https://github.com/kwokhing/uplimit-project-podcast-frontend

An LLM app to summarize a podcast episode, identifies podcast guests and attempts to retrieve the guest's public information from wikipedia, and identifies key highlights using OpenAI ChatGPT with prompting techniques
https://github.com/kwokhing/uplimit-project-podcast-frontend

llm openai-chatgpt streamlit streamlit-webapp

Last synced: 2 months ago
JSON representation

An LLM app to summarize a podcast episode, identifies podcast guests and attempts to retrieve the guest's public information from wikipedia, and identifies key highlights using OpenAI ChatGPT with prompting techniques

• Host: GitHub
• URL: https://github.com/kwokhing/uplimit-project-podcast-frontend
• Owner: KwokHing
• Created: 2023-08-19T07:23:58.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2023-08-22T07:47:03.000Z (almost 3 years ago)
• Last Synced: 2025-03-25T05:53:33.087Z (over 1 year ago)
• Topics: llm, openai-chatgpt, streamlit, streamlit-webapp
• Language: Jupyter Notebook
• Homepage: https://uplimit-project-podcast-frontend.streamlit.app/
• Size: 3.93 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
## [Uplimit](https://uplimit.com/course/building-ai-products-with-openai) Project: Podcast Summarizer

In this project, an LLM app was built to summarize a podcast episode, identifies the podcast guests and attempts to retrieve the guest's public information from wikipedia, and identifies key highlights using [OpenAI ChatGPT](https://platform.openai.com/) and prompting techniques. Cloud deployment provider [Modal](https://modal.com/) was used to convert the information extraction function into a cloud on demand service, while the front-end interface was deployed on [Streamlit](https://streamlit.io/)

### The solution was developed in three parts: ###

**Part 1**: Use a large language model from OpenAI to build the information extraction functionality, paired with a speech-to-text model for transcribing the podcast.

**Part 2**: Use a simple cloud deployment provider to easily convert the information extraction function to run on demand – This would be the app backend.

**Part 3**: Use ChatGPT from OpenAI as your coding assistant to create and deploy a front-end that allows users to experience the end-to-end functionality.

Try it [here](https://uplimit-project-podcast-frontend.streamlit.app/)

## Getting started

Open `Uplimit_Week1_Summarise_Podcast_GPT.ipynb` on [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://githubtocolab.com/KwokHing/Uplimit-Project-Podcast-Frontend/blob/master/Uplimit_Week1_Summarise_Podcast_GPT.ipynb). The notebook consists of further technical details.