Master Llms With Langchain
Published 11/2024
MP4 | Video: h264, 1920×1080 | Audio: AAC, 44.1 KHz
Modern Generative AI and NLP Solutions! Build real-world projects using advanced LLMs like ChatGPT, Llama and Phi
What you’ll learn
Understand the theory behind LLMs and key concepts from LangChain and Hugging Face
Integrate proprietary LLMs (like OpenAI’s ChatGPT) and open-source models such as Meta’s Llama and Microsoft’s Phi
Learn about LangChain components, including chains, templates, RAG modules, agents, and tools
Explore RAG step-by-step for storage and retrieval using vector stores, with access to documents and web pages
Implement agents and tools to add features like conducting internet searches and retrieving up-to-date information
Deploy solutions in a local environment, enabling the use of open-source models without internet connection
Build an application that automatically summarizes videos and responds to questions about them
Develop a complete custom chatbot with memory and create a user-friendly interface using Streamlit
Create an advanced RAG application to interact with documents and extract relevant information using a chat interface
Requirements
Programming logic
Basic Python programming
Description
Overview
Section 1: Introduction
Lecture 1 Course content
Lecture 2 Course materials
Lecture 3 What are LLMs?
Lecture 4 How LLMs work 1
Lecture 5 How LLMs work 2
Lecture 6 Embeddings and tokens
Lecture 8 Examples of applications
Lecture 9 Challenges, limitations and ethics
Lecture 10 LLM models
Section 2: LLM using Hugging Face
Lecture 11 Hugging Face account and token
Lecture 12 Types of models
Lecture 13 Installation and configuration
Lecture 14 Parameters to text generation
Lecture 15 Prompt templates
Lecture 16 Exploring prompt engineering
Lecture 17 Message format
Lecture 18 Optimizing with quantization
Section 3: LLM using LangChain
Lecture 19 LangChain – intuition
Lecture 20 Installing LangChain
Lecture 21 LangChain models
Lecture 22 Other open source models
Lecture 23 Chat models
Lecture 24 Prompt templates
Lecture 25 Chains and custom functions
Lecture 26 Streaming
Lecture 27 Other model services
Lecture 28 Running on local machine
Lecture 29 Ollama in local machine
Section 4: LangChain – RAG
Lecture 30 RAG – intuition
Lecture 31 Preparing the environment
Lecture 32 Tests with RAG
Lecture 33 Debugging
Lecture 34 Indexing – intuition
Lecture 35 Indexing – implementation
Lecture 36 Text retrieval and generation – intuition
Lecture 37 Text retrieval and generation – implementation
Section 5: LangChain – Agents and Tools
Lecture 38 Agents and Tools – intuition
Lecture 39 Wikipedia tool
Lecture 40 Custom tool
Lecture 41 ReAct
Lecture 42 Creating and running the agent
Lecture 43 Tests with ChatGPT
Lecture 44 Tests with Tavily
Lecture 45 Chat templates
Lecture 46 Langsmith
Section 6: Project 1: Video transcription
Lecture 47 Preparing the environment
Lecture 48 Video transcription
Lecture 49 Loading the model
Lecture 50 Prompt template
Lecture 51 Chain, response, and translation
Lecture 52 Complete pipeline
Lecture 53 Markdown for visualization
Section 7: Project 2: Chatbot with memory and interface
Lecture 54 Preparing the environment
Lecture 55 Prompt, chain, and response
Lecture 56 State session
Lecture 57 User input and conversation
Lecture 58 Google Colab code
Section 8: Project 3: Talk to your documents
Lecture 59 Preparing the environment
Lecture 60 Panel to select documents
Lecture 61 Indexing and retrieval
Lecture 62 Advanced chain for conversation
Lecture 64 Conversation
Lecture 65 Google Colab code
Section 9: Final remarks
Lecture 66 Final remarks
Lecture 67 BONUS
