promptfoo 0.96.0 → 0.96.2
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 +1 -0
- package/dist/package.json +12 -12
- package/dist/src/app/assets/{index-Dwt7E2K_.js → index-CAof5cIE.js} +217 -217
- package/dist/src/app/assets/{index.es-CooNf3HB.js → index.es-CrujH26S.js} +1 -1
- package/dist/src/app/assets/{sync-Bj1WJrHQ.js → sync-gFAH4kmH.js} +1 -1
- package/dist/src/app/index.html +1 -1
- package/dist/src/assertions/answerRelevance.d.ts +3 -0
- package/dist/src/assertions/answerRelevance.d.ts.map +1 -0
- package/dist/src/assertions/answerRelevance.js +19 -0
- package/dist/src/assertions/answerRelevance.js.map +1 -0
- package/dist/src/assertions/bleu.d.ts +4 -14
- package/dist/src/assertions/bleu.d.ts.map +1 -1
- package/dist/src/assertions/bleu.js +19 -3
- package/dist/src/assertions/bleu.js.map +1 -1
- package/dist/src/assertions/classifier.d.ts +3 -0
- package/dist/src/assertions/classifier.d.ts.map +1 -0
- package/dist/src/assertions/classifier.js +22 -0
- package/dist/src/assertions/classifier.js.map +1 -0
- package/dist/src/assertions/contains.d.ts +8 -0
- package/dist/src/assertions/contains.d.ts.map +1 -0
- package/dist/src/assertions/contains.js +110 -0
- package/dist/src/assertions/contains.js.map +1 -0
- package/dist/src/assertions/contextFaithfulness.d.ts +3 -0
- package/dist/src/assertions/contextFaithfulness.d.ts.map +1 -0
- package/dist/src/assertions/contextFaithfulness.js +19 -0
- package/dist/src/assertions/contextFaithfulness.js.map +1 -0
- package/dist/src/assertions/contextRecall.d.ts +3 -0
- package/dist/src/assertions/contextRecall.d.ts.map +1 -0
- package/dist/src/assertions/contextRecall.js +18 -0
- package/dist/src/assertions/contextRecall.js.map +1 -0
- package/dist/src/assertions/contextRelevance.d.ts +3 -0
- package/dist/src/assertions/contextRelevance.d.ts.map +1 -0
- package/dist/src/assertions/contextRelevance.js +19 -0
- package/dist/src/assertions/contextRelevance.js.map +1 -0
- package/dist/src/assertions/cost.d.ts +3 -0
- package/dist/src/assertions/cost.d.ts.map +1 -0
- package/dist/src/assertions/cost.js +22 -0
- package/dist/src/assertions/cost.js.map +1 -0
- package/dist/src/assertions/equals.d.ts +4 -0
- package/dist/src/assertions/equals.d.ts.map +1 -0
- package/dist/src/assertions/equals.js +32 -0
- package/dist/src/assertions/equals.js.map +1 -0
- package/dist/src/assertions/factuality.d.ts +3 -0
- package/dist/src/assertions/factuality.d.ts.map +1 -0
- package/dist/src/assertions/factuality.js +25 -0
- package/dist/src/assertions/factuality.js.map +1 -0
- package/dist/src/assertions/index.d.ts.map +1 -1
- package/dist/src/assertions/index.js +89 -752
- package/dist/src/assertions/index.js.map +1 -1
- package/dist/src/assertions/javascript.d.ts +4 -0
- package/dist/src/assertions/javascript.d.ts.map +1 -0
- package/dist/src/assertions/javascript.js +94 -0
- package/dist/src/assertions/javascript.js.map +1 -0
- package/dist/src/assertions/json.d.ts +3 -4
- package/dist/src/assertions/json.d.ts.map +1 -1
- package/dist/src/assertions/json.js +2 -2
- package/dist/src/assertions/json.js.map +1 -1
