Generative AI: RAG, LangChain, GraphRAG & Fine-Tuning is a hands-on course from Deesa Technologies for developers who want to build real Generative AI applications — not just call an API once and stop.
You’ll follow a clear path from your first LLM app through production-style patterns used in modern engineering teams: prompt design, guardrails, structured outputs, LangChain, conversation memory, RAG, GraphRAG, MCP tool integration, map-reduce summarization, and fine-tuning open-weight models with deployment to Hugging Face. Every module includes runnable projects with a consistent structure (main, services, config, prompts, guardrails) so you learn how professionals organize Gen AI codebases.
What you’ll build
Across 11 modules, you’ll create practical applications including:
- Executive Brief Generator and Professional Report Drafter — your first Gradio LLM apps
- Prompt Playground and Temperature & Latency Lab — control model behavior, cost, and speed
- Model Scorecard and Translation Quality Report — evaluate outputs with real evaluation patterns
- Output Formatter and Contract Clause Extractor — structured extraction from documents
- AI SQL Assistant — LangChain, LCEL, and safe natural-language-to-SQL
- Customer Support Thread Analyzer — stateless vs memory-based conversations
- On-Call Runbook Assistant — RAG over production runbooks
- GraphRAG Dependency Explorer — combine graphs + retrieval for relationship-aware answers
