fbpx

LLM for Web Scraping & Prompts

Unlock the full potential of LLMs for web scraping and performance optimization.

Course details

Discover the immense potential of Large Language Models (LLM) for web scraping and information extraction in this comprehensive course. Participants will learn to use LLMs effectively for web scraping, including connecting websites, utilizing LlamaIndex, and building a Question-Answering System with web data. The course also focuses on optimizing LLMs for peak performance through prompt design and caching techniques. Ethical considerations in Generative AI are explored, covering privacy, bias, and misinformation, with a forward-looking discussion on the future implications of this technology. Whether you’re a data enthusiast, developer, or AI professional, this course equips you with the skills and insights to leverage LLMs for practical applications and ethical AI use.

Please bring along:

  • 1x Laptop
  • Purchased ticket

Schedule

  • Leveraging LLM for Web Scraping and Information Extraction

    Day 1

  • Optimizing LLM for Performance Enhancement

    Day 2

  • Ethical Considerations and Future Implications of Generative AI with LLM

    Day 3

Course Producer

Samuel Chan

Machine learning practitioner in the field of marketing automation, fraud detection, finance and e-commerce. Samuel is Indonesia’s top-ranked Stack Overflow user in R (top 5% worldwide), a certified professional (certificates from Microsoft, MongoDB, Stanford University, John Hopkins University), and an experienced consultant that has worked with several public-trading companies from his time staying in China, Japan and Singapore.

Between 2017 and 2018, Samuel has trained and consulted with more than 20 companies around Indonesia and a regular guest speaker/trainer in a number of universities in Singapore and Indonesia. He is also among the first recipients of Microsoft Professional Program Certificate in Data Science in Southeast Asia, having demonstrated proficiency in R, Python, Microsoft Azure, SQL / T-SQL, PowerBI and a list of other technologies.

3-Day Workshop Modules

Syllabus: LLM for Web Scraping & Prompts

Module 1: Leveraging LLM for Web Scraping and Information Extraction

  • Using LLM for web scraping
  • Introduction to the steps involved in connecting website URLs with LLM
  • Introduction to LlamaIndex and its usage in web scraping
  • Demonstration of using LangChain and OpenAI to build a Question-Answering System with website data

Module 2: Optimizing LLM for Performance Enhancement

  • Demonstration of using LlamaIndex
  • Designing effective prompts for LLM
  • Using LangChain’s Caching to enhance LLM performance
  • Demonstration of prompt design and caching to maximize LLM usage

Module 3: Ethical Considerations and Future Implications of Generative AI with LLM

  • A language for LLM prompt design: Guidance
  • Understanding the ethical considerations of Generative AI
  • Impact on privacy, bias, and misinformation
  • Responsible user of Large Language Models in society
  • Discussion on the future of Generative AI and its potential impact

Program Receivables:

  • Cutting Edge Curriculum

    A hands-on coding bootcamp with the opportunity to work on real datasets donated by businesses and the public sector. Coursebooks (PDF/HTML files), data set for practice, reference notes, and working files (R Notebook or Jupyter Notebook) are accessible through our Learning Management System account.

  • Project-Oriented Learning

    Work with real-life cases and learn under the assistance of our qualified instructors throughout the 1-month course.

  • Certification of Completion

    Show current and prospective employers that you’ve completed the course with a signed certificate of completion.

  • Quality Learning Environment

    We pay meticulous attention to the logistical details of our workshops: quality audio and visual setups, comfortable sitting arrangements, small group size. Dinners are included for evening workshops.

  • Engaging Community

    Be a part of our data-passionate community with 5000+ members and 300+ alumni.

A STRUCTURED APPROACH TO LEARNING DATA SCIENCE

The Large Language Model Specialization is a 4-week intensive program meticulously crafted to fast-track students’ expertise in harnessing large-scale linguistic models and their real-world applications.

No prior knowledge of Python, NLP, or deep learning principles is required. The course follows a well-structured learning trajectory, emphasizing hands-on exercises. Group mentoring sessions, led by our seasoned instructors and teaching assistants, provide insights and clarification throughout the learning process. For those keen on delving deeper into AI or understanding foundational theories, our Advanced Neural Network and Generative AI Specialization offers a comprehensive next step.

Throughout this specialization, participants will undertake a series of projects, each exploring the vast capabilities of Large Language Models in different scenarios. On completion, our dedicated career support team and industry mentors will assist graduates in navigating their path towards influential roles in AI and language model-centric sectors in leading organizations.

Learn LLM by building:

Students work through tons of real-life examples using sample datasets donated by our team of mentors and corporate partners. We believe in a learn-by-building approach, and we employ instructors who are uncompromisingly passionate about your growth and education.

Part of Large Language Models Specialization

This course is part of the Algoritma Large Language Models Specialization. Participants are rewarded with a certificate of completion upon passing criteria.