https://github.com/ruankie/vid-qa

An app that summarises and answers questions about arbitrary YouTube videos using LangChain and LLMs
https://github.com/ruankie/vid-qa

app autogpt chatgpt embedding gpt langchain large-language-models openai qa streamlit summary tldr transcribe youtube youtube-summary

Last synced: 3 months ago
JSON representation

An app that summarises and answers questions about arbitrary YouTube videos using LangChain and LLMs

• Host: GitHub
• URL: https://github.com/ruankie/vid-qa
• Owner: ruankie
• License: mit
• Created: 2023-05-02T14:18:55.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2023-05-15T20:37:13.000Z (about 2 years ago)
• Last Synced: 2025-03-09T16:52:25.843Z (3 months ago)
• Topics: app, autogpt, chatgpt, embedding, gpt, langchain, large-language-models, openai, qa, streamlit, summary, tldr, transcribe, youtube, youtube-summary
• Homepage:
• Size: 110 KB
• Stars: 6
• Watchers: 1
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
[![GitHub Repo stars](https://img.shields.io/github/stars/ruankie/vid-qa)](https://github.com/ruankie/vid-qa)

# 🎥🗨️ VidQA

## Description

VidQA is an AutoGPT app that summarises and answers questions about arbitrary YouTube videos using LangChain and LLMs.

> 🏗️ Under construction. More coming soon...

> 💡 The main idea for this app came from a [YouTube video](https://www.youtube.com/watch?v=NYSWn1ipbgg) by [Dave Ebbelaar](https://www.youtube.com/@daveebbelaar).

## Setup

1. Set up your virtual env with all the required dependencies

    ```shell

    poetry install

    ```

2. Set your environment variables in a file called `.env` (see `.env.example`)

3. [Create a resource and deploy a model using Azure OpenAI](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/create-resource?pivots=web-portal)

> Note: You can use this directly with OpenAI's API (without using Azure's OpenAI Services) with minor modifications to the code and environment variables

## Usage

> TODO: Add Streamlit app link

> Note: Whe using notebooks, make sure you activate the correct poetry environment. You can set your Python kernel to the value that gets returned when you run `poetry run which python`.

1. Browse the example notebooks in `notebooks/`

## Useful Resources

- https://www.youtube.com/watch?v=NYSWn1ipbgg

- https://platform.openai.com/docs/api-reference

- https://python.langchain.com/en/latest/index.html