🌉
3-Week Building LLMs Bootcamp
  • Welcome to the Bootcamp
    • Course Structure
    • Course Syllabus and Timelines
    • Know your Educators
    • Action Items and Prerequisites
    • Kick Off Session at Tryst 2024
  • Basics of LLMs
    • What is Generative AI?
    • What is a Large Language Model?
    • Advantages and Applications of LLMs
    • Bonus Resource: Multimodal LLMs and Google Gemini
    • Group Session Recording
  • Word Vectors, Simplified
    • What is a Word Vector
    • Word Vector Relationships
    • Role of Context in LLMs
    • Transforming Vectors into LLM Responses
    • Bonus Section: Overview of the Transformers Architecture
      • Attention Mechanism
      • Multi-Head Attention and Transformers Architecture
      • Vision Transformers
    • Graded Quiz 1
    • Group Session Recording
  • Prompt Engineering and Token Limits
    • What is Prompt Engineering
    • Prompt Engineering and In-context Learning
    • For Starters: Best Practices to Follow
    • Navigating Token Limits
    • Hallucinations in LLMs
    • Prompt Engineering Excercise (Ungraded)
      • Story for the Excercise: The eSports Enigma
      • Your Task for the Module
    • Group Session Recording
  • RAG and LLM Architecture
    • What is Retrieval Augmented Generation (RAG)?
    • Primer to RAG: Pre-trained and Fine-Tuned LLMs
    • In-context Learning
    • High-level LLM Architecture Components for In-context Learning
    • Diving Deeper: LLM Architecture Components
    • Basic RAG Architecture with Key Components
    • RAG versus Fine-Tuning and Prompt Engineering
    • Versatility and Efficiency in RAG
    • Key Benefits of using RAG in an Enterprise/Production Setup
    • Hands-on Demo: Performing Similarity Search in Vectors (Bonus Module)
    • Using kNN and LSH to Enhance Similarity Search (Bonus Module)
    • Bonus Video: Implementing End-to-End RAG | 1-Hour Session
    • Group Session Recording
    • Graded Quiz 2
  • Hands-on Development
    • Prerequisites
    • 1 – Dropbox Retrieval App
      • Understanding Docker
      • Building the Dockerized App
      • Retrofitting your Dropbox app
    • 2 – Amazon Discounts App
      • How the Project Works
      • Building the App
    • 3 – RAG with Open Source and Running "Examples"
    • 4 (Bonus) – Realtime RAG with LlamaIndex/Langchain and Pathway
      • Understanding the Basics
      • Implementation with LlamaIndex and Langchain
    • Building LLM Apps with Open AI Alternatives using LiteLLM
  • Bonus Resource: Recorded Interactions from the Archives
  • Final Project + Giveaways
    • Prizes and Giveaways
    • Suggested Tracks for Ideation
    • Sample Projects and Additional Resources
    • Form for Submission
Powered by GitBook
On this page
  • 💡 A practical insight
  • How to Choose the Right Vector Embeddings Model

Was this helpful?

  1. Word Vectors, Simplified

Word Vector Relationships

PreviousWhat is a Word VectorNextRole of Context in LLMs

Last updated 1 year ago

Was this helpful?

Navigating the landscape of text representation, it's essential to grasp how words relate to each other in vector form. In the upcoming video, Anup Surendran dives into the history of word vectors and takes a closer look at Google's groundbreaking Word2Vec project. Why are vector relationships so critical, and what biases do they bring?

Let's find out!

In this segment, Anup delves into the development of word vectors, highlighting the significant advancement made by Google's Word2Vec project. A remarkable aspect of Word2Vec is its ability to perform vector arithmetic, enabling mathematical operations with words. A classic example illustrating this feature is the equation "King - Man + Woman = Queen," demonstrating the intuitive understanding of relationships between words.

The video further examines how word vector relationships contribute to similarity searches, a crucial function in large language models. Additionally, Anup addresses an essential topic: the biases present in these technological advancements. Recognizing and understanding these biases is vital, not only for a deeper comprehension of Large Language Models but also for their ethical application. 🌐

💡 A practical insight

The terms "vector embeddings" and "word vectors" are often used interchangeably when discussing LLMs. These embeddings are stored in vector indexes, which are sophisticated data structures designed for fast and accurate retrieval of information based on these embeddings.

The rise of LLMs has spurred the development of specialized 'databases' focused on managing vector indexes. Platforms like Pinecone, Weaviate, ChromaDB, Mills etc., are prime examples of such databases.

However, these databases are not mandatory in every production-grade application of LLMs. We'll delve into this later in the course. For the moment, being familiar with these terms and their relevance to LLMs is a great starting point.

How to Choose the Right Vector Embeddings Model

Selecting the appropriate model for generating embeddings is an intriguing topic on its own. It's essential to recognize that there isn't a one-size-fits-all solution in this domain. A glance at this reveals a variety of embedding models, each tailored for specific applications. Currently, OpenAI's text-embedding-ada-002 is a commonly used ago-to model for producing efficient vector embeddings from diverse data, whether structured or unstructured. But like we've moved from GPT-2 to GPT-3, and now GPT-4, these embedding models are also bound to evolve and become more efficient. We'll delve deeper into its utilization in our tutorials by the end of this course.

MTEB Leaderboard on Hugging Face