GenAI App Development: LLM APIs, RAG and Vector Search for Developers

Calling a language model from code is easy. Building an application that gives reliable, secure and affordable answers from your own data is harder. This two-day course gives developers the patterns for doing it well, in a provider-neutral way.

Participants build a small retrieval-augmented application step by step, covering prompts, embeddings, vector search, evaluation and security. Exercises use Python. The course complements the OWASP LLM Top 10 course, which goes deeper on security, and the MLOps course, which covers classical models.

HRD Corp Training Provider Malaysia HRD Corp SBL-Khas Claimable

Course at a Glance

Course at a glance
Duration2 days
DeliveryPhysical or online. Tell us your preference when you enquire.

Programme Agenda

01

Day 1, 9:00 AM - 9:15 AM

Welcome and Programme Overview

Introduction to the session, objectives, and housekeeping.

02

Day 1, 9:15 AM - 10:15 AM

How LLM Applications Are Put Together

Models, APIs, prompts, context windows, tokens and cost. The parts of a typical application, what the model is good and bad at and how to choose between hosted and self-hosted models.

03

Day 1, 10:15 AM - 10:30 AM

Break

04

Day 1, 10:30 AM - 12:30 PM

Working With an LLM API

Sending requests, system and user messages, parameters, structured output, errors, rate limits and streaming. Keeping keys and personal data safe.

05

Day 1, 12:30 PM - 1:30 PM

Lunch

06

Day 1, 1:30 PM - 3:15 PM

Prompt Design and Output Control

Writing instructions that hold up, few-shot examples, asking for a fixed format, validating outputs in code and handling refusals and drift.

07

Day 1, 3:15 PM - 3:30 PM

Break

08

Day 1, 3:30 PM - 4:45 PM

Embeddings and Vector Databases

What an embedding is, how similarity search works, chunking documents, metadata and choosing and querying a vector store.

09

Day 1, 4:45 PM - 5:00 PM

Day 1 Close

Recap and what to review before day two.

10

Day 2, 9:00 AM - 9:15 AM

Day 1 Review

Recap of day one and the questions it left open.

11

Day 2, 9:15 AM - 10:15 AM

Retrieval-Augmented Generation

Retrieving relevant passages, building the prompt from them, citing sources, handling missing answers and improving retrieval through chunking, filters and re-ranking.

12

Day 2, 10:15 AM - 10:30 AM

Break

13

Day 2, 10:30 AM - 12:30 PM

Evaluation and Quality

Building a small test set, measuring answer accuracy, grounding and cost, spotting regressions after changes and the limits of automated judges.

14

Day 2, 12:30 PM - 1:30 PM

Lunch

15

Day 2, 1:30 PM - 3:15 PM

Security, Privacy and Safety

Prompt injection, data leakage, access control on retrieved documents, logging without storing personal data and the PDPA. Links to the OWASP LLM Top 10.

16

Day 2, 3:15 PM - 3:30 PM

Break

17

Day 2, 3:30 PM - 4:45 PM

Deployment and Operations

Caching, latency, cost control, monitoring, versioning prompts and models, and a handover checklist. Participants present their working application.

18

Day 2, 4:45 PM - 5:00 PM

Wrap-Up and Q&A

Key takeaways, next steps, and close.

Key Outcomes

  • Describe the parts of an LLM application and where cost and risk arise
  • Call an LLM API with structured, validated output
  • Prepare documents and build embedding-based search
  • Build a retrieval-augmented answer flow with citations
  • Evaluate quality with a small test set
  • Apply basic security, privacy and operational controls

Training Mode   Physical / Online / Hybrid / e-learning

HRD Corp   SBL-Khas Claimable

Level   Intermediate, for developers with working knowledge of Python. Prior machine learning experience is not required.

Duration   2 Days (16 Hours)  |  9:00 AM to 5:00 PM daily

Venue   In-house at the client's premises, or delivered via the client's preferred platform (Microsoft Teams, Zoom, or equivalent)

Assessment   A working retrieval-augmented application built during the course, plus a short knowledge check

Certificate   Certificate of Completion issued to all participants upon full attendance

Enquiries   Contact us to register or discuss scheduling

Frequently Asked Questions

GenAI App Development: LLM APIs, RAG and Vector Search for Developers runs for 2 days (16 hours) | 9:00 AM to 5:00 PM daily. It is delivered as an in-house closed group session, so the schedule can be adjusted to fit your team's working hours.

Yes. Delivery options are physical, online, hybrid, e-learning. In-house sessions run at your premises anywhere in Malaysia, online sessions run live over video conference, and hybrid combines both for teams split across sites.

Certificate of Completion issued to all participants upon full attendance. Each certificate carries a certificate number that can be checked at orbixtech.my/certificate-verify.

Level: Intermediate, for developers with working knowledge of Python. Prior machine learning experience is not required. The session is built around worked examples and group exercises rather than theory, so participants apply the material to their own organisation during the session.

Yes. GenAI App Development: LLM APIs, RAG and Vector Search for Developers is also available through the Orbix <a href="lms-malaysia">LMS and e-learning platform</a>, where participants work through the material on their own schedule and device rather than attending one fixed session. A knowledge assessment and certificate on completion work the same way as the instructor-led session.

Minimum 2 participants for an in-house or live online session. With only 1 participant, we deliver it as a one-to-one online session instead.

Yes. Many clients pair GenAI App Development: LLM APIs, RAG and Vector Search for Developers with our one-day <a href="training-team-building-malaysia">team building and high-performing teams programme</a> on the same engagement, so the budget and the day cover both.

Yes. Participants can follow up by email with questions that come up while applying what they learned, and we will point you to the right template, checklist or framework reference even after the session is over.