Module 3: Advanced LLMs – APIs, RAG, and Custom Workflows
Type: Intermediate technical workshop
Location: LGRC A112 + Zoom
Date: October 28, 12:00 – 2:00 PM
Move beyond basic LLM usage by integrating models into customized research or workflow pipelines. This module will cover:
-
- Retrieval-Augmented Generation (RAG): using your own data to enhance LLM outputs
- Model selection: comparing Claude, GPT-4, Mistral, etc.
- Orchestration tools: LangChain, LlamaIndex, and other tools
- API best practices: for access and cost management
GenAI for Teaching:
- Automate parts of content creation or grading workflows
- Build internal knowledge retrieval tools for course materials
GenAI for Research:
- Develop RAG pipelines over lab documents, papers, or grant archives
- Perform domain-specific Q&A or data augmentation
SELF-PACED RESOURCES
These optional materials are provided for participants who would like additional enrichment. You can explore them at your own pace to deepen your understanding and get more out of the workshop experience.
1. What is a REST API?
2. What is LangChain?
3. What is Retrieval-Augmented Generation (RAG)?
4. Retrieval Augmented Generation (RAG) for LLMs