Building Agentic AI Applications with Large Language Models

Building Agentic AI Applications with Large Language ModelsBAALLMNVNvidiaNV-BAALLM1.0By participating in this course, you will: <ul> <li>Understand the strengths and limitations of LLMs, and why agent-based paradigms help us to empower them in our modern software landscape.</li><li>Learn to produce structured outputs to enable machine-parseable function calls or API integrations.</li><li>Explore retrieval mechanisms and knowledge graphs for domain knowledge.</li><li>Experiment with multi-agent orchestration using frameworks like LangGraph.</li><li>Implement resilient systems and data flywheels for production-oriented deployments.</li></ul><ul> <li>Introductory deep learning knowledge (including attention mechanisms and transformers). Experience from DLI’s Getting Started with Deep Learning or Fundamentals of Deep Learning is preferred.</li><li>Intermediate Python proficiency (including object-oriented programming and familiarity with ML libraries). Tutorials like Python Tutorial (w3schools.com) or equivalent practical experience suffice.</li></ul>We start with basic LLM usage and agent fundamentals, covering structured outputs, retrieval, and knowledge graphs. We then move to multi-agent concurrency, data flywheels, real-time constraints, and scaling considerations—finishing with a final assessment that has you interfacing with a scalable multi-tenant agent API.1. Fundamentals of Agent Abstraction and LLMs <ul> <li>Discuss LLM capabilities & pitfalls</li><li>Introduce agents as a task decomposition abstraction.</li><li>Demonstrate minimal agent with free-text LLM calls.</li></ul> 2. Structured Output & Basic Fulfillment Mechanisms <ul> <li>Bottlenecking LLMs with JSON/task-based outputs.</li><li>Ensure domain alignment & stable schema enforcement.</li><li>Introduction to cognitive architectures.</li></ul> 3. Retrieval Mechanisms & Environmental Tooling <ul> <li>Formalize environment access strategies for agents to interface with other systems.</li><li>Develop tool interfaces for external data repositories (DBs, APIs)</li><li>Use vector-RAG-coded for semantic retrieval over document sets.</li></ul> 4. Knowledge Graphs & Document Graphs <ul> <li>Plan progression of data from raw docs to canonical forms.</li><li>Motivate threshold/equilibrium objectives for driving event loop.</li><li>Build state pools/ontologies for robust domain coverage</li></ul> 5. Multi-Agent Systems & Frameworks <ul> <li>Decompose tasks among specialized agents</li><li>Formalize communication buffers and process distribution schemes.</li><li>Differentiate between different frameworks and their unique approaches.</li></ul> 6. Data Flywheels & System Hardening <ul> <li>Capture usage logs, refining domain constraints, or sub-models</li><li>Implement human-in-the-loop oversight for error correction</li><li>Iterative improvement & pipeline simplification using real/synthetic data.</li></ul> 7. Scaling & Productionalization <ul> <li>Discuss production-oriented considerations like resource management, concurrency, resource utilization, multi-tenancy</li><li>Motivate framework-agnostic modular deployments (meta-frameworks) and their selection criteria.</li></ul> 8. Final Assessment <ul> <li>Deploy an agent endpoint that can support multiple different interactions.</li><li>Run a distributed dialog loop across the deployed server to assess satisfaction.</li></ul> 9.1. [Optional] Real-Time Agents <ul> <li>Discuss multimodal considerations and agentic use-cases that interact with the physical world.</li><li>Explore recent advances in robotics, audio systems, and world models.</li></ul> 9.2. [Optional] Responsible Agents <ul> <li>Discuss common failure modes in software design that introduce unfairness, liability, and poor software experiences.</li><li>Consider checks-and-balances systems, standards creation, and evaluation needs.</li></ul>By participating in this course, you will: - Understand the strengths and limitations of LLMs, and why agent-based paradigms help us to empower them in our modern software landscape. - Learn to produce structured outputs to enable machine-parseable function calls or API integrations. - Explore retrieval mechanisms and knowledge graphs for domain knowledge. - Experiment with multi-agent orchestration using frameworks like LangGraph. - Implement resilient systems and data flywheels for production-oriented deployments.- Introductory deep learning knowledge (including attention mechanisms and transformers). Experience from DLI’s Getting Started with Deep Learning or Fundamentals of Deep Learning is preferred. - Intermediate Python proficiency (including object-oriented programming and familiarity with ML libraries). Tutorials like Python Tutorial (w3schools.com) or equivalent practical experience suffice.We start with basic LLM usage and agent fundamentals, covering structured outputs, retrieval, and knowledge graphs. We then move to multi-agent concurrency, data flywheels, real-time constraints, and scaling considerations—finishing with a final assessment that has you interfacing with a scalable multi-tenant agent API.1. Fundamentals of Agent Abstraction and LLMs - Discuss LLM capabilities & pitfalls - Introduce agents as a task decomposition abstraction. - Demonstrate minimal agent with free-text LLM calls. 2. Structured Output & Basic Fulfillment Mechanisms - Bottlenecking LLMs with JSON/task-based outputs. - Ensure domain alignment & stable schema enforcement. - Introduction to cognitive architectures. 3. Retrieval Mechanisms & Environmental Tooling - Formalize environment access strategies for agents to interface with other systems. - Develop tool interfaces for external data repositories (DBs, APIs) - Use vector-RAG-coded for semantic retrieval over document sets. 4. Knowledge Graphs & Document Graphs - Plan progression of data from raw docs to canonical forms. - Motivate threshold/equilibrium objectives for driving event loop. - Build state pools/ontologies for robust domain coverage 5. Multi-Agent Systems & Frameworks - Decompose tasks among specialized agents - Formalize communication buffers and process distribution schemes. - Differentiate between different frameworks and their unique approaches. 6. Data Flywheels & System Hardening - Capture usage logs, refining domain constraints, or sub-models - Implement human-in-the-loop oversight for error correction - Iterative improvement & pipeline simplification using real/synthetic data. 7. Scaling & Productionalization - Discuss production-oriented considerations like resource management, concurrency, resource utilization, multi-tenancy - Motivate framework-agnostic modular deployments (meta-frameworks) and their selection criteria. 8. Final Assessment - Deploy an agent endpoint that can support multiple different interactions. - Run a distributed dialog loop across the deployed server to assess satisfaction. 9.1. [Optional] Real-Time Agents - Discuss multimodal considerations and agentic use-cases that interact with the physical world. - Explore recent advances in robotics, audio systems, and world models. 9.2. [Optional] Responsible Agents - Discuss common failure modes in software design that introduce unfairness, liability, and poor software experiences. - Consider checks-and-balances systems, standards creation, and evaluation needs.8 Stunden500.00500.00500.00500.00500.00500.00