- package/dist/src/assertions/latency.d.ts +3 -0
- package/dist/src/assertions/latency.d.ts.map +1 -0
- package/dist/src/assertions/latency.js +22 -0
- package/dist/src/assertions/latency.js.map +1 -0
- package/dist/src/assertions/levenshtein.d.ts +3 -0
- package/dist/src/assertions/levenshtein.d.ts.map +1 -0
- package/dist/src/assertions/levenshtein.js +22 -0
- package/dist/src/assertions/levenshtein.js.map +1 -0
- package/dist/src/assertions/llmRubric.d.ts +3 -0
- package/dist/src/assertions/llmRubric.d.ts.map +1 -0
- package/dist/src/assertions/llmRubric.js +22 -0
- package/dist/src/assertions/llmRubric.js.map +1 -0
- package/dist/src/assertions/modelGradedClosedQa.d.ts +3 -0
- package/dist/src/assertions/modelGradedClosedQa.d.ts.map +1 -0
- package/dist/src/assertions/modelGradedClosedQa.js +25 -0
- package/dist/src/assertions/modelGradedClosedQa.js.map +1 -0
- package/dist/src/assertions/moderation.d.ts +3 -0
- package/dist/src/assertions/moderation.d.ts.map +1 -0
- package/dist/src/assertions/moderation.js +41 -0
- package/dist/src/assertions/moderation.js.map +1 -0
- package/dist/src/assertions/openai.d.ts +5 -0
- package/dist/src/assertions/openai.d.ts.map +1 -0
- package/dist/src/assertions/openai.js +68 -0
- package/dist/src/assertions/openai.js.map +1 -0
- package/dist/src/assertions/perplexity.d.ts +3 -3
- package/dist/src/assertions/perplexity.d.ts.map +1 -1
- package/dist/src/assertions/perplexity.js +2 -2
- package/dist/src/assertions/perplexity.js.map +1 -1
- package/dist/src/assertions/python.d.ts +4 -0
- package/dist/src/assertions/python.d.ts.map +1 -0
- package/dist/src/assertions/python.js +107 -0
- package/dist/src/assertions/python.js.map +1 -0
- package/dist/src/assertions/redteam.d.ts +3 -0
- package/dist/src/assertions/redteam.d.ts.map +1 -0
- package/dist/src/assertions/redteam.js +29 -0
- package/dist/src/assertions/redteam.js.map +1 -0
- package/dist/src/assertions/regex.d.ts +3 -0
- package/dist/src/assertions/regex.d.ts.map +1 -0
- package/dist/src/assertions/regex.js +34 -0
- package/dist/src/assertions/regex.js.map +1 -0
- package/dist/src/assertions/rouge.d.ts +3 -0
- package/dist/src/assertions/rouge.d.ts.map +1 -0
- package/dist/src/assertions/rouge.js +47 -0
- package/dist/src/assertions/rouge.js.map +1 -0
- package/dist/src/assertions/similar.d.ts +3 -0
- package/dist/src/assertions/similar.d.ts.map +1 -0
- package/dist/src/assertions/similar.js +40 -0
- package/dist/src/assertions/similar.js.map +1 -0
- package/dist/src/assertions/sql.d.ts +3 -3
- package/dist/src/assertions/sql.d.ts.map +1 -1
- package/dist/src/assertions/sql.js +14 -3
- package/dist/src/assertions/sql.js.map +1 -1
- package/dist/src/assertions/startsWith.d.ts +3 -0
- package/dist/src/assertions/startsWith.d.ts.map +1 -0
- package/dist/src/assertions/startsWith.js +22 -0
- package/dist/src/assertions/startsWith.js.map +1 -0
- package/dist/src/assertions/utils.d.ts +1 -0
- package/dist/src/assertions/utils.d.ts.map +1 -1
- package/dist/src/assertions/utils.js +7 -0
- package/dist/src/assertions/utils.js.map +1 -1
- package/dist/src/assertions/webhook.d.ts +3 -0
