GenAI and LLM interview questions

Semantic chunking splits on headings, paragraphs, or embedding breakpoints so a chunk is a coherent idea.

You embed small child chunks for precise search, then return a larger parent section to the LLM.

Tiny chunks match precisely but lose surrounding meaning.

Keep a table with its header and nearby caption

Common methods are reciprocal rank fusion, weighted score mixes after normalization, or a learned reranker on the union.

Exact SKUs, error codes, names, and legal citations often fail in embedding space.

RRF combines ranked lists by summing 1 over k plus rank for each document across systems.

MMR reranks hits to balance relevance with diversity so near-duplicate chunks do not fill the prompt.

The context window is the hard cap on prompt plus completion tokens the model can see.

Streaming sends tokens as they are generated instead of waiting for the full completion.

RAG searches your documents first, then feeds relevant chunks into the LLM prompt.

Embeddings are numeric vectors that place similar meanings near each other.

Balance context completeness versus retrieval precision.

Models accept a maximum context window measured in tokens, not words.

Measuring angle between vectors — common for nearest neighbor search.

Models and vector search work better on focused passages.

Ground the model on retrieved text, cite sources, and refuse when context is weak.

Untrusted content tries to override system instructions.

Citations, confidence language, and easy correction.