Retrievers And Query Engines

A RetrieverQueryEngine is left at similarity_top_k=2 for a corpus where relevant evidence is routinely spread across 5-8 chunks; answers are incomplete.

Tune similarity_top_k to the evidence-spread of the corpus and the LLM's context budget — raise k (and optionally add a reranker to trim) when answers need more chunks, while watching context overflow and cost. Treat k as a measured parameter, not a default.

A query engine returns a Response. The application renders response.response text to users as cited answers but never inspects response.source_nodes.

Use response.source_nodes (NodeWithScore) to attribute each answer to the retrieved nodes — render citations from node metadata (source, page) and verify the answer's claims are supported by those nodes. An answer with no/low-score source nodes should be flagged as ungrounded, not presented as cite…

The integrator wants higher precision, so they set similarity_top_k=3 and add an LLMRerank node postprocessor expecting it to improve recall.

Retrieve a wider candidate set (higher similarity_top_k) and let the reranker (LLMRerank / SentenceTransformerRerank / Cohere rerank) cut to a smaller top_n. Reranking cannot recover documents the retriever never fetched — set retrieval k > rerank top_n.