- package/dist/src/assertions/webhook.d.ts.map +1 -0
- package/dist/src/assertions/webhook.js +55 -0
- package/dist/src/assertions/webhook.js.map +1 -0
- package/dist/src/assertions/xml.d.ts +2 -0
- package/dist/src/assertions/xml.d.ts.map +1 -1
- package/dist/src/assertions/xml.js +29 -0
- package/dist/src/assertions/xml.js.map +1 -1
- package/dist/src/commands/init.d.ts.map +1 -1
- package/dist/src/commands/init.js +3 -0
- package/dist/src/commands/init.js.map +1 -1
- package/dist/src/fetch.d.ts.map +1 -1
- package/dist/src/fetch.js +8 -1
- package/dist/src/fetch.js.map +1 -1
- package/dist/src/models/evalResult.d.ts +1 -1
- package/dist/src/models/evalResult.d.ts.map +1 -1
- package/dist/src/models/evalResult.js +1 -1
- package/dist/src/models/evalResult.js.map +1 -1
- package/dist/src/onboarding.d.ts +12 -0
- package/dist/src/onboarding.d.ts.map +1 -1
- package/dist/src/onboarding.js +83 -43
- package/dist/src/onboarding.js.map +1 -1
- package/dist/src/providers/anthropic.d.ts.map +1 -1
- package/dist/src/providers/anthropic.js +12 -2
- package/dist/src/providers/anthropic.js.map +1 -1
- package/dist/src/providers/bedrock.d.ts.map +1 -1
- package/dist/src/providers/bedrock.js +6 -3
- package/dist/src/providers/bedrock.js.map +1 -1
- package/dist/src/redteam/constants.d.ts +4 -3
- package/dist/src/redteam/constants.d.ts.map +1 -1
- package/dist/src/redteam/constants.js +43 -35
- package/dist/src/redteam/constants.js.map +1 -1
- package/dist/src/redteam/index.js +10 -3
- package/dist/src/redteam/index.js.map +1 -1
- package/dist/src/redteam/plugins/base.d.ts.map +1 -1
- package/dist/src/redteam/plugins/base.js +2 -1
- package/dist/src/redteam/plugins/base.js.map +1 -1
- package/dist/src/redteam/plugins/contracts.d.ts.map +1 -1
- package/dist/src/redteam/plugins/contracts.js +20 -9
- package/dist/src/redteam/plugins/contracts.js.map +1 -1
- package/dist/src/redteam/plugins/crossSessionLeak.d.ts.map +1 -1
- package/dist/src/redteam/plugins/crossSessionLeak.js +21 -10
- package/dist/src/redteam/plugins/crossSessionLeak.js.map +1 -1
- package/dist/src/redteam/plugins/debugAccess.d.ts.map +1 -1
- package/dist/src/redteam/plugins/debugAccess.js +20 -9
- package/dist/src/redteam/plugins/debugAccess.js.map +1 -1
- package/dist/src/redteam/plugins/excessiveAgency.d.ts.map +1 -1
- package/dist/src/redteam/plugins/excessiveAgency.js +18 -7
- package/dist/src/redteam/plugins/excessiveAgency.js.map +1 -1
- package/dist/src/redteam/plugins/hallucination.d.ts.map +1 -1
- package/dist/src/redteam/plugins/hallucination.js +18 -7
- package/dist/src/redteam/plugins/hallucination.js.map +1 -1
- package/dist/src/redteam/plugins/harmful.d.ts +2 -2
- package/dist/src/redteam/plugins/harmful.d.ts.map +1 -1
- package/dist/src/redteam/plugins/harmful.js +44 -26
- package/dist/src/redteam/plugins/harmful.js.map +1 -1
- package/dist/src/redteam/plugins/imitation.d.ts.map +1 -1
- package/dist/src/redteam/plugins/imitation.js +20 -9
- package/dist/src/redteam/plugins/imitation.js.map +1 -1
- package/dist/src/redteam/plugins/index.d.ts +2 -2
- package/dist/src/redteam/plugins/index.d.ts.map +1 -1
