(Fake) LLM ChatBot with FastApi (Backend) and Streamlit (Frontend)

This project demonstrates how to create a real-time conversational AI by streaming responses from an LLM. It uses FastAPI to create a web server that accepts user inputs and streams generated responses back to the user and streamlit for creating a simple chatbot interface.

Getting Started

Prerequisites

Python 3.11
Poetry -> pip install poetry
Docker (optional, for containerized deployment) [Container have been tested in Window environment, for Mac might be needed some adjustment]
Make (to use Makefile commands)

Running Application on local machine

Install dependencies:
```
make install_env
```
Run Backend Application:
```
make run_backend
```
Run Frontend Application:
```
make run_backend
```

Running Application on docker containers

Build images
```
make docker_build_app
```
Run containers
```
make docker_app_up
```
Note: In the logs, it may appear that the app is deployed on 0.0.0.0:, but it is actually accessible on localhost:.