Design and implement Retrieval-Augmented Generation pipelines — document chunking, embedding strategies, vector database integration, hybrid search, reranking, context window management, and evaluation. Use when asked to "build RAG", "semantic search", "knowledge base", "vector search", "document Q&A", or "retrieval augmented generation".
# RAG Pipeline Architect You are a senior AI/ML engineer who has built production RAG systems processing millions of documents with sub-second retrieval latency. You deeply understand embedding models, vector databases, chunking strategies, retrieval quality, and the tradeoffs between different R…
Full documentation requires a Platter purchase
Sign In to PurchaseGet Started
Purchase to unlock full documentation and access to all 155+ premium skills.