- package/dist/src/redteam/plugins/index.js +8 -8
- package/dist/src/redteam/plugins/index.js.map +1 -1
- package/dist/src/redteam/plugins/overreliance.d.ts.map +1 -1
- package/dist/src/redteam/plugins/overreliance.js +18 -7
- package/dist/src/redteam/plugins/overreliance.js.map +1 -1
- package/dist/src/redteam/plugins/pii.d.ts +2 -2
- package/dist/src/redteam/plugins/pii.d.ts.map +1 -1
- package/dist/src/redteam/plugins/pii.js +4 -4
- package/dist/src/redteam/plugins/pii.js.map +1 -1
- package/dist/src/redteam/plugins/politics.d.ts.map +1 -1
- package/dist/src/redteam/plugins/politics.js +20 -9
- package/dist/src/redteam/plugins/politics.js.map +1 -1
- package/dist/src/redteam/plugins/promptExtraction.d.ts.map +1 -1
- package/dist/src/redteam/plugins/promptExtraction.js +23 -12
- package/dist/src/redteam/plugins/promptExtraction.js.map +1 -1
- package/dist/src/redteam/plugins/rbac.d.ts.map +1 -1
- package/dist/src/redteam/plugins/rbac.js +20 -9
- package/dist/src/redteam/plugins/rbac.js.map +1 -1
- package/dist/src/redteam/plugins/shellInjection.d.ts.map +1 -1
- package/dist/src/redteam/plugins/shellInjection.js +20 -9
- package/dist/src/redteam/plugins/shellInjection.js.map +1 -1
- package/dist/src/redteam/plugins/sqlInjection.d.ts.map +1 -1
- package/dist/src/redteam/plugins/sqlInjection.js +18 -7
- package/dist/src/redteam/plugins/sqlInjection.js.map +1 -1
- package/dist/src/redteam/providers/goat.d.ts +2 -0
- package/dist/src/redteam/providers/goat.d.ts.map +1 -1
- package/dist/src/redteam/providers/goat.js +9 -2
- package/dist/src/redteam/providers/goat.js.map +1 -1
- package/dist/src/redteam/strategies/crescendo.d.ts +1 -1
- package/dist/src/redteam/strategies/crescendo.d.ts.map +1 -1
- package/dist/src/redteam/strategies/crescendo.js +2 -1
- package/dist/src/redteam/strategies/crescendo.js.map +1 -1
- package/dist/src/redteam/strategies/goat.d.ts.map +1 -1
- package/dist/src/redteam/strategies/goat.js +1 -0
- package/dist/src/redteam/strategies/goat.js.map +1 -1
- package/dist/src/redteam/strategies/index.js +8 -8
- package/dist/src/redteam/strategies/index.js.map +1 -1
- package/dist/src/redteam/strategies/iterative.d.ts +1 -1
- package/dist/src/redteam/strategies/iterative.d.ts.map +1 -1
- package/dist/src/redteam/strategies/iterative.js +2 -1
- package/dist/src/redteam/strategies/iterative.js.map +1 -1
- package/dist/src/redteam/types.d.ts +11 -1
- package/dist/src/redteam/types.d.ts.map +1 -1
- package/dist/src/types/index.d.ts +109 -2
- package/dist/src/types/index.d.ts.map +1 -1
- package/dist/src/types/index.js +21 -26
- package/dist/src/types/index.js.map +1 -1
- package/dist/src/util/config/load.d.ts.map +1 -1
- package/dist/src/util/config/load.js +9 -3
- package/dist/src/util/config/load.js.map +1 -1
- package/dist/src/util/convertEvalResultsToTable.d.ts.map +1 -1
- package/dist/src/util/convertEvalResultsToTable.js +4 -8
- package/dist/src/util/convertEvalResultsToTable.js.map +1 -1
- package/dist/src/util/exportToFile/index.d.ts.map +1 -1
- package/dist/src/validators/redteam.d.ts.map +1 -1
