sensei-eval 0.1.0
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 +201 -0
- package/dist/criteria/challenge.d.ts +7 -0
- package/dist/criteria/challenge.d.ts.map +1 -0
- package/dist/criteria/challenge.js +142 -0
- package/dist/criteria/challenge.js.map +1 -0
- package/dist/criteria/index.d.ts +5 -0
- package/dist/criteria/index.d.ts.map +1 -0
- package/dist/criteria/index.js +5 -0
- package/dist/criteria/index.js.map +1 -0
- package/dist/criteria/lesson.d.ts +7 -0
- package/dist/criteria/lesson.d.ts.map +1 -0
- package/dist/criteria/lesson.js +143 -0
- package/dist/criteria/lesson.js.map +1 -0
- package/dist/criteria/review.d.ts +6 -0
- package/dist/criteria/review.d.ts.map +1 -0
- package/dist/criteria/review.js +93 -0
- package/dist/criteria/review.js.map +1 -0
- package/dist/criteria/universal.d.ts +9 -0
- package/dist/criteria/universal.d.ts.map +1 -0
- package/dist/criteria/universal.js +204 -0
- package/dist/criteria/universal.js.map +1 -0
- package/dist/index.d.ts +5 -0
- package/dist/index.d.ts.map +1 -0
- package/dist/index.js +4 -0
- package/dist/index.js.map +1 -0
- package/dist/judge.d.ts +7 -0
- package/dist/judge.d.ts.map +1 -0
- package/dist/judge.js +55 -0
- package/dist/judge.js.map +1 -0
- package/dist/runner.d.ts +17 -0
- package/dist/runner.d.ts.map +1 -0
- package/dist/runner.js +59 -0
- package/dist/runner.js.map +1 -0
- package/dist/types.d.ts +56 -0
- package/dist/types.d.ts.map +1 -0
- package/dist/types.js +2 -0
- package/dist/types.js.map +1 -0
- package/dist/utils/markdown.d.ts +17 -0
- package/dist/utils/markdown.d.ts.map +1 -0
- package/dist/utils/markdown.js +69 -0
- package/dist/utils/markdown.js.map +1 -0
- package/package.json +56 -0
package/package.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "sensei-eval",
|
|
3
|
+
"version": "0.1.0",
|
|
4
|
+
"description": "Evaluate AI-generated educational content with deterministic checks and LLM-as-judge scoring",
|
|
5
|
+
"type": "module",
|
|
6
|
+
"license": "MIT",
|
|
7
|
+
"author": "Will Jones",
|
|
8
|
+
"repository": {
|
|
9
|
+
"type": "git",
|
|
10
|
+
"url": "git+https://github.com/CodeJonesW/prompt-eval.git"
|
|
11
|
+
},
|
|
12
|
+
"homepage": "https://github.com/CodeJonesW/prompt-eval#readme",
|
|
13
|
+
"bugs": {
|
|
14
|
+
"url": "https://github.com/CodeJonesW/prompt-eval/issues"
|
|
15
|
+
},
|
|
16
|
+
"keywords": [
|
|
17
|
+
"eval",
|
|
18
|
+
"evaluation",
|
|
19
|
+
"educational-content",
|
|
20
|
+
"llm",
|
|
21
|
+
"llm-judge",
|
|
22
|
+
"ai",
|
|
23
|
+
"content-quality",
|
|
24
|
+
"rubric",
|
|
25
|
+
"scoring"
|
|
26
|
+
],
|
|
27
|
+
"engines": {
|
|
28
|
+
"node": ">=18"
|
|
29
|
+
},
|
|
30
|
+
"main": "dist/index.js",
|
|
31
|
+
"types": "dist/index.d.ts",
|
|
32
|
+
"exports": {
|
|
33
|
+
".": {
|
|
34
|
+
"types": "./dist/index.d.ts",
|
|
35
|
+
"import": "./dist/index.js"
|
|
36
|
+
}
|
|
37
|
+
},
|
|
38
|
+
"scripts": {
|
|
39
|
+
"build": "tsc",
|
|
40
|
+
"prepublishOnly": "npm run build",
|
|
41
|
+
"test": "vitest run",
|
|
42
|
+
"test:watch": "vitest",
|
|
43
|
+
"test:integration": "vitest run --config tests/integration/vitest.config.ts",
|
|
44
|
+
"analyze": "npx tsx scripts/analyze-discrimination.ts"
|
|
45
|
+
},
|
|
46
|
+
"files": [
|
|
47
|
+
"dist"
|
|
48
|
+
],
|
|
49
|
+
"dependencies": {
|
|
50
|
+
"@anthropic-ai/sdk": "^0.72.1"
|
|
51
|
+
},
|
|
52
|
+
"devDependencies": {
|
|
53
|
+
"typescript": "^5.9.3",
|
|
54
|
+
"vitest": "^4.0.18"
|
|
55
|
+
}
|
|
56
|
+
}
|