- Home
- All Courses
- AI and LLM Certifications
- LLM Engineering for Multi-Agent Systems
Curriculum
- 12 Sections
- 64 Lessons
- 10 Weeks
Expand all sectionsCollapse all sections
- 1. Understanding the LLM Ecosystem8
- 1.1Large Language Models and Foundation Models
- 1.2Prompts and Prompt Engineering
- 1.3Context Window and Token Limits
- 1.4Embeddings and Vector Databases
- 1.5Build Custom LLM Applications
- 1.6Canonical Architecture for End-to-End LLM Application
- 1.7Quiz-1: LLM-Understanding the LLM Ecosystem10 Minutes0 Questions
- 1.8LLM-Assignment-1: Build and Evaluate a Basic LLM-Enabled Semantic Search3 Days
- 2. Adoption Challenges and Risks9
- 2.1Misaligned Behavior of AI Systems
- 2.2Handling Complex Datasets
- 2.3Limitations Due to Context Length
- 2.4Managing Cost and Latency
- 2.5Addressing Prompt Brittleness
- 2.6Ensuring Security in AI Applications
- 2.7Achieving Reproducibility
- 2.8Evaluating AI Performance and Outcomes
- 2.9Quiz-2: LLM-Adoption Challenges and Risks in LLM Systems10 Minutes0 Questions
- 3. Evolution of Embeddings: From One-Hot to Semantic Representations8
- 3.1Review of Classical Techniques
- 3.2Capturing Local Context with n-grams
- 3.3Semantic Encoding Techniques
- 3.4Text Embeddings
- 3.5Text Similarity Measures
- 3.6Module Summary: Embedding Evolution – From One-Hot to Semantic Representations
- 3.7Quiz-3: LLM-Evolution of Embeddings in NLP10 Minutes0 Questions
- 3.8LLM-Assignment-2: Exploring Semantic Embeddings for NLP Applications3 Days
- 4. Attention Mechanism and Transformers9
- 4.1Encoder-Decoder Architecture
- 4.2Transformer Networks
- 4.3Attention Mechanism
- 4.4Self-Attention
- 4.5Multi-Head Attention
- 4.6Transformer Models
- 4.7Module Summary: Attention Mechanism and Transformer Models
- 4.8Quiz-4: LLM-Transformer Attention and Architectures10 Minutes0 Questions
- 4.9LLM-Assignment-4: Building and Visualizing Transformer Attention Mechanisms3 Days
- 5. Vector Databases8
- 5.1Rationale for Vector Databases
- 5.2Different Types of Search
- 5.3Indexing Techniques
- 5.4Retrieval Techniques
- 5.5Challenges Using Vector Databases in Production
- 5.6Module Summary: Efficient Vector Storage and Retrieval with Vector Databases
- 5.7Quiz-5: LLM-Vector Storage and Retrieval with Vector Databases10 Minutes0 Questions
- 5.8LLM-Assignment-5: Build a Hybrid Vector Search Engine with Optimized Retrieval3 Days
- 6. Understanding and Implementing Semantic Search7
- 6.1Introduction and Importance of Semantic Search
- 6.2Lexical vs. Semantic Search
- 6.3Semantic Search Using Embeddings
- 6.4Advanced Concepts and Techniques in Semantic Search
- 6.5Module Summary: Understanding and Implementing Semantic Search
- 6.6Quiz-6: LLM-Understanding and Implementing Semantic Search10 Minutes0 Questions
- 6.7LLM-Assignment-6: Implementing Semantic Search with Embeddings3 Days
- 7. Prompt Engineering7
- 7.1Prompt Design and Engineering
- 7.2Tailoring Prompts to Goals, Tasks, and Domains
- 7.3Understanding and Mitigating Prompt Engineering Risks
- 7.4Advanced Prompting Techniques
- 7.5Module Summary: Prompt Engineering
- 7.6Quiz-7: LLM-Prompt Engineering10 Minutes0 Questions
- 7.7LLM-Assignment-7: Prompt Engineering3 Days
- 8. LLM Fine-Tuning and Evaluation9
- 8.1Fine-Tuning Foundation LLMs
- 8.2Parameter-Efficient Fine-Tuning in Depth
- 8.3Advanced Fine-Tuning Topics
- 8.4LLM Evaluation: Why Evaluate LLMs?
- 8.5LLM Evaluation: Human Evaluation and Feedback Loops
- 8.6LLM Evaluation: Benchmarks and Leaderboards
- 8.7Module Summary: LLM Fine-Tuning & Evaluation
- 8.8Quiz-8: LLM-Fine-Tuning and Evaluation10 Minutes0 Questions
- 8.9LLM-Assignment-8: LLM Fine-Tune and Evaluate3 Days
- 9. LangChain for building LLM Applications11
- 9.1Introduction to LangChain
- 9.2Why Are Orchestration Frameworks Needed
- 9.3Interface with Any LLM Using Model I/O
- 9.4Connecting External Data with LLM Application with Retrieval
- 9.5Creating Complex LLM Workflows with Chains
- 9.6Retain Context and Refer to Past Interactions with the Memory Component
- 9.7Dynamic Decision-Making with LLMs Using Agents
- 9.8Monitoring and Logging Using Callbacks
- 9.9Module Summary: Building LLM Applications Using LangChain
- 9.10Quiz-9: LLM-Building LLM Applications Using LangChain10 Minutes0 Questions
- 9.11LLM-Assignment-9: Build an RAG LLM Application Using LangChain3 Days
- 10. Multi-Agent Applications7
- 10.1Introduction to Agents and Tools
- 10.2Agent Types in LangChain
- 10.3Designing and Implementing Specialized Agents
- 10.4Multi-Agent LLM Labs with LangChain
- 10.5Module Summary: LLM Multi-Agent Applications Using LangChain
- 10.6Quiz-10: LLM-Multi-Agent Applications Using LangChain10 Minutes0 Questions
- 10.7LLM-Assignment-10: Building Multi-Agent LLM Systems Using LangChain3 Days
- 11. Advanced RAG0
- 12. LLM Bootcamp Project: Build A Multi-Agent LLM Application0
Quiz-10: LLM-Multi-Agent Applications Using LangChain
Prev