MongoDB, Voyage AI Teach Developers to Build AI Apps Without Separate Embedding Pipelines

Key takeaway

• MongoDB University and Voyage AI have released free AI Skill Badges that teach developers how to build production-grade applications using vector embeddings and retrieval-augmented generation without needing separate embedding pipelines.

• The program clarifies that RAG and fine-tuning are complementary tools solving different problems: RAG handles what information the model accesses at runtime, while fine-tuning changes how the model behaves by default, and production systems often need both.

3 Key Points

Context & Analysis

FAQ

What is the difference between RAG and fine-tuning?

RAG operates at inference time, retrieving relevant knowledge from external sources and passing it to the model without changing its weights—answering "what should the model know." Fine-tuning happens offline before deployment, updating model weights to change behavior, tone, vocabulary, and reasoning patterns—answering "how should the model behave."

When should I use RAG versus fine-tuning?

Use RAG if you need the model to reference specific documents, product catalogs, or information that updates frequently. Use fine-tuning if you need the model to adopt internal vocabulary, match a specific writing style, or follow domain-specific reasoning patterns. Production systems often need both.

How much does the MongoDB University AI Skill Badges program cost?

The learning is free to start on MongoDB University.