The outcome
Answer from an approved corpus with measurable retrieval quality instead of relying on unsupported model memory.
Step by step
A workflow you can repeat.
- 01
Define the questions, corpus owners, access rules, freshness, languages, citation format, and a benchmark with relevant and unanswerable cases.
- 02
Clean and chunk approved documents, preserve source IDs and permissions, then embed documents with the correct input type and pinned model.
- 03
Embed each query with the search-query input type, retrieve a broad candidate set, and rerank candidates using stable document identifiers.
- 04
Send only top verified passages to Chat with an instruction to cite sources and abstain when evidence is missing or contradictory.
- 05
Measure retrieval recall, reranking quality, answer support, latency, and billed units; version the index and rerun tests on model changes.
Working standard
What good use looks like.
- Use the correct embedding input types.
- Evaluate retrieval before generation.
- Preserve source IDs through reranking.
Official references