pandastable VS streamlit

If you're looking to implement a GUI of some sort, make sure you're not reinventing the wheel. PandasTable should be able to do exactly what you're looking for.

Streamlit: Streamlit turns data scripts into shareable web apps in minutes.

From the official website, Streamlit is a faster way to build and share data apps. It is an open-source Python library that helps you build web applications for sharing analytical results, building complex interactive experiences, and iterating on top of new machine-learning models.

The dashboard itself was built with the help of Cursor. As usual, I was faster than if I had done it alone but I still suffer some hallucinations (Cursos suggested to use a Cell Renderer that made a lot of sense but that, unfortunatley, didn't exist and for a couple of bugs I had to go the "old way" and find myself the solution in StackOverflow and the Streamlit forums)

This recipe uses Streamlit to create a web app that interactively visualizes the e-commerce data and anomalies, and allows users to prompt OpenAI for an explanation of a particular anomaly. Using the OpenAI API allows us to access pre-trained AI models like GPT-3, DALL-E, and Codex.

streamlit

Streamlit is an open source platform that turns your Python scripts into shareable web apps in minutes with just a few lines of code. These interactive web apps are often the demo apps for most ML projects. The most fascinating thing about this platform is that it requires no front-end or back-end experience. Moreover, Streamlit lets you create these sites without HTML, CSS, or JavaScript, without defining routes and focusing on handling HTTP requests.

Streamlit for the web interface

My first attempt to design this GUI was based on Streamlit. The GUI creation worked flawless, but I hit an essential limitation: Streamlit apps reload their code on every interaction, which triggers the recreation of LLM objects too, removing the chat history in the process. Although it is possible to define global stateful objects, the framework relies internally on serialization with the pickle data format. This could not be applied to an autogen agent. Therefore, I could not continue with Streamlit.

In this guide, I’ll show you how to create a chatbot using Retrieval-Augmented Generation (RAG) with LangChain and Streamlit. This chatbot will pull relevant information from a knowledge base and use a language model to generate responses.