Evals · JSON-LD Context
Evals Context
JSON-LD context defining the semantic vocabulary for Evals from Evals.
12 Classes
52 Properties
5 Namespaces
Namespaces
evals:
https://api-evangelist.github.io/evals/schema/
schema:
https://schema.org/
dcterms:
http://purl.org/dc/terms/
prov:
http://www.w3.org/ns/prov#
xsd:
http://www.w3.org/2001/XMLSchema#
Classes
EvalRun
EvalSuite
EvalCase
EvalDataset
Scorer
Judge
Model
Experiment
name
description
version
license
Properties
| Property | Type | Container |
|---|---|---|
| id | string | |
| created | dateTime | |
| modified | dateTime | |
| timestamp | dateTime | |
| suite_id | reference | |
| case_id | reference | |
| experiment_id | reference | |
| dataset_id | reference | |
| model | reference | |
| provider | string | |
| temperature | decimal | |
| max_tokens | integer | |
| system_prompt | string | |
| prompt | string | |
| input | string | |
| output | string | |
| expected | string | |
| context | string | list |
| scorer | reference | |
| judge | reference | |
| judge_model | string | |
| judge_prompt | string | |
| judge_kind | string | |
| prompt_template | string | |
| rubric | string | |
| output_format | string | |
| calibration | reference | |
| human_agreement | decimal | |
| kappa | decimal | |
| type | string | |
| scale | reference | |
| threshold | decimal | |
| score | decimal | |
| label | string | |
| evidence | reference | |
| rationale | string | |
| retrieved_context | string | list |
| trace_id | string | |
| metrics | reference | |
| latency_ms | integer | |
| input_tokens | integer | |
| output_tokens | integer | |
| cost_usd | decimal | |
| task | string | |
| source | reference | |
| splits | reference | |
| case_count | integer | |
| tags | string | set |
| scorers | reference | set |
| policy | reference | |
| aggregation | string | |
| fail_on_threshold | boolean |
JSON-LD Document
{
"@context": {
"@version": 1.1,
"evals": "https://api-evangelist.github.io/evals/schema/",
"schema": "https://schema.org/",
"dcterms": "http://purl.org/dc/terms/",
"prov": "http://www.w3.org/ns/prov#",
"xsd": "http://www.w3.org/2001/XMLSchema#",
"EvalRun": "evals:EvalRun",
"EvalSuite": "evals:EvalSuite",
"EvalCase": "evals:EvalCase",
"EvalDataset": "evals:EvalDataset",
"Scorer": "evals:Scorer",
"Judge": "evals:Judge",
"Model": "evals:Model",
"Experiment": "evals:Experiment",
"id": {
"@id": "dcterms:identifier",
"@type": "xsd:string"
},
"name": "schema:name",
"description": "schema:description",
"version": "schema:version",
"created": {
"@id": "schema:dateCreated",
"@type": "xsd:dateTime"
},
"modified": {
"@id": "schema:dateModified",
"@type": "xsd:dateTime"
},
"timestamp": {
"@id": "prov:generatedAtTime",
"@type": "xsd:dateTime"
},
"suite_id": {
"@id": "evals:suite",
"@type": "@id"
},
"case_id": {
"@id": "evals:case",
"@type": "@id"
},
"experiment_id": {
"@id": "evals:experiment",
"@type": "@id"
},
"dataset_id": {
"@id": "evals:dataset",
"@type": "@id"
},
"model": {
"@id": "evals:model",
"@type": "@id"
},
"provider": {
"@id": "evals:provider",
"@type": "xsd:string"
},
"temperature": {
"@id": "evals:temperature",
"@type": "xsd:decimal"
},
"max_tokens": {
"@id": "evals:maxTokens",
"@type": "xsd:integer"
},
"system_prompt": {
"@id": "evals:systemPrompt",
"@type": "xsd:string"
},
"prompt": {
"@id": "evals:prompt",
"@type": "xsd:string"
},
"input": {
"@id": "evals:input",
"@type": "xsd:string"
},
"output": {
"@id": "evals:output",
"@type": "xsd:string"
},
"expected": {
"@id": "evals:expected",
"@type": "xsd:string"
},
"context": {
"@id": "evals:context",
"@container": "@list",
"@type": "xsd:string"
},
"scorer": {
"@id": "evals:scorer",
"@type": "@id"
},
"judge": {
"@id": "evals:judge",
"@type": "@id"
},
"judge_model": {
"@id": "evals:judgeModel",
"@type": "xsd:string"
},
"judge_prompt": {
"@id": "evals:judgePrompt",
"@type": "xsd:string"
},
"judge_kind": {
"@id": "evals:judgeKind",
"@type": "xsd:string"
},
"prompt_template": {
"@id": "evals:promptTemplate",
"@type": "xsd:string"
},
"rubric": {
"@id": "evals:rubric",
"@type": "xsd:string"
},
"output_format": {
"@id": "evals:outputFormat",
"@type": "xsd:string"
},
"calibration": {
"@id": "evals:calibration",
"@type": "@id"
},
"human_agreement": {
"@id": "evals:humanAgreement",
"@type": "xsd:decimal"
},
"kappa": {
"@id": "evals:kappa",
"@type": "xsd:decimal"
},
"type": {
"@id": "evals:scorerType",
"@type": "xsd:string"
},
"scale": {
"@id": "evals:scale",
"@type": "@id"
},
"threshold": {
"@id": "evals:threshold",
"@type": "xsd:decimal"
},
"score": {
"@id": "evals:score",
"@type": "xsd:decimal"
},
"label": {
"@id": "evals:label",
"@type": "xsd:string"
},
"evidence": {
"@id": "evals:evidence",
"@type": "@id"
},
"rationale": {
"@id": "evals:rationale",
"@type": "xsd:string"
},
"retrieved_context": {
"@id": "evals:retrievedContext",
"@container": "@list",
"@type": "xsd:string"
},
"trace_id": {
"@id": "evals:traceId",
"@type": "xsd:string"
},
"metrics": {
"@id": "evals:metrics",
"@type": "@id"
},
"latency_ms": {
"@id": "evals:latencyMs",
"@type": "xsd:integer"
},
"input_tokens": {
"@id": "evals:inputTokens",
"@type": "xsd:integer"
},
"output_tokens": {
"@id": "evals:outputTokens",
"@type": "xsd:integer"
},
"cost_usd": {
"@id": "evals:costUsd",
"@type": "xsd:decimal"
},
"task": {
"@id": "evals:task",
"@type": "xsd:string"
},
"source": {
"@id": "schema:url",
"@type": "@id"
},
"license": "schema:license",
"splits": {
"@id": "evals:splits",
"@type": "@id"
},
"case_count": {
"@id": "evals:caseCount",
"@type": "xsd:integer"
},
"tags": {
"@id": "schema:keywords",
"@container": "@set",
"@type": "xsd:string"
},
"scorers": {
"@id": "evals:scorers",
"@container": "@set",
"@type": "@id"
},
"policy": {
"@id": "evals:policy",
"@type": "@id"
},
"aggregation": {
"@id": "evals:aggregation",
"@type": "xsd:string"
},
"fail_on_threshold": {
"@id": "evals:failOnThreshold",
"@type": "xsd:boolean"
}
}
}