Why Study with PlanetCert?
The Latest Questions
Practice questions and exam topics aligned with the current exam objectives.
Detailed Explanations
Go beyond the answer. Master the material with comprehensive learning and professional explanations for every concept.
AI-Powered Insights
Personalized preparation guidance that adapts to your performance and identifies weak spots automatically.
Exam Information
Official specifications published by Oracle
Exam Format
90 min
50
68%
Professional
Registration
$245 USD
Pearson VUE or online proctoring
Validity
Non-Expiring
Follow Oracle Cloud Recertification policy; Exam credentials do not expire but certification may require updates for new versions
1Z0-1127-25 Exam Topics and Domains
1Z0-1127-25 is organized into 4 weighted domains. Expect to work with Content moderation APIs, OCI Generative AI Agents service, OCI Generative AI Chat models, OCI Generative AI Service, and more.
1
Fundamentals of Large Language Models (LLMs)
20%
Explain the fundamentals of LLMs
LLM Architecture FundamentalsToken Processing and Embeddings
- Understand the basic architecture of Large Language Models
- Explain how transformers process text data
- Describe tokenization and embedding concepts
Understand LLM architectures
Transformer Model ComponentsPre-trained Model Types
- Describe detailed transformer architecture components
- Compare different pre-trained model types
- Select appropriate models for specific use cases
Design and use prompts for LLMs
Prompt Engineering TechniquesModel Parameters for Prompt Control
- Design effective prompts for various LLM tasks
- Configure model parameters to control output quality
- Apply prompt engineering best practices
Understand LLM fine-tuning
Fine-tuning MethodologiesParameter-Efficient Fine-Tuning (PEFT)
- Explain different fine-tuning approaches for LLMs
- Calculate training parameters like totalTrainingSteps
- Understand parameter-efficient fine-tuning methods
Understand the fundamentals of code models, multi-modal, and language agents
Code Generation ModelsMulti-modal ModelsLanguage Agents
- Understand specialized LLM applications (code, vision, etc.)
- Explain multi-modal model capabilities and limitations
- Describe language agent architectures and patterns
2
Using OCI Generative AI Service
40%
Explain the fundamentals of OCI Generative AI service
OCI Generative AI Service OverviewOCI Generative AI Components
- Understand OCI Generative AI service architecture
- Explain service components and their relationships
- Configure IAM policies for AI services
Use pretrained foundational models for Chat and Embedding
Chat Model APIsEmbedding Model APIs
- Use OCI Generative AI client for text embedding requests
- Configure chat completion API calls
- Understand embedding generation and use cases
Create dedicated AI clusters for fine-tuning and inference
Dedicated AI Cluster ArchitectureCluster Use Cases
- Create and configure dedicated AI clusters
- Understand cluster architecture and resource allocation
- Optimize clusters for fine-tuning and inference
Fine-tune base models with custom dataset
Fine-tuning ProcessFine-tuning Best Practices
- Fine-tune base models with custom datasets
- Configure training parameters effectively
- Evaluate and version fine-tuned models
Create and use model endpoints for inference
Model Endpoint ConfigurationInference API Usage
- Create and configure model endpoints for inference
- Deploy fine-tuned models to production
- Optimize inference performance and costs
Explore OCI Generative AI security architecture
Security and ComplianceData Privacy and Governance
- Understand OCI Generative AI security architecture
- Implement security controls for AI workloads
- Ensure compliance with data privacy regulations
3
Implement RAG using OCI Generative AI service
20%
Explain OCI Generative AI integration with LangChain and Oracle Database 23ai
LangChain Framework IntegrationOracle Database 23ai Vector Search
- Understand LangChain integration with OCI Generative AI
- Use Oracle Database 23ai for vector storage and search
- Build integrated RAG architectures
Explain RAG and RAG workflow
RAG Architecture and PhasesRAG Workflow Steps
- Explain RAG architecture and workflow phases
- Understand benefits and use cases for RAG
