AI & Data
Databricks ML Associate: Batch vs Real-Time Model Inference
Batch and real-time inference solve different operational problems. Batch scoring processes many records on a schedule or as a dataset…
ExamTopics reading room
All articles
Explore more technical insights and certification explainers. Page 78 of 214.
From the editorial desk
Browse the archive
Technical explainers and certification perspectives from our editorial library.
AI & Data
Databricks GenAI Engineer Associate: Vector Search for Enterprise AI
Enterprise AI applications often need to find information by meaning rather than exact keywords. Vector retrieval represents text, images, or…
AI & Data
Databricks GenAI Engineer Associate: Serving & Monitoring GenAI Models
Putting a generative AI model behind an endpoint is only the start of production operations. A reliable serving design must…
AI & Data
Databricks GenAI Engineer Associate: MLflow GenAI Evaluation
Generative AI evaluation is difficult because many important qualities are not captured by one accuracy number. A response can be…
AI & Data
Databricks GenAI Engineer Associate: Unity Catalog for GenAI
Generative AI governance must cover more than model access. Production applications depend on prompts, evaluation datasets, vector indexes, tools, functions,…
AI & Data
Databricks GenAI Engineer Associate: Building RAG Systems
Retrieval-augmented generation, or RAG, improves a generative AI application by retrieving relevant enterprise information and placing that information into the…
AI & Data
Databricks Data Engineer Associate: Unity Catalog Governance
Unity Catalog is the governance layer that connects identity, permissions, lineage, auditing, discovery, and policy across data and AI assets…
AI & Data
Databricks Data Engineer Associate: Troubleshooting Slow Spark Jobs
A slow Spark job is rarely fixed by immediately choosing a larger cluster. Performance problems usually come from a specific…
AI & Data
Databricks Data Engineer Associate: Schema Evolution & Data Quality
Schema change is normal in data engineering. Sources add fields, rename concepts, change optionality, widen numeric ranges, and occasionally send…