Production-Ready RAG Systems, LLM Fine-Tuning, and MLOps for LLMs
Master the skills to build, fine-tune, and deploy production-ready LLM applications with RAG, efficient fine-tuning techniques, and robust MLOps practices.
...
Introduction to Production-Ready LLM Systems
Unit 1: Understanding Production LLM Systems
Unit 2: Challenges and Considerations
Unit 3: RAG, Fine-Tuning, and MLOps Overview
RAG System Deep Dive: Architecture and Components
Unit 1: RAG Architecture Fundamentals
Unit 2: Component Interactions and Information Flow
Unit 3: Advanced RAG Concepts
Vector Database Selection: ChromaDB
Unit 1: ChromaDB Fundamentals
Unit 2: Configuring ChromaDB
Unit 3: Vector Search Operations
Vector Database Selection: Pinecone
Unit 1: Pinecone Fundamentals
Unit 2: Setting Up and Configuring Pinecone
Unit 3: Working with Data in Pinecone
Vector Database Selection: Weaviate
Unit 1: Introduction to Weaviate
Unit 2: Setting Up Weaviate
Unit 3: Data Ingestion and Querying
Indexing Strategies: Data Preparation and Chunking
Unit 1: Data Cleaning and Preprocessing
Unit 2: Text Chunking Strategies
Unit 3: Chunk Size and Overlap Optimization
Indexing Strategies: Metadata Enrichment
Unit 1: Metadata Fundamentals
Unit 2: Metadata Extraction Techniques
Unit 3: Metadata Integration and Utilization
Query Optimization: Similarity Metrics
Unit 1: Fundamentals of Similarity Metrics
Unit 2: Advanced Similarity Metrics and Trade-offs
Unit 3: Selecting the Right Metric for Your RAG Application
Query Optimization: Hybrid Search
Unit 1: Understanding Hybrid Search
Unit 2: Implementing Hybrid Search Techniques
Unit 3: Optimization and Evaluation
RAG Evaluation Metrics
Unit 1: Understanding RAG Evaluation
Unit 2: Implementing Evaluation Pipelines
Unit 3: Analyzing and Improving RAG Systems
Introduction to LLM Fine-Tuning
Unit 1: Fundamentals of LLM Fine-Tuning
Unit 2: LoRA and QLoRA Overview
Unit 3: Use Cases and Practical Considerations
Data Preparation for Fine-Tuning
Unit 1: Dataset Curation and Cleaning
Unit 2: Data Formatting and Augmentation
Unit 3: Data Splitting and Advanced Techniques
Parameter-Efficient Fine-Tuning: LoRA
Unit 1: LoRA Fundamentals
Unit 2: LoRA Implementation with Transformers
Unit 3: Advanced LoRA Techniques
Parameter-Efficient Fine-Tuning: QLoRA
Unit 1: QLoRA Fundamentals
Unit 2: QLoRA Implementation with bitsandbytes
Unit 3: QLoRA Evaluation and Optimization
Hyperparameter Tuning for Fine-Tuning
Unit 1: Fundamentals of Hyperparameter Tuning
Unit 2: Hyperparameter Optimization Techniques
Unit 3: Experiment Tracking and Management with Weights & Biases
Evaluation Metrics for Generative Tasks
Unit 1: Fundamentals of Generative Evaluation
Unit 2: Advanced Evaluation Metrics
Unit 3: Building Evaluation Pipelines
Introduction to MLOps for LLMs
Unit 1: MLOps Fundamentals for LLMs
Unit 2: Key MLOps Components for LLMs
Unit 3: MLOps Workflows for LLMs
Version Control for Models and Datasets
Unit 1: Introduction to Version Control for LLMs
Unit 2: Versioning Models with DVC
Unit 3: Advanced DVC and Git Integration
Automated Training Pipelines
Unit 1: Fundamentals of Automated Training Pipelines
Unit 2: Building Pipelines with Kubeflow
Unit 3: Building Pipelines with Airflow
Monitoring Strategies for LLMs
Unit 1: Fundamentals of LLM Monitoring
Unit 2: LLM-Specific Monitoring
Unit 3: Alerting and Anomaly Detection
LLM Serving with vLLM
Unit 1: Introduction to vLLM
Unit 2: Setting up vLLM
Unit 3: Advanced vLLM Techniques
Unit 4: Monitoring and Optimization
LLM Serving with TensorRT-LLM
Unit 1: Introduction to TensorRT-LLM
Unit 2: Model Conversion and Deployment
Unit 3: Optimization Techniques
Optimization Techniques: Quantization
Unit 1: Quantization Fundamentals
Unit 2: Post-Training Quantization
Unit 3: Quantization-Aware Training
Optimization Techniques: Speculative Decoding
Unit 1: Speculative Decoding Fundamentals
Unit 2: Implementation Techniques
Unit 3: Evaluation and Optimization
Security Best Practices: Prompt Injection
Unit 1: Understanding Prompt Injection
Unit 2: Detection Techniques
Unit 3: Prevention and Mitigation
Unit 4: Advanced Strategies
Security Best Practices: Data Privacy
Unit 1: Understanding Data Privacy in LLMs
Unit 2: Anonymization and De-identification Techniques
Unit 3: Compliance with Data Privacy Regulations
Security Best Practices: Access Controls
Unit 1: Fundamentals of Access Control
Unit 2: Authentication Mechanisms
Unit 3: Authorization and Role-Based Access Control (RBAC)
