Files
GEWU_agent/contracts/schemas/IngestReviewCreate.schema.json
T

278 lines
5.8 KiB
JSON

{
"$defs": {
"FacetLabelProposal": {
"additionalProperties": false,
"properties": {
"definition": {
"maxLength": 500,
"minLength": 1,
"title": "Definition",
"type": "string"
},
"facet": {
"enum": [
"tags",
"audience",
"use_for",
"domain"
],
"title": "Facet",
"type": "string"
},
"schema_version": {
"const": 1,
"default": 1,
"title": "Schema Version",
"type": "integer"
},
"value": {
"maxLength": 100,
"minLength": 1,
"title": "Value",
"type": "string"
}
},
"required": [
"facet",
"value",
"definition"
],
"title": "FacetLabelProposal",
"type": "object"
},
"Locator": {
"additionalProperties": false,
"properties": {
"block_id": {
"maxLength": 128,
"minLength": 1,
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9._:-]*$",
"title": "Block Id",
"type": "string"
},
"end": {
"exclusiveMinimum": 0,
"title": "End",
"type": "integer"
},
"kind": {
"enum": [
"text_span",
"pdf_page_span",
"transcript_timestamp_span"
],
"title": "Kind",
"type": "string"
},
"page": {
"anyOf": [
{
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Page"
},
"schema_version": {
"const": 1,
"default": 1,
"title": "Schema Version",
"type": "integer"
},
"start": {
"minimum": 0,
"title": "Start",
"type": "integer"
},
"time_end_ms": {
"anyOf": [
{
"minimum": 0,
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Time End Ms"
},
"time_start_ms": {
"anyOf": [
{
"minimum": 0,
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Time Start Ms"
}
},
"required": [
"kind",
"block_id",
"start",
"end"
],
"title": "Locator",
"type": "object"
}
},
"additionalProperties": false,
"properties": {
"candidate_audience": {
"default": [],
"items": {
"maxLength": 100,
"minLength": 1,
"type": "string"
},
"maxItems": 3,
"title": "Candidate Audience",
"type": "array"
},
"candidate_domain": {
"default": [],
"items": {
"maxLength": 100,
"minLength": 1,
"type": "string"
},
"maxItems": 3,
"title": "Candidate Domain",
"type": "array"
},
"candidate_facet_labels": {
"default": [],
"items": {
"$ref": "#/$defs/FacetLabelProposal"
},
"maxItems": 14,
"title": "Candidate Facet Labels",
"type": "array"
},
"candidate_tags": {
"default": [],
"items": {
"maxLength": 100,
"minLength": 1,
"type": "string"
},
"maxItems": 5,
"title": "Candidate Tags",
"type": "array"
},
"candidate_use_for": {
"default": [],
"items": {
"maxLength": 100,
"minLength": 1,
"type": "string"
},
"maxItems": 3,
"title": "Candidate Use For",
"type": "array"
},
"excerpt": {
"maxLength": 4000,
"minLength": 1,
"title": "Excerpt",
"type": "string"
},
"extraction_id": {
"pattern": "^[a-f0-9]{64}$",
"title": "Extraction Id",
"type": "string"
},
"lens": {
"enum": [
"technical",
"conceptual",
"cultural-historical",
"financial-market"
],
"title": "Lens",
"type": "string"
},
"locator": {
"$ref": "#/$defs/Locator"
},
"project_id": {
"maxLength": 128,
"minLength": 1,
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9._:-]*$",
"title": "Project Id",
"type": "string"
},
"relevance": {
"default": "borderline",
"enum": [
"borderline",
"low"
],
"title": "Relevance",
"type": "string"
},
"relevance_rationale": {
"maxLength": 2000,
"minLength": 1,
"title": "Relevance Rationale",
"type": "string"
},
"review_id": {
"maxLength": 128,
"minLength": 1,
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9._:-]*$",
"title": "Review Id",
"type": "string"
},
"run_id": {
"maxLength": 128,
"minLength": 1,
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9._:-]*$",
"title": "Run Id",
"type": "string"
},
"schema_version": {
"const": 1,
"default": 1,
"title": "Schema Version",
"type": "integer"
},
"source_revision_id": {
"maxLength": 128,
"minLength": 1,
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9._:-]*$",
"title": "Source Revision Id",
"type": "string"
},
"summary": {
"maxLength": 2000,
"minLength": 1,
"title": "Summary",
"type": "string"
}
},
"required": [
"review_id",
"project_id",
"run_id",
"source_revision_id",
"extraction_id",
"locator",
"excerpt",
"lens",
"summary",
"relevance_rationale"
],
"title": "IngestReviewCreate",
"type": "object"
}