Import an existing retriever

Exact-span imports

{"question_id":"Q1","hits":[{"source_id":"COPY_ORIGINAL_SOURCE_ID","start":0,"end":13,"text":"eight seconds","rank":1,"score":0.8}]}

Use original source IDs and exact offsets/text from your corpus; the illustration assumes the source starts with eight seconds. Include a row for every question, even empty hit lists. Ranks are one-based; scores can be omitted. All hit tails are validated before selection.

ragvi import-data ./docs --reviewed ./reviewed.json --results ./results.jsonl

Registered-unit proxies

ID-only hits use source_unit_id referring to a registered original or passage. They are explicitly labeled registered_unit_proxy: the actual external context was not supplied. Exact spans and proxy hits cannot mix in one run. Proxy scores cannot satisfy actual-context quality criteria.

Use your system as a comparison baseline

ragvi compare-data ./docs --reviewed ./reviewed.json --results ./results.jsonl --techniques bm25,parent-child

existing becomes the default baseline; --baseline chooses another named participant. Missing external timing, internal stages and generation-request context remain unavailable.

• Import contract and evidence validation