@axlsdk/eval 0.4.0 → 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/README.md +5 -3
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
|
1
|
-
#
|
|
1
|
+
# @axlsdk/eval
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
[](https://www.npmjs.com/package/@axlsdk/eval)
|
|
4
|
+
|
|
5
|
+
Evaluation framework for [Axl](https://github.com/axl-sdk/axl) agentic workflows. Define datasets, scoring functions, and run evaluations to measure and compare agent performance.
|
|
4
6
|
|
|
5
7
|
## Installation
|
|
6
8
|
|
|
@@ -73,7 +75,7 @@ import { z } from 'zod';
|
|
|
73
75
|
const qualityJudge = llmScorer({
|
|
74
76
|
name: 'quality',
|
|
75
77
|
description: 'Rates output quality on a 0-1 scale',
|
|
76
|
-
model: 'openai:gpt-
|
|
78
|
+
model: 'openai-responses:gpt-5.4',
|
|
77
79
|
system: 'You are an expert evaluator. Rate the quality of AI outputs.',
|
|
78
80
|
schema: z.object({
|
|
79
81
|
score: z.number().min(0).max(1),
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@axlsdk/eval",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.6.0",
|
|
4
4
|
"description": "Evaluation framework for Axl agentic workflows",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "./dist/index.cjs",
|
|
@@ -25,7 +25,7 @@
|
|
|
25
25
|
"dist"
|
|
26
26
|
],
|
|
27
27
|
"dependencies": {
|
|
28
|
-
"@axlsdk/axl": "0.
|
|
28
|
+
"@axlsdk/axl": "0.6.0"
|
|
29
29
|
},
|
|
30
30
|
"devDependencies": {
|
|
31
31
|
"@types/node": "^25.2.3",
|