https://github.com/nirmit27/genai-capstone-project-2025
This repository is dedicated to the development and exploration of generative AI technologies as a part of the capstone project for the 5-day Gen AI Intensive Course with Google.
https://github.com/nirmit27/genai-capstone-project-2025
chatbot embeddings gemini gemini-api generative-ai generative-ai-projects google-ai google-ai-studio kaggle kaggle-competition rag video-understanding
Last synced: 4 months ago
JSON representation
This repository is dedicated to the development and exploration of generative AI technologies as a part of the capstone project for the 5-day Gen AI Intensive Course with Google.
- Host: GitHub
- URL: https://github.com/nirmit27/genai-capstone-project-2025
- Owner: nirmit27
- License: mit
- Created: 2025-04-12T03:09:23.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2025-06-01T16:53:00.000Z (5 months ago)
- Last Synced: 2025-06-02T02:13:36.828Z (5 months ago)
- Topics: chatbot, embeddings, gemini, gemini-api, generative-ai, generative-ai-projects, google-ai, google-ai-studio, kaggle, kaggle-competition, rag, video-understanding
- Language: Jupyter Notebook
- Homepage: https://www.kaggle.com/code/nirmit27/gen-ai-intensive-course-capstone-2025q1-project
- Size: 44.9 KB
- Stars: 0
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# NewsGenius AI
## Overview
Welcome to **NewsGenius AI**, an advanced Capstone Project for the **5-day Gen AI Intensive Course with Google** (March 31 - April 4, 2025). This project summarizes the latest news or YouTube videos on any topic by leveraging generative AI to provide concise, accurate digests of complex information. 📰
### Problem
The information overload in today's digital landscape presents significant challenges for individuals trying to stay informed. Users face difficulties in efficiently processing the overwhelming volume of news articles and video content available across multiple platforms. Traditional consumption methods are time-consuming and often result in missing key insights or context. **NewsGenius AI** addresses this challenge by providing an automated solution that extracts and synthesizes essential information from diverse media sources, enabling users to quickly grasp the core content without sacrificing comprehension.
### Solution
This tool integrates multiple Gen AI capabilities to:
- Efficiently summarize text content from news articles while preserving key information and context.
- Extract and condense important insights from YouTube videos into a well-formatted summary.
- Build a Q&A chatbot leveraging RAG to provide informed answers based on a video summary.
### Gen AI Capabilities
1. **Few-shot Prompting & Structured Output** : Summarization of a news article excerpt with few-shot prompting.
2. **Video Understanding** : Summarization of a YouTube video using the Gemini Pro model.
3. **Retrieval augmented generation (RAG)** : Building a Q&A chatbot leveraging RAG to provide informed answers based on a video summary.
> *The [notebook](./notebook_nirmit27.ipynb) has been submitted for the Gen AI Intensive Course Capstone 2025Q1 Project, open April 4 - April 20, 2025.*