/oci-generative-ai

OCI Generative AI Certification Notes

Prepare for OCI Generative AI Professional Certification

The porpuse of this repository is to promote the usage of Oracle Generative AI by providing important information and notes needed to acquire the Professional Certification

The content is structured in four parts

  1. LLM Fundamentals
  2. Generative AI Service
  3. Blocks for LLM Apps
  4. OCI Generative AI Service

Prerequisites

To successfully complete the certification, we should have:

  • Familiarity with machine learning and deep learning concepts
  • Familiarity with Python (Intermediate)
  • Familiarity with foundational OCI services (IAM, Compute, Storage)
  • Completed the OCI Generative AI Professional course including skill checks and practice exam

OCI Generative AI 2024 Professional Exam

  • Number of questions: 40
  • Duration: 90 minutes
  • Passing score: 65% (26 questions)
  • Format: Multiple Choice questions

Exam Topics

Topics Areas Domain Weights (% of the exam) Objectives and Concepts
Large Language Models Fundamentals 20%
  • Explain the fundamentals of LLMs
  • Understand LLM architectures
  • Design and use prompts for LLMs and tune hyperparameters
  • Understand LLM fine-tuning
  • Understand the fundamentals of code models, multi-modal, and language agents
Using OCI Generative AI Service 45%
  • Explain the fundamentals of OCI Generative AI service
  • Use pretrained foundational models for Generation, Summarization, and Embedding
  • Create dedicated AI clusters for fine-tuning and inference
  • Fine-tuning base model with custom dataset
  • Create and use model endpoints for inference
  • Explore OCI Generative AI security architecture
Building LLM Application with OCI Generative AI Service 35%
  • Understand Retrieval Augmented Generation (RAG) concepts
  • Explain vector database concepts
  • Explain semantic search concepts
  • Build LangChain models, prompts, memory, and chains
  • Build an LLM application with RAG and LangChain
  • Trace and evaluate an LLM application
  • Deploy an LLM application

Key Points to Remember

  • Read the question very carefully
  • Identify themes and keywords in the questions
  • Read all the options very carefully
  • We might find two choices sounding exactly the same
  • Identify and discard the "distractors"
  • Start with eliminating obvious options that don't apply
  • Don't get struck at one place, mark for review
  • Always answer, words case scenario, make a guess