Selected engineering work
YouTube video summarisation
Published in portfolio:
A Streamlit prototype that retrieves YouTube transcripts, splits the text and generates summaries using LangChain and GPT-3.5.
My contribution
Prototype adaptation
Published a transcript-summarisation prototype in my GitHub portfolio, bringing transcript retrieval, text chunking and language-model summarisation into a Streamlit interface.
Project context
The repository README references the upstream DevRico003/youtube_summarizer project. This is presented as an adaptation, without claiming original authorship of every component.
Generative AI · Workflow
How it works
Retrieve
Read the transcript associated with a YouTube URL.
Split
Break the transcript into chunks using LangChain.
Summarise
Generate and display a text summary in Streamlit.
Explore the work
The portfolio date records the public listing. It does not establish the project's development dates.
Project description and engineering work
The application takes a YouTube URL and works from its transcript. Text chunks are passed through a language-model summarisation workflow, with the result shown in a Streamlit interface.
The repository documents a GPT-3.5-based implementation and acknowledges that generated summaries may need review. The linked source is a historical prototype; the portfolio itself does not call the model or process videos.
The README’s installation instructions reference DevRico003/youtube_summarizer, which is retained here as upstream attribution.