image
The Ultimate Drawing Course Beginner to Advanced...
$179
$79
image
User Experience Design Essentials - Adobe XD UI UX...
$179
$79
Total:
$659

Description

Unlock the potential of large language models (LLM) with my comprehensive course: "Introduction to Large Language Models (LLMs) In Python." With a focus on LLM frameworks such as OpenAI, LangChain, and LLMA-Index, this course empowers you to build your own Document-Reading Virtual Assistant. Whether you're new to LLM implementation or seeking to advance your AI skills, this course offers an invaluable opportunity to explore the cutting-edge field of AI.
Course Highlights
:
- Cloud-Based Python Environment: Harness the power of Saturn Cloud, a cloud-based Python environment, to implement robust LLM implementations.
- Practical Text Analysis: Learn to implement essential Natural Language Processing (NLP) techniques, including entity recognition and keyword extraction, to deconstruct the text documents
- Leveraging LLM Frameworks: Discover standard techniques for LLM frameworks, including LangChain, OpenAI and LLAMA-Index, for abstract summarization and querying.
Why Enroll in This Course?
By enrolling in this course, you're embarking on a journey to become an expert in harnessing the potential of text data with Large Language Models (LLMs). Driven by the vision of our experienced instructor, who holds an MPhil from the University of Oxford and a data-intensive PhD from Cambridge University, you'll receive the guidance needed to navigate the complexities of LLM implementation.
Beyond the course content, you'll benefit from continuous support, ensuring you extract the maximum value from your investment. Join our community of learners, immerse yourself in LLM analysis, and advance your expertise in AI and data science.
Enroll Now to Unlock the Power of Text Data With LLMs!
Who this course is for:
Students with prior exposure to NLP analysis
Those interested in using LLM frameworks for learning more about your texts
Students and practitioners of Artificial Intelligence (AI)

What you'll learn

Learn to work with Jupyter notebooks in a brand new cloud ecosystem-Saturn Cloud

Read in multiple PDFs into Python

Implement common natural language processing (NLP) techniques including entity recognition and keyword extraction

Get acquainted with common Large Language Model (LLM) frameworks including LangChain

Implement LLM frameworks for abstract summarisation and answering questions

Requirements

  • You will need a copy of Adobe XD 2019 or above. A free trial can be downloaded from Adobe.
  • No previous design experience is needed.
  • No previous Adobe XD skills are needed.

Course Content

27 sections • 95 lectures
Expand All Sections
1-Introduction To The Course
9
1.1-Welcome To the Course
1.2-Data and Code
1.3-Python Installation
1.4-Start With Google Colaboratory Environment
1.5-Google Colabs and GPU
1.6-Installing Packages In Google Colab
1.7-Another Cloud To Work In: Saturn Cloud
1.8-Say Hello To The Saturn Interface
1.9-Brain Fail: Dealing With Memory Problems
2-Get Started With The LLMs and Their Infrastructure
3
2.1-What Is a Document Reading Virtual Assistant?
2.2-Get Access To the OpenAI API
2.3-Introduction to LangChain
3-Start Reading in and Exploring Data
8
3.1-Read in a Single PDF
3.2-Read In Multiple PDFs
3.3-A More Straightforward Way To Read in Multiple PDFs
3.4-Learn More About Your Documents: Why We Need A Preliminary NLP Analysis
3.5-Entity Matching
3.6-Keyword Extraction
3.7-What Is TF-IDF?
3.8-Text Similarity
4-Use LLMs To Learn From Your Text
5
4.1-Overview-The Summarisation Process
4.2-Abstract Summarizer
4.3-Answer Questions Based On Given Text-LangChain
4.4-Theoretical Undepinnings
4.5-Answer Questions With Llama-Index
5-Preliminary Prompt Engineering
2
5.1-What Is Prompt Engineering?
5.2-Prompt Engineering With Langchain
6-Introduction to The HuggingFace Hub
1
6.1-What Is Hugging Face?
7-Basic Python Primer
5
7.1-Introduction to Numpy
7.2-What Is Pandas?
7.3-Basic Data Cleaning With Pandas
7.4-Basic Principles of Data Visualisation
7.5-Distributed Computing