50 lines
1.9 KiB
JSON
50 lines
1.9 KiB
JSON
{
|
|
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
"$id": "https://kb.local/wire/v1/search_hit.schema.json",
|
|
"title": "SearchHit v1",
|
|
"description": "Stub schema — declares the schema_version label and the required top-level fields per design §2.2.",
|
|
"type": "object",
|
|
"required": [
|
|
"schema_version",
|
|
"rank",
|
|
"score",
|
|
"chunk_id",
|
|
"doc_id",
|
|
"doc_path",
|
|
"heading_path",
|
|
"snippet",
|
|
"citation",
|
|
"retrieval",
|
|
"index_version",
|
|
"chunker_version",
|
|
"indexed_at",
|
|
"stale"
|
|
],
|
|
"properties": {
|
|
"schema_version": { "const": "search_hit.v1" },
|
|
"rank": { "type": "integer", "minimum": 1 },
|
|
"score": { "type": "number" },
|
|
"score_kind": {
|
|
"type": "string",
|
|
"enum": ["rrf", "bm25", "cosine"],
|
|
"description": "p9-fb-38: kind of `score` value. `rrf` = RRF normalized [0,1] (hybrid mode); `bm25` = raw BM25 score (lexical-only); `cosine` = raw cosine similarity (vector-only). Older clients that omit this field can treat absence as `rrf` (the historical default)."
|
|
},
|
|
"chunk_id": { "type": "string" },
|
|
"doc_id": { "type": "string" },
|
|
"doc_path": { "type": "string" },
|
|
"heading_path": { "type": "array", "items": { "type": "string" } },
|
|
"section_label": { "type": ["string", "null"] },
|
|
"snippet": { "type": "string" },
|
|
"snippet_full_text": { "type": "boolean" },
|
|
"citation": { "type": "object" },
|
|
"retrieval": { "type": "object" },
|
|
"index_version": { "type": "string" },
|
|
"embedding_model": { "type": ["string", "null"] },
|
|
"chunker_version": { "type": "string" },
|
|
"indexed_at": { "type": "string", "format": "date-time" },
|
|
"stale": { "type": "boolean" },
|
|
"repo": { "type": ["string", "null"] },
|
|
"code_lang": { "type": ["string", "null"] }
|
|
}
|
|
}
|