BLAPENVNvidiaNV-BLAPE1.0<p>By the end of the workshop, you will: </p> <ul> <li>Understand how to apply iterative prompt engineering best practices to create LLM-based applications for various language-related tasks.</li><li>Be proficient in using LangChain to organize and compose LLM workflows.</li><li>Write application code to harness LLMs for generative tasks, document analysis, chatbot applications, and more.</li></ul><p>This course is primarily intended for intermediate level and above Python developers with a solid understanding of LLM fundamentals.</p><h4>Course Introduction</h4> <ul> <li>Orient to the main worshop topics, schedule and prerequisites.</li><li>Learn why prompt engineering is core to interacting with Large Languange Models (LLMs).</li><li>Discuss how prompt engineering can be used to develop many classes of LLM-based applications.</li><li>Learn about NVIDIA LLM NIM, used to deploy the Llama 3.1 LLM used in the workshop.</li></ul><h4>Introduction to Prompting</h4> <ul> <li>Get familiar with the workshop environment.</li><li>Create and view responses from your first prompts using the OpenAI API, and LangChain.</li><li>Learn how to stream LLM responses, and send LLMs prompts in batches, comparing differences in performance.</li><li>Begin practicing the process of iterative prompt development.</li><li>Create and use your first prompt templates.</li><li>Do a mini project where to perform a combination of analysis and generative tasks on a batch of inputs.</li></ul> <h4>LangChain Expression Language (LCEL), Runnables, and Chains</h4> <ul> <li>Learn about LangChain runnables, and the ability to compose them into chains using LangChain Expression Language (LCEL).</li><li>Write custom functions and convert them into runnables that can be included in LangChain chains.</li><li>Compose multiple LCEL chains into a single larger application chain.</li><li>Exploit opportunities for parallel work by composing parallel LCEL chains.</li><li>Do a mini project where to perform a combination of analysis and generative tasks on a batch of inputs using LCEL and parallel execution.</li></ul><h4>Prompting With Messages</h4><ul> <li>Learn about two of the core chat message types, human and AI messages, and how to use them explictly in application code.</li><li>Provide chat models with instructive examples by way of a technique called few-shot prompting.</li><li>Work explicitly with the system message, which will allow you to define an overarching persona and role for your chat models.</li><li>Use chain-of-thought prompting to augment your LLMs ability to perform tasks requiring complex reasoning.</li><li>Manage messages to retain conversation history and enable chatbot functionality.</li><li>Do a mini-project where you build a simple yet flexible chatbot application capable of assuming a variety of roles.</li></ul><h4>Structured Output</h4><ul> <li>Explore some basic methods for using LLMs to generate structured data in batch for downstream use.</li><li>Generate structured output through a combination of Pydantic classes and LangChain&#039;s `JsonOutputParser`.</li><li>Learn how to extract data and tag it as you specify out of long form text.</li><li>Do a mini-project where you use structured data generation techniques to perform data extraction and document tagging on an unstructured text document.</li></ul><h4>Tool Use and Agents</h4><ul> <li>Create LLM-external functionality called tools, and make your LLM aware of their availability for use.</li><li>Create an agent capable of reasoning about when tool use is appropriate, and integrating the result of tool use into its responses.</li><li>Do a mini-project where you create an LLM agent capable of utilizing external API calls to augment its responses with real-time data.</li></ul><h4>Final Review</h4><ul> <li>Review key learnings and answer questions.</li><li>Earn a certificate of competency for the workshop.</li><li>Complete the workshop survey.</li><li>Get recommendations for the next steps to take in your learning journey.</li></ul>By the end of the workshop, you will: - Understand how to apply iterative prompt engineering best practices to create LLM-based applications for various language-related tasks. - Be proficient in using LangChain to organize and compose LLM workflows. - Write application code to harness LLMs for generative tasks, document analysis, chatbot applications, and more.This course is primarily intended for intermediate level and above Python developers with a solid understanding of LLM fundamentals.Course Introduction - Orient to the main worshop topics, schedule and prerequisites. - Learn why prompt engineering is core to interacting with Large Languange Models (LLMs). - Discuss how prompt engineering can be used to develop many classes of LLM-based applications. - Learn about NVIDIA LLM NIM, used to deploy the Llama 3.1 LLM used in the workshop. Introduction to Prompting - Get familiar with the workshop environment. - Create and view responses from your first prompts using the OpenAI API, and LangChain. - Learn how to stream LLM responses, and send LLMs prompts in batches, comparing differences in performance. - Begin practicing the process of iterative prompt development. - Create and use your first prompt templates. - Do a mini project where to perform a combination of analysis and generative tasks on a batch of inputs. LangChain Expression Language (LCEL), Runnables, and Chains - Learn about LangChain runnables, and the ability to compose them into chains using LangChain Expression Language (LCEL). - Write custom functions and convert them into runnables that can be included in LangChain chains. - Compose multiple LCEL chains into a single larger application chain. - Exploit opportunities for parallel work by composing parallel LCEL chains. - Do a mini project where to perform a combination of analysis and generative tasks on a batch of inputs using LCEL and parallel execution. Prompting With Messages - Learn about two of the core chat message types, human and AI messages, and how to use them explictly in application code. - Provide chat models with instructive examples by way of a technique called few-shot prompting. - Work explicitly with the system message, which will allow you to define an overarching persona and role for your chat models. - Use chain-of-thought prompting to augment your LLMs ability to perform tasks requiring complex reasoning. - Manage messages to retain conversation history and enable chatbot functionality. - Do a mini-project where you build a simple yet flexible chatbot application capable of assuming a variety of roles. Structured Output - Explore some basic methods for using LLMs to generate structured data in batch for downstream use. - Generate structured output through a combination of Pydantic classes and LangChain's `JsonOutputParser`. - Learn how to extract data and tag it as you specify out of long form text. - Do a mini-project where you use structured data generation techniques to perform data extraction and document tagging on an unstructured text document. Tool Use and Agents - Create LLM-external functionality called tools, and make your LLM aware of their availability for use. - Create an agent capable of reasoning about when tool use is appropriate, and integrating the result of tool use into its responses. - Do a mini-project where you create an LLM agent capable of utilizing external API calls to augment its responses with real-time data. Final Review - Review key learnings and answer questions. - Earn a certificate of competency for the workshop. - Complete the workshop survey. - Get recommendations for the next steps to take in your learning journey.1 day500.00500.00500.00500.00500.00500.00