Skip to content

DrPolat/LangChain-Summarize-Text-From-YouTube-or-Website

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

LangChain-Summarize-Text-From-YouTube-or-Website

This Streamlit-based application allows users to summarize content from YouTube videos or websites using the Groq API and LangChain framework.

Features:

  • Groq API Integration: Utilizes the Groq API for large language model inference.
  • Content Summarization: Provides a summarized output from both YouTube videos and websites.
  • Validation & Input Handling: Includes validation for API key and URL inputs, ensuring a smooth user experience.
  • Document Processing: Uses loaders for YouTube and website content, followed by text splitting and summarization.

Methodology:

  • Input Handling: Users input their Groq API key and a URL (either YouTube or a website).
  • Data Loading: Depending on the URL type, either YoutubeLoader or UnstructuredURLLoader is used.
  • Text Splitting: Documents are split into smaller chunks for summarization using RecursiveCharacterTextSplitter.
  • Summarization: The LangChain framework, specifically the map_reduce chain, is employed to generate a comprehensive summary from the split chunks.

I would like to state that I benefited from the codes used by Krish Naik.

About

LangChain: Summarize Text From YouTube and Website

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages