@orq-ai/evaluatorq 1.0.0-12 → 1.0.0-8
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 +15 -28
- package/dist/lib/evaluatorq.d.ts.map +1 -1
- package/dist/lib/evaluatorq.js +3 -7
- package/dist/lib/types.d.ts +5 -6
- package/dist/lib/types.d.ts.map +1 -1
- package/dist/tsconfig.lib.tsbuildinfo +1 -1
- package/package.json +1 -18
- package/src/index.ts +4 -0
- package/src/lib/effects.ts +174 -0
- package/src/lib/evaluatorq.ts +260 -0
- package/src/lib/progress.ts +170 -0
- package/src/lib/table-display.ts +352 -0
- package/src/lib/types.ts +79 -0
- package/src/lib/visualizer/html-generator.ts +364 -0
- package/src/lib/visualizer/index.ts +70 -0
- package/src/lib/visualizer/types.ts +17 -0
- package/tsconfig.json +10 -0
- package/tsconfig.lib.json +14 -0
package/README.md
CHANGED
|
@@ -185,43 +185,27 @@ Promise that resolves when evaluation is complete.
|
|
|
185
185
|
### Types
|
|
186
186
|
|
|
187
187
|
```typescript
|
|
188
|
-
type Output = string | number | boolean | Record<string, unknown> | null;
|
|
189
|
-
|
|
190
188
|
interface DataPoint {
|
|
191
|
-
inputs: Record<string,
|
|
192
|
-
expectedOutput?:
|
|
189
|
+
inputs: Record<string, any>;
|
|
190
|
+
expectedOutput?: any;
|
|
191
|
+
metadata?: Record<string, any>;
|
|
193
192
|
}
|
|
194
193
|
|
|
195
194
|
interface JobResult {
|
|
196
|
-
|
|
197
|
-
output:
|
|
198
|
-
error?: Error;
|
|
199
|
-
evaluatorScores?: EvaluatorScore[];
|
|
200
|
-
}
|
|
201
|
-
|
|
202
|
-
interface EvaluatorScore {
|
|
203
|
-
evaluatorName: string;
|
|
204
|
-
score: number | boolean | string;
|
|
205
|
-
error?: Error;
|
|
195
|
+
name: string;
|
|
196
|
+
output: any;
|
|
206
197
|
}
|
|
207
198
|
|
|
208
|
-
|
|
209
|
-
data: DataPoint,
|
|
210
|
-
row: number,
|
|
211
|
-
) => Promise<{
|
|
199
|
+
interface Evaluator {
|
|
212
200
|
name: string;
|
|
213
|
-
|
|
214
|
-
}
|
|
201
|
+
scorer: (context: EvaluatorContext) => Promise<number>;
|
|
202
|
+
}
|
|
215
203
|
|
|
216
|
-
|
|
204
|
+
interface EvaluatorContext {
|
|
217
205
|
data: DataPoint;
|
|
218
|
-
output:
|
|
219
|
-
|
|
220
|
-
|
|
221
|
-
type Scorer =
|
|
222
|
-
| ((params: ScorerParameter) => Promise<string>)
|
|
223
|
-
| ((params: ScorerParameter) => Promise<number>)
|
|
224
|
-
| ((params: ScorerParameter) => Promise<boolean>);
|
|
206
|
+
output: any;
|
|
207
|
+
row: number;
|
|
208
|
+
}
|
|
225
209
|
```
|
|
226
210
|
|
|
227
211
|
## 🛠️ Development
|
|
@@ -232,6 +216,9 @@ bunx nx build evaluatorq
|
|
|
232
216
|
|
|
233
217
|
# Run type checking
|
|
234
218
|
bunx nx typecheck evaluatorq
|
|
219
|
+
|
|
220
|
+
# Run tests
|
|
221
|
+
bunx nx test evaluatorq
|
|
235
222
|
```
|
|
236
223
|
|
|
237
224
|
## 📄 License
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"evaluatorq.d.ts","sourceRoot":"","sources":["../../src/lib/evaluatorq.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,EAAQ,MAAM,QAAQ,CAAC;AAWtC,OAAO,KAAK,EAEV,eAAe,EACf,gBAAgB,EAEjB,MAAM,YAAY,CAAC;AA+CpB;;;;GAIG;AACH,wBAAsB,UAAU,CAC9B,KAAK,EAAE,MAAM,EACb,MAAM,EAAE,eAAe,GACtB,OAAO,CAAC,gBAAgB,CAAC,
|
|
1
|
+
{"version":3,"file":"evaluatorq.d.ts","sourceRoot":"","sources":["../../src/lib/evaluatorq.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,EAAQ,MAAM,QAAQ,CAAC;AAWtC,OAAO,KAAK,EAEV,eAAe,EACf,gBAAgB,EAEjB,MAAM,YAAY,CAAC;AA+CpB;;;;GAIG;AACH,wBAAsB,UAAU,CAC9B,KAAK,EAAE,MAAM,EACb,MAAM,EAAE,eAAe,GACtB,OAAO,CAAC,gBAAgB,CAAC,CAoE3B;AAGD,eAAO,MAAM,gBAAgB,GAC3B,OAAO,MAAM,EACb,QAAQ,eAAe,KACtB,MAAM,CAAC,MAAM,CAAC,gBAAgB,EAAE,KAAK,EAAE,KAAK,CAuD9C,CAAC;AAoDF,eAAO,MAAM,yBAAyB,GACpC,MAAM,MAAM,EACZ,QAAQ,eAAe,KACtB,MAAM,CAAC,MAAM,CAAC,gBAAgB,EAAE,KAAK,EAAE,KAAK,CAI5C,CAAC"}
|
package/dist/lib/evaluatorq.js
CHANGED
|
@@ -5,7 +5,7 @@ import { displayResultsTableEffect } from "./table-display.js";
|
|
|
5
5
|
async function setupOrqClient(apiKey) {
|
|
6
6
|
try {
|
|
7
7
|
const client = await import("@orq-ai/node");
|
|
8
|
-
return new client.Orq({ apiKey });
|
|
8
|
+
return new client.Orq({ apiKey, serverURL: "https://my.staging.orq.ai" });
|
|
9
9
|
}
|
|
10
10
|
catch (error) {
|
|
11
11
|
const err = error;
|
|
@@ -67,9 +67,7 @@ export async function evaluatorq(_name, params) {
|
|
|
67
67
|
phase: "initializing",
|
|
68
68
|
}));
|
|
69
69
|
// Process data points
|
|
70
|
-
const results = yield* _(Effect.forEach(dataPromises.map((dataPromise, index) => ({ dataPromise, index })), ({ dataPromise, index }) => processDataPointEffect(dataPromise
|
|
71
|
-
? dataPromise
|
|
72
|
-
: Promise.resolve(dataPromise), index, jobs, evaluators, parallelism), { concurrency: parallelism }));
|
|
70
|
+
const results = yield* _(Effect.forEach(dataPromises.map((dataPromise, index) => ({ dataPromise, index })), ({ dataPromise, index }) => processDataPointEffect(dataPromise, index, jobs, evaluators, parallelism), { concurrency: parallelism }));
|
|
73
71
|
return results.flat();
|
|
74
72
|
}),
|
|
75
73
|
// Conditionally add table display
|
|
@@ -122,9 +120,7 @@ const runEvaluationEffect = (dataPromises, evaluators = [], jobs, parallelism, p
|
|
|
122
120
|
phase: "initializing",
|
|
123
121
|
}));
|
|
124
122
|
// Process data points
|
|
125
|
-
const results = yield* _(Effect.forEach(dataPromises.map((dataPromise, index) => ({ dataPromise, index })), ({ dataPromise, index }) => processDataPointEffect(dataPromise
|
|
126
|
-
? dataPromise
|
|
127
|
-
: Promise.resolve(dataPromise), index, jobs, evaluators, parallelism), { concurrency: parallelism }));
|
|
123
|
+
const results = yield* _(Effect.forEach(dataPromises.map((dataPromise, index) => ({ dataPromise, index })), ({ dataPromise, index }) => processDataPointEffect(dataPromise, index, jobs, evaluators, parallelism), { concurrency: parallelism }));
|
|
128
124
|
return results.flat();
|
|
129
125
|
}),
|
|
130
126
|
// Conditionally add table display
|
package/dist/lib/types.d.ts
CHANGED
|
@@ -46,16 +46,15 @@ export type Job = (data: DataPoint, row: number) => Promise<{
|
|
|
46
46
|
export interface EvaluatorParams {
|
|
47
47
|
data: {
|
|
48
48
|
datasetId: string;
|
|
49
|
-
} |
|
|
50
|
-
evaluators?:
|
|
49
|
+
} | Promise<DataPoint>[];
|
|
50
|
+
evaluators?: {
|
|
51
|
+
name: string;
|
|
52
|
+
scorer: Scorer;
|
|
53
|
+
}[];
|
|
51
54
|
jobs: Job[];
|
|
52
55
|
parallelism?: number;
|
|
53
56
|
print?: boolean;
|
|
54
57
|
}
|
|
55
|
-
export type Evaluator = {
|
|
56
|
-
name: string;
|
|
57
|
-
scorer: Scorer;
|
|
58
|
-
};
|
|
59
58
|
export type ScorerParameter = {
|
|
60
59
|
data: DataPoint;
|
|
61
60
|
output: Output;
|
package/dist/lib/types.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../../src/lib/types.ts"],"names":[],"mappings":"AAAA,MAAM,MAAM,MAAM,GAAG,MAAM,GAAG,MAAM,GAAG,OAAO,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,IAAI,CAAC;AAEhF,MAAM,WAAW,cAAc;IAC7B,aAAa,EAAE,MAAM,CAAC;IACtB,KAAK,EAAE,MAAM,GAAG,OAAO,GAAG,MAAM,CAAC;IACjC,KAAK,CAAC,EAAE,KAAK,CAAC;CACf;AAED,MAAM,WAAW,SAAS;IACxB,OAAO,EAAE,MAAM,CAAC;IAChB,MAAM,EAAE,MAAM,CAAC;IACf,KAAK,CAAC,EAAE,KAAK,CAAC;IACd,eAAe,CAAC,EAAE,cAAc,EAAE,CAAC;CACpC;AAED,MAAM,WAAW,eAAe;IAC9B,SAAS,EAAE,SAAS,CAAC;IACrB,KAAK,CAAC,EAAE,KAAK,CAAC;IACd,UAAU,CAAC,EAAE,SAAS,EAAE,CAAC;CAC1B;AAED,MAAM,MAAM,gBAAgB,GAAG,eAAe,EAAE,CAAC;AAEjD;;;GAGG;AACH,MAAM,WAAW,SAAS;IACxB,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IAChC,cAAc,CAAC,EAAE,MAAM,CAAC;CACzB;AAED;;;;GAIG;AACH,MAAM,MAAM,GAAG,GAAG,CAChB,IAAI,EAAE,SAAS,EACf,GAAG,EAAE,MAAM,KACR,OAAO,CAAC;IACX,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,MAAM,CAAC;CAChB,CAAC,CAAC;AAEH;;;;;;;;;GASG;AACH,MAAM,WAAW,eAAe;IAC9B,IAAI,EACA;QACE,SAAS,EAAE,MAAM,CAAC;KACnB,GACD,
|
|
1
|
+
{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../../src/lib/types.ts"],"names":[],"mappings":"AAAA,MAAM,MAAM,MAAM,GAAG,MAAM,GAAG,MAAM,GAAG,OAAO,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,IAAI,CAAC;AAEhF,MAAM,WAAW,cAAc;IAC7B,aAAa,EAAE,MAAM,CAAC;IACtB,KAAK,EAAE,MAAM,GAAG,OAAO,GAAG,MAAM,CAAC;IACjC,KAAK,CAAC,EAAE,KAAK,CAAC;CACf;AAED,MAAM,WAAW,SAAS;IACxB,OAAO,EAAE,MAAM,CAAC;IAChB,MAAM,EAAE,MAAM,CAAC;IACf,KAAK,CAAC,EAAE,KAAK,CAAC;IACd,eAAe,CAAC,EAAE,cAAc,EAAE,CAAC;CACpC;AAED,MAAM,WAAW,eAAe;IAC9B,SAAS,EAAE,SAAS,CAAC;IACrB,KAAK,CAAC,EAAE,KAAK,CAAC;IACd,UAAU,CAAC,EAAE,SAAS,EAAE,CAAC;CAC1B;AAED,MAAM,MAAM,gBAAgB,GAAG,eAAe,EAAE,CAAC;AAEjD;;;GAGG;AACH,MAAM,WAAW,SAAS;IACxB,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IAChC,cAAc,CAAC,EAAE,MAAM,CAAC;CACzB;AAED;;;;GAIG;AACH,MAAM,MAAM,GAAG,GAAG,CAChB,IAAI,EAAE,SAAS,EACf,GAAG,EAAE,MAAM,KACR,OAAO,CAAC;IACX,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,MAAM,CAAC;CAChB,CAAC,CAAC;AAEH;;;;;;;;;GASG;AACH,MAAM,WAAW,eAAe;IAC9B,IAAI,EACA;QACE,SAAS,EAAE,MAAM,CAAC;KACnB,GACD,OAAO,CAAC,SAAS,CAAC,EAAE,CAAC;IACzB,UAAU,CAAC,EAAE;QACX,IAAI,EAAE,MAAM,CAAC;QACb,MAAM,EAAE,MAAM,CAAC;KAChB,EAAE,CAAC;IACJ,IAAI,EAAE,GAAG,EAAE,CAAC;IACZ,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,KAAK,CAAC,EAAE,OAAO,CAAC;CACjB;AAED,MAAM,MAAM,eAAe,GAAG;IAC5B,IAAI,EAAE,SAAS,CAAC;IAChB,MAAM,EAAE,MAAM,CAAC;CAChB,CAAC;AAEF,MAAM,MAAM,MAAM,GACd,CAAC,CAAC,MAAM,EAAE,eAAe,KAAK,OAAO,CAAC,MAAM,CAAC,CAAC,GAC9C,CAAC,CAAC,MAAM,EAAE,eAAe,KAAK,OAAO,CAAC,MAAM,CAAC,CAAC,GAC9C,CAAC,CAAC,MAAM,EAAE,eAAe,KAAK,OAAO,CAAC,OAAO,CAAC,CAAC,CAAC"}
|