the following command to run streamlit app locally using Timescale index:

streamlit run src/timescale/streamlit_app_ts.py