Project Info
This project did not submit a demo video on Devpost.
Inspiration
Today news travels faster than ever and it is getting harder and harder to stay up to date but also make sure that the new that you are reading is accurate. We wanted to make determining the accuracy of news articles as easy as possible for users to get with a click of a button. When the news article is analyzed, key topics and phrases are highlighted. Users can then click on the highlighted text to read new and updated information on the topic.
What it does
Our project is a Google Chrome extension that when activated highlights key quotes in the current tab's news article and provides further context on those topics. This analysis is done by Google Gemini's 1.5 Flash.
How we built it
We used Javascript, Google Gemini API, HTML, and CSS. First we read the text on the webpage, sent it to Google Gemini, and then parsed Google Gemini's response with Javascript. Finally, we displayed everything on the webpage using HTML and CSS.
Challenges we ran into
We initially were using another LLM API to analyze news articles but found the performance and formatting too inconsistent. We then switched to Google Gemini's 1.5 Flash and were much more satisfied with the performance.
Accomplishments we're proud of
We are proud of completing a viable product and getting experience with a less popular area of web development.
What we learned
We learned about the process of creating a Chrome extension, Javascript development, using HTML and CSS for essential formatting and styling, and prompt engineering APIs.
What's next
We want to improve the accuracy of our LLM's quote background as well as the design and styling of our quote analysis boxes.
Analysis
View
Metric
- 2
Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.
Technology
- HTMLIn code
- JavaScriptIn code
- Google GeminiClaimed
2 of 3 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
19 KB
Source files
6
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
bluekid2457/ContextClick
7 files · 19 KB · @ 2be481d
Structure
Interface
1 file · 14%Screens, components and styles rendered to the user.
Application logic
5 files · 71%Domain rules, services and shared utilities.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- JavaScript91%
- HTML9%
- Markdown0%
Share of indexed source by file size. Binary and vendored files are excluded.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.