DeepLearning.AI · Issued Jul 2026 · 31 hours

RAG improves LLM responses by retrieving relevant data from external knowledge bases and using it to generate grounded, accurate answers. This course covered the design, evaluation, and refinement of production-ready RAG pipelines across five hands-on modules.

Core skills:

• Built a RAG system from scratch: retrieval functions, prompt augmentation, and structured input handling for LLMs
• Implemented and compared retrieval methods including semantic search, BM25, and Reciprocal Rank Fusion
• Scaled a RAG pipeline with Weaviate, chunking and indexing a real news dataset for vector-based retrieval
• Developed a domain-specific chatbot for FAQ handling and product recommendations using custom datasets
• Handled production challenges like dynamic pricing and interaction logging for monitoring and debugging
• Built a second chatbot variant using open-source LLMs hosted on Together AI

Applied to: media, healthcare, and e-commerce datasets, culminating in a fully functional RAG system.

This certification covers RAG systems, vector database integration, and LLM pipeline design — core skills for building production-grade retrieval architectures with tools like Weaviate and Together AI.