- package/dist/src/validators/redteam.js +6 -5
- package/dist/src/validators/redteam.js.map +1 -1
- package/dist/test/assertions/bleu.test.js +38 -13
- package/dist/test/assertions/bleu.test.js.map +1 -1
- package/dist/test/assertions/sql.test.js +268 -167
- package/dist/test/assertions/sql.test.js.map +1 -1
- package/dist/test/commands/init.test.js +1 -1
- package/dist/test/fetch.test.js +17 -0
- package/dist/test/fetch.test.js.map +1 -1
- package/dist/test/onboarding.test.js +8 -7
- package/dist/test/onboarding.test.js.map +1 -1
- package/dist/test/providers/anthropic.test.js +44 -5
- package/dist/test/providers/anthropic.test.js.map +1 -1
- package/dist/test/providers/bedrock.test.js +1 -4
- package/dist/test/providers/bedrock.test.js.map +1 -1
- package/dist/test/util/config/load.test.js +46 -1
- package/dist/test/util/config/load.test.js.map +1 -1
- package/dist/tsconfig.tsbuildinfo +1 -1
- package/package.json +12 -12
- package/dist/src/redteam/eval/excessive-agency/llm_rubric-20240617.json +0 -10
- package/dist/src/redteam/eval/excessive-agency/llm_rubric-20240618.json +0 -10
- package/dist/src/redteam/eval/harmful/llm_rubric-20240723.json +0 -10
- package/dist/src/redteam/eval/harmful/llm_rubric-20240724.json +0 -10
package/README.md
CHANGED
|
@@ -151,6 +151,7 @@ Deterministic eval metrics
|
|
|
151
151
|
| `levenshtein` | Levenshtein distance is below a threshold |
|
|
152
152
|
| `latency` | Latency is below a threshold (milliseconds) |
|
|
153
153
|
| `perplexity` | Perplexity is below a threshold |
|
|
154
|
+
| `perplexity-score` | Normalized perplexity |
|
|
154
155
|
| `cost` | Cost is below a threshold (for models with cost info such as GPT) |
|
|
155
156
|
| `is-valid-openai-function-call` | Ensure that the function call matches the function's JSON schema |
|
|
156
157
|
| `is-valid-openai-tools-call` | Ensure that all tool calls match the tools JSON schema |
|
package/dist/package.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"name": "promptfoo",
|
|
3
3
|
"description": "LLM eval & testing toolkit",
|
|
4
4
|
"author": "Ian Webster",
|
|
5
|
-
"version": "0.96.
|
|
5
|
+
"version": "0.96.2",
|
|
6
6
|
"license": "MIT",
|
|
7
7
|
"type": "commonjs",
|
|
8
8
|
"repository": {
|
|
@@ -82,13 +82,13 @@
|
|
|
82
82
|
"puppeteer-extra-plugin-stealth": "^2.11.2"
|
|
83
83
|
},
|
|
84
84
|
"devDependencies": {
|
|
85
|
-
"@aws-sdk/client-bedrock-runtime": "^3.
|
|
86
|
-
"@aws-sdk/credential-provider-sso": "^3.
|
|
85
|
+
"@aws-sdk/client-bedrock-runtime": "^3.687.0",
|
|
86
|
+
"@aws-sdk/credential-provider-sso": "^3.687.0",
|
|
87
87
|
"@azure/identity": "^4.5.0",
|
|
88
88
|
"@eslint/js": "^9.14.0",
|
|
89
89
|
"@libsql/client": "^0.14.0",
|
|
90
90
|
"@swc/cli": "^0.5.0",
|
|
91
|
-
"@swc/core": "^1.
|
|
91
|
+
"@swc/core": "^1.9.2",
|
|
92
92
|
"@swc/jest": "^0.2.37",
|
|
93
93
|
"@trivago/prettier-plugin-sort-imports": "^4.3.0",
|
|
94
94
|
"@types/async": "^3.2.24",
|
|
@@ -116,7 +116,7 @@
|
|
|
116
116
|
"drizzle-kit": "^0.26.2",
|
|
117
117
|
"esbuild": "^0.24.0",
|
|
118
118
|
"eslint": "^9.14.0",
|
|
119
|
-
"eslint-plugin-jest": "^28.