- Design effective RAG pipelines
Discuss loading, splitting and chunking of documents for RAG
Document LoadingDocument Splitting and Chunking
- Load and preprocess documents for RAG
- Apply effective chunking strategies
- Optimize chunk size and overlap for retrieval
Create embeddings of chunks using OCI Generative AI service
Chunk Embedding GenerationEmbedding Quality and Optimization
- Create embeddings for document chunks using OCI
- Optimize embedding generation process
- Select appropriate embedding models
Store and index embedded chunks in Oracle Database 23ai
Vector Storage in Oracle 23aiVector Indexing Strategies
- Store embeddings in Oracle Database 23ai
- Create and configure vector indexes
- Optimize vector storage and retrieval
Describe similarity search and retrieve chunks from Oracle Database 23ai
Similarity Search AlgorithmsRetrieval Optimization
- Perform similarity searches in Oracle Database 23ai
- Retrieve relevant document chunks efficiently
- Optimize retrieval with filtering and reranking
Explain response generation using OCI Generative AI service
Context-Augmented GenerationRAG Response Quality
- Generate responses using retrieved context
- Optimize RAG prompt templates
- Evaluate and improve response quality
4
Using OCI Generative AI RAG Agents service
20%
Explain the fundamentals of OCI Generative AI Agents service
Agents Service ArchitectureAgent Capabilities and Use Cases
- Understand OCI Generative AI Agents service fundamentals
- Explain agent architecture and capabilities
- Identify appropriate use cases for agents
Discuss options for creating knowledge bases
Knowledge Base SourcesKnowledge Base Management
- Create knowledge bases from various data sources
- Manage knowledge base lifecycle
- Understand knowledge base dependencies
Create and deploy agents using knowledge bases
Agent ConfigurationContent Moderation ConfigurationAgent Deployment
- Create and configure RAG agents
- Deploy agents using knowledge bases
- Configure content moderation and safety controls
Invoke deployed RAG agent as a chatbot
Agent InvocationChatbot Integration
- Invoke deployed RAG agents via API
- Integrate agents as chatbots in applications
- Manage multi-turn conversations
How do I earn this certification?
Passing 1Z0-1127-25 earns the Oracle Cloud Infrastructure 2025 Certified Generative AI Professional certification. It sits in the Oracle Cloud Infrastructure - AI track.
Next Level Options
Advanced AI Certifications - Future advanced AI certifications (when available) Oracle may release advanced-level AI certifications in the future
Alternative Paths
- OCI AI Foundations - Oracle Cloud Infrastructure AI Foundations Foundation-level AI understanding before professional certification
- OCI Data Science - Oracle Cloud Infrastructure Data Science Professional Complementary data science skills for AI professionals
- OCI AI Vector Search - Oracle AI Vector Search Certification Specialized vector database skills for RAG applications
- 1Z0-997-25 - Oracle Cloud Infrastructure 2025 Architect ProfessionalBroader OCI architecture knowledge for AI infrastructure design
Practice with Precision
The PlanetCert Simulator mirrors the real exam environment with authentic questions and timed pressure.
How to study for this exam?
The most effective way to prepare for 1Z0-1127-25 is by using the PlanetCert Simulator to practice questions and review detailed explanations.
What's changed on this exam?
Current Status
- ACTIVE
- Last content update: 2025-01-01
- Announcement date: 2024-Q4
Updates
- OCI Generative AI Agents Service 2025 New exam domain (20% of exam) focused on RAG agents service • Release date: 2024-Q4
- Oracle Database 23ai 23ai Critical for RAG implementation domain (20% of exam) • Release date: 2024-05-02
- LangChain OCI Integration Latest Essential for RAG domain, used throughout exam scenarios • Release date: 2024
Who should take this exam?
This exam is typically taken by Software Developers and Machine Learning Engineers.
- Basic understanding of Machine Learning and Deep Learning concepts
- Familiarity with Python programming language
- Basic understanding of Oracle Cloud Infrastructure (OCI)
- Knowledge of Large Language Models (LLMs)
- Experience with AI/ML development