Merci d'avoir envoyé votre demande ! Un membre de notre équipe vous contactera sous peu.
Merci d'avoir envoyé votre réservation ! Un membre de notre équipe vous contactera sous peu.
Plan du cours
Introduction to WrenAI OSS
- Overview of WrenAI architecture
- Key OSS components and ecosystem
- Installation and setup
Semantic Modeling in Wren AI
- Defining semantic layers
- Designing reusable metrics and dimensions
- Best practices for consistency and maintainability
Text to SQL in Practice
- Mapping natural language to queries
- Improving SQL generation accuracy
- Common challenges and troubleshooting
Prompt Tuning and Optimization
- Prompt engineering strategies
- Fine-tuning for enterprise datasets
- Balancing accuracy and performance
Implementing Guardrails
- Preventing unsafe or costly queries
- Validation and approval mechanisms
- Governance and compliance considerations
Integrating WrenAI into Data Workflows
- Embedding Wren AI in pipelines
- Connecting to BI and visualization tools
- Multi-user and enterprise deployments
Advanced Use Cases and Extensions
- Custom plugins and API integrations
- Extending WrenAI with ML models
- Scaling for large datasets
Summary and Next Steps
Pré requis
- Strong understanding of SQL and database systems
- Experience with data modeling and semantic layers
- Familiarity with machine learning or natural language processing concepts
Audience
- Data engineers
- Analytics engineers
- ML engineers
21 Heures
