LLMs with LangChain - Beginner friendly
LLMs with LangChain - Beginner friendly
Published 6/2024
Duration: 1h14m | .MP4 1280x720, 30 fps(r) | AAC, 44100 Hz, 2ch | 522 MB
Genre: eLearning | Language: English
Published 6/2024
Duration: 1h14m | .MP4 1280x720, 30 fps(r) | AAC, 44100 Hz, 2ch | 522 MB
Genre: eLearning | Language: English
Understand Prompts, Chains and Agents. Build your first LLM App.
What you'll learn
Build an LLM based App from scratch using Streamlit.
Learn how Agents work. Understand the 3 components of Agents and code an Agent in LangChain
Learn how Chains work. Understand and build Simple and Sequential Chains.
Learn what are Prompts and how to use its structure
Understand how LangChain works. What are the components that make this library so effective
Requirements
There is no pre-requisite. I assume no knowledge of Langchain or Large Language Models
Description
This beginner-friendly course will help you start using LangChain to develop LLM applications with NO prior experience! We will understand the concepts by coding up examples.
I see LangChain becoming what Pandas is to Data Science. It will be the core library that Data Scientists and Machine Learning professionals will use to build applications using Large Language Models.
The goal of this course is to provide an understanding of how to navigate LangChain. There is no expectation of understanding of Natural Language Processing or Large Language Models. We will leverage the power of LangChain to build our use cases.
Step-by-Step we will build up the key components of LangChain. Prompts, Chains, and then Agents. We will build our understanding with easy-to-follow code.
Topics covered are
1. Prompts - We will see what is a Prompt and how can we build Prompt templates to automate prompt inputs
2. Chains - This is the Chain part of LangChain. We will see how Prompts roll up to Chains and explore Simple and Sequential Chains
3. Agents - The most important and powerful feature of LangChain. We will see the 3 components that make up Agents- Tools, LLMs, and Agent type. We will explore Tools - Wikipedia, SerpAPI, LLMmath - to see how to best extract the power of Agents.
4. Build an LLM App. Use your knowledge to solve a real-world problem.
Who this course is for:
Beginner A.I. enthusiasts who want to understand how Large Language Models can be used by using Langchain
Serve LLM based app using Streamlit
More Info