Skip to main content

Syllabus: LLMOps and Evaluation

1. Header Information

FieldValue
Technical Group?
Topic NameLLMOps and Evaluation
Topic Code?
Version1.0
Training AudienceFreshers

2. Course Objectives

[!NOTE] This topic introduces LLMOps and Evaluation knowledge; adapting trainees with skills, lessons, and practices specific to evaluating RAG systems, implementing observability tools like LangFuse and LangSmith, and designing deep architectural experiments.

Output Standards table

NameCodeDescription
Ragas Evaluation Metrics?Evaluate RAG quality using Faithfulness, Answer Relevancy, Context Precision, and Context Recall.
Observability Tools?Master open source and native observability tools (LangFuse & LangSmith) for tracing and debugging.
Experiment Comparison?Design experimental frameworks to rigorously compare Naive, Advanced, GraphRAG, and Hybrid systems.

Detailed Learning Outcomes (LOs)

  • ? LO1 - Able to comprehend and apply Ragas framework metrics for automated LLM evaluation.
  • ? LO2 - Able to calculate Faithfulness and Answer Relevancy for generation quality.
  • ? LO3 - Able to assess Context Precision and Context Recall for retrieval performance.
  • ? LO4 - Able to set up and integrate LangFuse for Open Source tracing and prompt management.
  • ? LO5 - Able to configure LangSmith for native LangChain execution tracing and playground debugging.
  • ? LO6 - Able to implement best practices for production LLMOps (Sampling, PII, Alerts).
  • ? LO7 - Able to design an experimental infrastructure for comparing different RAG architectures.
  • ? LO8 - Able to analyze trade-offs (quality, cost, latency) across Naive, Advanced, Graph, and Hybrid setups.

3. Topic Outline

  • Unit 01: Ragas Evaluation Metrics
  • Unit 02: Observability: LangFuse & LangSmith
  • Unit 03: Experiment Comparison: Naive, Graph, Hybrid

4. Time Allocation

Activity TypePercentageDescription
Concept/Lecture40%Concepts, theory (3 Sessions)
Assignment/Lab40%Assignment, Lab
Guides/Review10%Self review/Cross review
Exam10%Pre-Test, Final Topic Test

5. Training Materials & Environments

Textbooks

  • Advanced AI Module: LLMOps and Evaluation Guidelines

References

Technical Requirements

  • Python 3.10+
  • Ragas, LangChain, LangSmith, LangFuse
  • Neo4j, Qdrant/ChromaDB
  • IDE (VSCode / PyCharm)

6. Assessment Scheme

ComponentQuantityWeight (%)Note
Quiz520%In-class labs
Assignments230%In-class labs
Final Practice Test150%Comprehensive project

Pass Criteria

  • Total topic GPA >= 7.0/10
  • Completed 100% Online video, Quiz, Assignments, Labs, Final Test
  • Successful demo of the Final Project (RAG system with evaluation and tracing)

7. Training Delivery Principles

RoleResponsibility/Criteria
TraineesMust be familiar with basic RAG.
TrainerCertified AI Engineer or higher.
TrainingDaily offline training and labs.
Re-TestAllowed 1 time for Failed status.
MarkingDirect grading of Practice tests.
Waiver CriteriaEquivalent industry certificates.
OthersNeed personal laptop for labs.