parent child
AI, ML & GenAI interview questions tagged parent child, across every topic.
2 questions · 0 unlocked for you
Concepts behind "parent child"
The curriculum that explains the ideas these questions test.
Core
ChunkingChunking divides documents into the passages you embed and retrieve, and it ranks among the highest-leverage knobs in RAG. Make chunks too large and embeddings get diluted so retrieval turns imprecise; make them too small and chunks lose the context needed to answer. Past fixed-size splitting, structure-aware and semantic chunking hold coherent units together, while parent-child (small-to-big) retrieval matches on small chunks yet returns larger context. AI, ML, and GenAI interviews test it because weak chunking quietly caps retrieval quality.🤖 Retrieval & AgentsSign in
Core
Hierarchical Retrieval (RAPTOR and Small-to-Big)Hierarchical retrieval resolves the chunk-granularity dilemma: small chunks retrieve precisely but miss context, large chunks hold context but retrieve poorly. RAPTOR grows a tree by recursively clustering and summarizing chunks, so retrieval can land on a precise leaf or a higher-level summary. Small-to-big (parent-child) embeds small chunks for matching yet returns the larger parent for context. Applied-AI interviews cover it because it is the standard production fix once naive fixed-size chunking begins missing answers.🤖 Retrieval & AgentsSign in