This short course covers the foundations of conversational systems—classic NLU (intents, entities, slot filling, dialogue design) and modern LLM workflows (prompt engineering, function calling, RAG). Participants build a practical chatbot grounded in their own documents, evaluate quality and safety, and deploy a lightweight interface. An HPC module is included for large-scale embeddings and offline evaluation/load testing.
- Date: 21.11.2025 at 11:45
- Venue: PS, UDG
- Registration required: https://forms.gle/SRW6GYiRAbi8pFBe8
- Designed for: students, researchers, and professionals with basic Python and web/API skills.
Course content overview
Session 1 (90 min) – theoretical framework
- From classic NLU (intents/entities/slots) to LLM “agents”
- Dialogue design: state machines vs. tools/functions
- RAG essentials: indexing, chunking, hybrid search, source citations
- Evaluation & safety: relevance/groundedness, moderation, PII
- HPC view: when batch embeddings and batch evaluation matter
Session 2 (90 min)- hands-on lab
- Project setup and starter RAG pipeline
- Document import/index, prompt + function calling
- Quick evaluation and guardrails
- Deploy a web chat
Learning outcomes
- Contrast intent-based vs. LLM-based chatbots.
- Design dialogue and implement a grounded RAG pipeline with citations.
- Ship a lightweight production chatbot with evaluation and safety.
- Apply HPC techniques to scale embeddings and offline performance testing.