I’m excited to announce my new workshop: Introduction to RAG in Production - a comprehensive hands-on session designed for teams looking to implement robust RAG systems in real-world environments.

What You’ll Learn

Foundation & Architecture

• Introduction to GenAI and LLMs - Understanding the landscape and capabilities
• LLM Application Architectures - Design patterns for scalable systems
• Embeddings Overview - What are embeddings and how they power semantic search
• Vector Database Comparison - Choosing the right storage solution
• Data Exploration Fundamentals - Analyzing and understanding your data for RAG

Production RAG Pipeline

We’ll build a complete RAG system covering every critical step:

1. Document Preprocessing - Text extraction, chunking strategies, and optimization
2. Data Ingestion - Efficient embedding generation and storage
3. Querying & Search - Semantic retrieval and relevance scoring
4. Document Post-processing - Context ranking and filtering
5. Answer Generation - Prompt engineering and response optimization
6. Evaluation - Metrics, testing frameworks, and quality assurance
7. Production Challenges - Scaling, monitoring, and maintenance

Who Should Attend

This workshop is ideal for:

• Engineering teams implementing RAG systems
• Data scientists exploring production deployment
• Product managers overseeing AI initiatives
• CTOs evaluating RAG solutions

Format

Interactive 3-hour workshop combining theory with practical implementation.

Interested in bringing this workshop to your team? Contact me to discuss custom sessions tailored to your specific use cases and tech stack.

---

Available for both in-person and remote delivery.