Oracle Cloud Infrastructure AI Code Academy

---

• Description
• Development
  • Requirements
  • Environment Variables
  • How to prepare the environment

Description

Oracle University offers several courses to become familiar with the Oracle Cloud Infrastructure (OCI) services. One of these learning paths relates to OCI Generative AI offering. OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.

Upon the completion of the OCI Generative AI Professional certification, the student will have learned:

• Fundamentals of Large Language Models (LLMs): LLM basics, LLM architectures, Prompt Engineering, Fine-tuning techniques, fundamentals of code models, Multi-modal LLMs and Language Agents
• OCI Generative AI Deep-Dive: Pretrained Foundational Models (Generation, Summarization, Embedding), Flexible Fine-tuning including T-Few techniques, Model Inference, Dedicated AI Clusters, Generative AI Security architecture
• Build a Conversational Chatbot with OCI Generative AI: Understand RAG, Vector Databases, Semantic Search, build chatbot using LangChain Framework (Prompts, Models, Memory, Chains), Trace and Evaluate chatbot and deploy on OCI

Development

Requirements

• Git
• Python >= 3.11
• Poetry >= 1.7.0

Environment Variables

Name	Description	Default
LOG_DIR	Location of the logging files	logs/
LOG_LEVEL	Logging level to be applied during execution	INFO

Populating .env file

Name	Description
OCI_COMPARTMENT_ID	Identifier of the compartment grouping Oracle Cloud Infrastructure (OCI) resources.
OCI_REGION	Region in which the Oracle Cloud Infrastructure services are accessed
OCI_CONFIG_PROFILE	Oracle Cloud Infrastructure CLI profile containing credentials to access the user account.
OCI_GENAI_ENDPOINT	Oracle Cloud Infrastructure endpoint to access Generative AI inference models.

Note: As prerequisite to setting the OCI CLI profile, the following steps are required:

1. Install the OCI Command Line Interface (CLI) on your machine
2. Set up the configuration file (see instructions)

How to prepare the environment

• Install dependencies

  poetry update