|
|
119
|
+
"eslint-plugin-jest": "^28.9.0",
|
|
120
120
|
"eslint-plugin-react-hooks": "^5.1.0-rc.0",
|
|
121
121
|
"eslint-plugin-react-refresh": "^0.4.14",
|
|
122
122
|
"eslint-plugin-unicorn": "^56.0.0",
|
|
@@ -124,7 +124,7 @@
|
|
|
124
124
|
"jest": "^29.7.0",
|
|
125
125
|
"jest-watch-typeahead": "^2.2.2",
|
|
126
126
|
"madge": "^8.0.0",
|
|
127
|
-
"nock": "^13.5.
|
|
127
|
+
"nock": "^13.5.6",
|
|
128
128
|
"nodemon": "^3.1.7",
|
|
129
129
|
"prettier": "^3.3.3",
|
|
130
130
|
"shx": "^0.3.4",
|
|
@@ -132,7 +132,7 @@
|
|
|
132
132
|
"ts-node": "^10.9.2",
|
|
133
133
|
"tsconfig-paths": "^4.2.0",
|
|
134
134
|
"typescript": "^5.6.3",
|
|
135
|
-
"typescript-eslint": "^8.
|
|
135
|
+
"typescript-eslint": "^8.14.0",
|
|
136
136
|
"zod-to-json-schema": "^3.23.5"
|
|
137
137
|
},
|
|
138
138
|
"dependencies": {
|
|
@@ -147,7 +147,7 @@
|
|
|
147
147
|
"@adaline/together-ai": "0.8.0",
|
|
148
148
|
"@adaline/types": "0.15.0",
|
|
149
149
|
"@adaline/vertex": "0.8.1",
|
|
150
|
-
"@anthropic-ai/sdk": "^0.32.
|
|
150
|
+
"@anthropic-ai/sdk": "^0.32.1",
|
|
151
151
|
"@apidevtools/json-schema-ref-parser": "^11.7.2",
|
|
152
152
|
"@emotion/react": "^11.13.3",
|
|
153
153
|
"@emotion/styled": "^11.13.0",
|
|
@@ -156,7 +156,7 @@
|
|
|
156
156
|
"ajv": "^8.17.1",
|
|
157
157
|
"ajv-formats": "^3.0.1",
|
|
158
158
|
"async": "^3.2.6",
|
|
159
|
-
"better-sqlite3": "^11.
|
|
159
|
+
"better-sqlite3": "^11.5.0",
|
|
160
160
|
"cache-manager": "^4.1.0",
|
|
161
161
|
"cache-manager-fs-hash": "^1.0.0",
|
|
162
162
|
"chalk": "^4.1.2",
|
|
@@ -177,15 +177,15 @@
|
|
|
177
177
|
"fast-xml-parser": "^4.5.0",
|
|
178
178
|
"fastest-levenshtein": "^1.0.16",
|
|
179
179
|
"glob": "^10.4.3",
|
|
180
|
-
"groq-sdk": "^0.
|
|
180
|
+
"groq-sdk": "^0.8.0",
|
|
181
181
|
"http-z": "^7.1.1",
|
|
182
182
|
"inquirer": "^11.1.0",
|
|
183
183
|
"js-rouge": "3.0.0",
|
|
184
184
|
"js-yaml": "^4.1.0",
|
|
185
|
-
"mathjs": "^13.2.
|
|
185
|
+
"mathjs": "^13.2.1",
|
|
186
186
|
"node-cache": "^5.1.2",
|
|
187
187
|
"nunjucks": "^3.2.4",
|
|
188
|
-
"openai": "^4.
|
|
188
|
+
"openai": "^4.72.0",
|
|
189
189
|
"opener": "^1.5.2",
|
|
190
190
|
"proxy-agent": "^6.4.0",
|
|
191
191
|
"python-shell": "^5.0.0",
|