Highlights
- Understand the architecture and mechanisms of modern transformer-based language models
- Design and implement AI agents using industry-standard frameworks
- Apply advanced prompting techniques for improved model performance
- Implement Retrieval-Augmented Generation (RAG) systems with vector databases
- Optimise LLM deployments for enterprise environments
- Navigate the ethical and regulatory landscape of AI implementation
Workshop Format:
Each module follows a consistent pattern:
- Core concept introduction and theory
- Hands-on lab work
- Review, troubleshooting, and best practices discussion
Course Details
Module 1: Foundations of Modern LLMs
Theory Component:
- Quick overview of Transformer Neural Network architecture
- Key concepts in self-attention mechanisms
Practical Labs:
- Implementing a basic attention mechanism from scratch
- Visualizing attention patterns in practice
- Analyzing the impact of different attention heads
- Building a mini-transformer for practical understanding
Module 2: AI Agents and Framework Implementation
Theory Component:
- Introduction to AI agents and their components
- Overview of LangChain framework architecture
Practical Labs:
- Setting up a development environment for AI agents
- Building a basic agent with LangChain
- Implementing custom tools and capabilities
- Testing and debugging agent behaviors
Module 3: Advanced Agent Development
Theory Component:
- Patterns for complex agent behaviors
- Best practices for prompt engineering
Practical Labs:
- Building an agent for data analysis
- Implementing Chain-of-Thought reasoning
- Creating custom tools for domain-specific tasks
- Validation and testing
Module 4: Retrieval-Augmented Generation (RAG)
Theory Component:
- Vector database concepts and selection criteria
- Embedding strategies overview
Practical Labs:
- Setting up a vector database
- Building a document processing pipeline
- Implementing efficient retrieval mechanisms
- Optimizing search quality and performance
Module 5: Model Fine-tuning and Adaptation
Theory Component:
- Understanding fine-tuning approaches
- Overview of evaluation metrics
Practical Labs:
- Preparing datasets for fine-tuning
- Implementing LoRA fine-tuning
- Evaluating model performance
- Deploying fine-tuned models
Module 6: Advanced Optimisation Techniques
Theory Component:
- Introduction to quantisation and optimization approaches
- Overview of deployment considerations
Practical Labs:
- Implementing QLoRA optimization
- Testing different quantisation strategies
- Benchmarking performance improvements
- Optimizing for specific hardware configurations
Module 7: Ethical Implementation and Compliance
Theory Component:
- Key regulatory requirements in the US and UK
Ethical considerations in AI implementation
Who should attend
This course is designed for technical professionals in data analytics, particularly those working in forensic data analysis and large-scale data processing environments. It's ideal for team members who have strong foundations in Python programming and machine learning concepts, looking to incorporate LLM technologies into their existing data processing pipelines.
Prerequisites
- Strong proficiency in Python programming
- Experience with data processing frameworks (pandas, Hadoop, Spark)
- Understanding of basic machine learning concepts
- Familiarity with SQL and database concepts
- Experience in handling large-scale data transformations
Feedback
4.8 out of 5 average
"Our tailored course provided a well rounded introduction and also covered some intermediate level topics that we needed to know. " Brian Leek, Data Analyst, May 2022
“JBI did a great job of customizing their syllabus to suit our business needs and also bringing our team up to speed on the current best practices. ” Brian F, Team Lead, RBS, Data Analysis Course, 20 April 2022