Issue: `requirements.txt` is incomplete and missing required dependencies

[Pratham-U-dev]

Description

The current requirements.txt does not include all of the Python packages required to run the project successfully.

Following the installation instructions in the README:

python -m venv venv
pip install -r requirements.txt
streamlit run main.py

results in runtime errors because several dependencies are missing.

The project only ran successfully after installing the additional packages listed in environment.yml.

---

Environment

• OS: Windows 11
• Python: 3.9.x (recommended by environment.yml)
• Installation Method: Python virtual environment (venv)

---

Steps to Reproduce

1. Clone the repository.
2. Create a virtual environment.

python -m venv venv

3. Activate it.

venv\Scripts\activate

4. Install the dependencies.

pip install -r requirements.txt

5. Run the application.

streamlit run main.py

---

Actual Behavior

The application starts but immediately raises import errors because required packages are missing.

Example:

ModuleNotFoundError: No module named 'dotenv'

After installing python-dotenv, additional missing packages related to the chatbot and Streamlit functionality were also required.

---

Expected Behavior

Running

pip install -r requirements.txt

should install all required dependencies, allowing the application to run without requiring any additional manual installations.

---

Root Cause

The repository contains both:

• requirements.txt
• environment.yml

However, the requirements.txt is not synchronized with the environment.yml.

The Conda environment includes many required packages that are absent from requirements.txt, including dependencies for:

• Streamlit
• LangChain
• OpenAI
• python-dotenv
• Streamlit runtime libraries
• Other supporting packages

As a result, users following the README encounter runtime errors even though they correctly installed the listed requirements.

---

Suggested Fix

Update requirements.txt so it contains all required pip packages from the pip: section of environment.yml.

This will ensure that both installation methods (pip and Conda) provide a consistent environment and prevent users from having to manually install missing dependencies.

---

Additional Suggestion

The README could also be updated to recommend using Python 3.9.x, since the provided environment.yml targets Python 3.9.19, and newer Python versions may introduce compatibility issues with TensorFlow and MediaPipe.

Thank you for the excellent project!