Challenge: Fixing hallucination via prompting - Python Tutorial

Contents

• Introduction Introduction

  • Building apps using large language models

    40s
• 1. LLM: The Essentials 1. LLM: The Essentials

  • Language models and tokenization

    4m 53s
  • Large language model capabilities

    1m 48s
  • Challenge: Introduction to Chainlit

    2m 28s
  • Solution: Introduction to Chainlit solution

    1m 18s
  • Prompts and prompt templates

    3m
  • Obtaining an OpenAI token

    1m 20s
  • Challenge: Adding an LLM to the Chainlit app

    1m 31s
  • Solution: Adding an LLM to the Chainlit app

    3m 20s
  • Large language model limitations

    3m 43s
• 2. Retrieval Augmented Generation 2. Retrieval Augmented Generation

  • Retrieval augmented generation

    3m 30s
  • Search engine basics

    2m 32s
  • Embedding search

    3m
  • Embedding model limitations

    3m 15s
  • Challenge: Enabling load PDF to Chainlit app

    48s
  • Solution: Enabling load PDF to Chainlit app

    5m 4s
  • Challenge: Indexing documents into a vector database

    1m 50s
  • Solution: Indexing documents into a vector database

    1m 43s
  • Challenge: Putting it all together

    1m 10s
  • Solution: Putting it all together

    3m 17s
  • Trying out your chat with the PDF app

    2m 15s
• 3. Prompt Engineering 3. Prompt Engineering

  • Prompt engineering basics

    5m 19s
  • Challenge: Set up prompting

    1m 35s
  • Solution: Set up prompting

    3m 53s
  • Prompt playground for LLM apps

    3m 15s
  • Challenge: Fixing hallucination via prompting

    1m 18s
  • Solution: Fixing hallucination via prompting

    7m 15s
• Conclusion Conclusion

  • Continue your LLM journey

    1m 23s