@learning-commons/evaluators 0.5.0 → 0.6.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +8 -0
- package/README.md +12 -0
- package/dist/batch/cli.js +39 -17
- package/dist/batch/cli.js.map +1 -1
- package/dist/batch/index.cjs +21 -8
- package/dist/batch/index.cjs.map +1 -1
- package/dist/batch/index.d.cts +1 -0
- package/dist/batch/index.d.ts +1 -0
- package/dist/batch/index.js +21 -8
- package/dist/batch/index.js.map +1 -1
- package/dist/index.cjs +18 -6
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +2 -0
- package/dist/index.d.ts +2 -0
- package/dist/index.js +18 -6
- package/dist/index.js.map +1 -1
- package/package.json +6 -2
- package/src/batch/README.md +14 -1
package/dist/batch/index.d.cts
CHANGED
package/dist/batch/index.d.ts
CHANGED
package/dist/batch/index.js
CHANGED
|
@@ -1277,7 +1277,9 @@ var VocabularyEvaluator = class _VocabularyEvaluator extends BaseEvaluator {
|
|
|
1277
1277
|
reasoning: complexityResponse.data.reasoning,
|
|
1278
1278
|
metadata: {
|
|
1279
1279
|
model: modelLabel,
|
|
1280
|
-
processingTimeMs: latencyMs
|
|
1280
|
+
processingTimeMs: latencyMs,
|
|
1281
|
+
inputTokens: totalTokenUsage.input_tokens,
|
|
1282
|
+
outputTokens: totalTokenUsage.output_tokens
|
|
1281
1283
|
},
|
|
1282
1284
|
_internal: complexityResponse.data
|
|
1283
1285
|
};
|
|
@@ -1607,7 +1609,9 @@ var SentenceStructureEvaluator = class _SentenceStructureEvaluator extends BaseE
|
|
|
1607
1609
|
reasoning: complexityResponse.data.reasoning,
|
|
1608
1610
|
metadata: {
|
|
1609
1611
|
model: this.provider.label,
|
|
1610
|
-
processingTimeMs: latencyMs
|
|
1612
|
+
processingTimeMs: latencyMs,
|
|
1613
|
+
inputTokens: totalTokenUsage.input_tokens,
|
|
1614
|
+
outputTokens: totalTokenUsage.output_tokens
|
|
1611
1615
|
},
|
|
1612
1616
|
_internal: {
|
|
1613
1617
|
sentenceAnalysis: analysisResponse.data,
|
|
@@ -1813,7 +1817,9 @@ var GradeLevelAppropriatenessEvaluator = class extends BaseEvaluator {
|
|
|
1813
1817
|
reasoning: response.data.reasoning,
|
|
1814
1818
|
metadata: {
|
|
1815
1819
|
model: this.provider.label,
|
|
1816
|
-
processingTimeMs: latencyMs
|
|
1820
|
+
processingTimeMs: latencyMs,
|
|
1821
|
+
inputTokens: tokenUsage.input_tokens,
|
|
1822
|
+
outputTokens: tokenUsage.output_tokens
|
|
1817
1823
|
},
|
|
1818
1824
|
_internal: response.data
|
|
1819
1825
|
};
|
|
@@ -2015,7 +2021,9 @@ var SmkEvaluator = class _SmkEvaluator extends BaseEvaluator {
|
|
|
2015
2021
|
reasoning: response.data.reasoning,
|
|
2016
2022
|
metadata: {
|
|
2017
2023
|
model: this.provider.label,
|
|
2018
|
-
processingTimeMs: latencyMs
|
|
2024
|
+
processingTimeMs: latencyMs,
|
|
2025
|
+
inputTokens: totalTokenUsage.input_tokens,
|
|
2026
|
+
outputTokens: totalTokenUsage.output_tokens
|
|
2019
2027
|
},
|
|
2020
2028
|
_internal: response.data
|
|
2021
2029
|
};
|
|
@@ -2221,7 +2229,9 @@ var ConventionalityEvaluator = class _ConventionalityEvaluator extends BaseEvalu
|
|
|
2221
2229
|
reasoning: response.data.reasoning,
|
|
2222
2230
|
metadata: {
|
|
2223
2231
|
model: this.provider.label,
|
|
2224
|
-
processingTimeMs: latencyMs
|
|
2232
|
+
processingTimeMs: latencyMs,
|
|
2233
|
+
inputTokens: totalTokenUsage.input_tokens,
|
|
2234
|
+
outputTokens: totalTokenUsage.output_tokens
|
|
2225
2235
|
},
|
|
2226
2236
|
_internal: response.data
|
|
2227
2237
|
};
|
|
@@ -2496,7 +2506,9 @@ var PurposeEvaluator = class _PurposeEvaluator extends BaseEvaluator {
|
|
|
2496
2506
|
reasoning: response.data.reasoning,
|
|
2497
2507
|
metadata: {
|
|
2498
2508
|
model: this.provider.label,
|
|
2499
|
-
processingTimeMs: latencyMs
|
|
2509
|
+
processingTimeMs: latencyMs,
|
|
2510
|
+
inputTokens: tokenUsage.input_tokens,
|
|
2511
|
+
outputTokens: tokenUsage.output_tokens
|
|
2500
2512
|
},
|
|
2501
2513
|
_internal: response.data
|
|
2502
2514
|
};
|
|
@@ -2609,6 +2621,7 @@ var BatchEvaluator = class {
|
|
|
2609
2621
|
concurrency: 3,
|
|
2610
2622
|
maxRetries: 2,
|
|
2611
2623
|
telemetry: false,
|
|
2624
|
+
bypassRowLimit: false,
|
|
2612
2625
|
...config
|
|
2613
2626
|
};
|
|
2614
2627
|
this.limit = pLimit(this.config.concurrency);
|
|
@@ -2762,9 +2775,9 @@ var BatchEvaluator = class {
|
|
|
2762
2775
|
`Unknown evaluator group: "${groupId}". Available: ${EVALUATOR_GROUPS.map((g) => g.id).join(", ")}`
|
|
2763
2776
|
);
|
|
2764
2777
|
}
|
|
2765
|
-
if (inputs.length > group.maxInputRows) {
|
|
2778
|
+
if (!this.config.bypassRowLimit && inputs.length > group.maxInputRows) {
|
|
2766
2779
|
throw new Error(
|
|
2767
|
-
`Input exceeds limit for "${group.id}": ${inputs.length} rows (max ${group.maxInputRows}). Split into smaller batches.`
|
|
2780
|
+
`Input exceeds limit for "${group.id}": ${inputs.length} rows (max ${group.maxInputRows}). Split into smaller batches, or pass { bypassRowLimit: true } in BatchConfig to bypass (use --bypass-row-limit on the CLI).`
|
|
2768
2781
|
);
|
|
2769
2782
|
}
|
|
2770
2783
|
this.isCancelled = false;
|