Skip to main content

Labs

Core labs (1–8) are the main graded path. Labs 9+ are optional extensions that deepen specific 2026 topics (structured output, caching, GraphRAG, guardrails, etc.). Complete them in order where possible — many build on earlier labs.

1Beginner

ChatBot with FastAPI

Build a streaming chat API with FastAPI, Dockerize it, deploy to Render, add Google Auth for protected endpoints, embed a simple frontend on HuggingFace Spaces.

FastAPIDockerRenderGoogle Auth
~3 hoursStart Lab
2Intermediate

RAG ChatBot

Build a full RAG pipeline: upload PDFs, chunk, embed into Chroma, retrieve with hybrid search, re-rank, generate answer, evaluate with RAGAS.

ChromaFAISSLLMRAGAS
~4 hoursStart Lab
3Advanced

Gemma4 Finetuning

Finetune Gemma4 on a custom instruction dataset using QLoRA with Unsloth, push adapter to HuggingFace Hub, create a Spaces demo.

UnslothPEFTHuggingFaceColab
~5 hoursStart Lab
4Intermediate

Hybrid RAG ChatBot

Extend Lab 2 with PGVector, add metadata filtering, multi-query retrieval, and a Streamlit/Gradio UI.

PGVectorBM25Re-rankersStreamlit
~4 hoursStart Lab
5Intermediate

Signature Detection & Cropper

Use Grounding DINO Tiny to detect and crop signature regions from scanned documents, output cropped PNGs + bounding box JSON.

Grounding DINOOpenCVFastAPI
~3 hoursStart Lab
6Advanced

AI Agent + MCP

Build an autonomous research agent: given a question, it searches the web, reads URLs, stores findings in SQLite, and synthesizes a report via MCP server.

Pydantic AIMCPVS CodeTavily
~5 hoursStart Lab
7Intermediate

CI/CD Pipeline

Add a full GitHub Actions pipeline (lint → test → build Docker → push to GHCR → deploy to Cloud Run) with branch protection and NeMo Guardrails.

GitHub ActionsDockerCloud RunNemoClaw
~3 hoursStart Lab
8Advanced

Full MLOps on GCP

End-to-end: Cloud Function trigger → GCS ingest → BigQuery ML → Cloud Run serving → Cloud Logging monitoring → automated retraining.

BigQuery MLCloud FunctionsCloud RunMonitoring
~6 hoursStart Lab
9Advanced

LLM Red-Teaming

Build a repeatable red-team harness for a tool-using LLM app and turn exploits into CI regression tests.

LLM SecurityRed-TeamingGuardrails
~4 hoursStart Lab
10Intermediate

Instructor Extraction Loops

Build a schema-first extraction pipeline with retries, validation, and tests.

PydanticinstructorStructured Output
~3 hoursStart Lab
11Intermediate

Prompt Caching & Cost Benchmarks

Implement a safe prompt/response cache and quantify cost + latency wins.

CachingLLM OpsLatency
~2 hoursStart Lab
12Intermediate

Contextual Retrieval Upgrade

Make chunks self-contained with headings/metadata and measure RAGAS improvements.

RAGChunkingRAGAS
~4 hoursStart Lab
13Advanced

GraphRAG Mini

Build a tiny knowledge graph alongside embeddings and use it for multi-hop retrieval.

GraphRAGKnowledge GraphsRAG
~5 hoursStart Lab
14Advanced

LangGraph Agent Workflow

Implement a stateful agent graph with retries, guard conditions, and logs.

AgentsLangGraphWorkflows
~5 hoursStart Lab
15Intermediate

Polars + DuckDB Local Warehouse

Build a fast local analytics pipeline (ETL → Parquet → SQL features) for ML/RAG.

PolarsDuckDBParquet
~4 hoursStart Lab
16Advanced

Guardrails + Red-Team Regression

Add guardrails to an LLM app and prove they work with a red-team suite in CI.

GuardrailsSecurityCI
~5 hoursStart Lab