Maria Waheed@MariaWaheed

AI BlogCurate is a Falcon LLM, LangChain and StreamLit based AI app for doing Top AI and Data Science Articles Search, Shortlisting, Analysis and Aspect based Rankings for given Topic. It's goal is to help Data Science and Artificial Intelligence students, enthusiasts and professionals in learning, acquiring skills learning and staying up-to-date through the best articles. AI BlogCurate searches for blogs/articles on the given topic from popular Data Science and AI articles websites including Medium/TowardsData Science, AnalyticsVidhya and KDNuggets. The articles are first short-listed by title relevance using Falcon-2 180B LLM using AI71 API. Then article content is scrapped and analyzed thoroughly through LLM. The scores of articles related to different aspects are computed and an overall rank is estimated. The Top 5 ranked articles urls and article information are displayed along with the scores for different aspects. Following are the Features of BlogCurate - Article Search, information extraction and analysis, from multiple sources. - Initial Shortlisting by Estimating article title relevance to topic. - Ranking and showing Top 5 Articles according to Overall Score. - Title, URL and Publish Date display. - Article Keywords extraction and display. - Publish Date Extraction - Score for Article Content Quality. - Score for Article Content Structure and Organization. - Score for Article Content Relevance. - Score for Article Practical Implementation Demonstration. - Score for Article Publish Date Recency. - Overall Article Score considering all aspects.

ReadAid.ai is a LangFlow and StreamLit based app for Dyslexia & ADHD reader friendly content search, structuring and display. It uses Web Search, Agents and Prompt Engineering to generate content on a given topic with suitable language, structure, formatting and display to help Dyslexic and ADHD readers. It was developed for LangFlow hackathon by lablab.ai A LangFlow Custom Component was developed for Content Generation. It uses Tavily Search API combined with a LangChain ReAct Agent for web scrapping, reasoning and content collection. This Custom Component is helpful to be reused for other LangFlow projects too. Research was done on readability for Dyslexia & ADHD readers to make guidelines with many considerations for structuring, formatting and displaying the content. Prompt Engineering was done and those guidelines were used inside a GPT-4o Prompt that generates an HTML with suitable formatting. A StreamLit App was developed that takes the topic as user input and uses the LangFlow Flow's JSON in the Python code, to get the result HTML and displays it.

It’s a great opportunity to: 🚀 Leverage Google’s advanced Gemma 2 models to create cutting-edge solutions. 💰 Access resources to support your project development. 🌟 Receive guidance from expert mentors throughout the hackathon. 🤝 Work solo or in teams to bring your ideas to life. 🏆 Compete for a chance to choose from unique Google swag and enjoy an opportunity to meet the Gemma team for the best solutions! 🧑🏻‍💻 Sign up before the Kick-Off Stream to secure your spot! 🗓️ On-site Workshops: Join us in-person at Google Cloud Space in London on 28th November from 5:00 PM to 9:00 PM UK time (GMT) for hands-on workshops

Build a productive AI Agent and compete in this challenge. 💰 $10,000 prize pool for the winners! 🚀 Take your chance and build a proactive AI Agent. 🌟 Expert mentors will guide you every step of the way. 🤝 Work alone or form a team to build something extraordinary. 🌉 Join us online or in person in San Francisco for an unforgettable experience! 🧑🏻‍💻 Sign up before the Kick-Off Stream to secure your spot!

🌟 Explore new AI capabilities 🤝 Collaborate and build something extraordinary. 👥 Take part alone or form a team with other participants. 🎓 Receive guidance from expert mentors. 🏆 Compete for $20,000 in Prizes. 🧑🏻‍💻 Sign up before the Kick-Off Stream to secure your spot!