judgeval 0.1.33
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/LICENSE.md +202 -0
- package/README.md +340 -0
- package/dist/clients.d.ts +7 -0
- package/dist/clients.js +78 -0
- package/dist/clients.js.map +1 -0
- package/dist/common/integrations/langgraph.d.ts +40 -0
- package/dist/common/integrations/langgraph.js +444 -0
- package/dist/common/integrations/langgraph.js.map +1 -0
- package/dist/common/logger-instance.d.ts +3 -0
- package/dist/common/logger-instance.js +64 -0
- package/dist/common/logger-instance.js.map +1 -0
- package/dist/common/logger.d.ts +54 -0
- package/dist/common/logger.js +221 -0
- package/dist/common/logger.js.map +1 -0
- package/dist/common/tracer.d.ts +205 -0
- package/dist/common/tracer.js +1035 -0
- package/dist/common/tracer.js.map +1 -0
- package/dist/constants.d.ts +51 -0
- package/dist/constants.js +344 -0
- package/dist/constants.js.map +1 -0
- package/dist/data/example.d.ts +70 -0
- package/dist/data/example.js +125 -0
- package/dist/data/example.js.map +1 -0
- package/dist/data/result.d.ts +51 -0
- package/dist/data/result.js +83 -0
- package/dist/data/result.js.map +1 -0
- package/dist/evaluation-run.d.ts +44 -0
- package/dist/evaluation-run.js +136 -0
- package/dist/evaluation-run.js.map +1 -0
- package/dist/index.d.ts +10 -0
- package/dist/index.js +73 -0
- package/dist/index.js.map +1 -0
- package/dist/judgment-client.d.ts +179 -0
- package/dist/judgment-client.js +1038 -0
- package/dist/judgment-client.js.map +1 -0
- package/dist/rules.d.ts +120 -0
- package/dist/rules.js +322 -0
- package/dist/rules.js.map +1 -0
- package/dist/run-evaluation.d.ts +78 -0
- package/dist/run-evaluation.js +618 -0
- package/dist/run-evaluation.js.map +1 -0
- package/dist/scorers/api-scorer.d.ts +79 -0
- package/dist/scorers/api-scorer.js +291 -0
- package/dist/scorers/api-scorer.js.map +1 -0
- package/dist/scorers/base-scorer.d.ts +100 -0
- package/dist/scorers/base-scorer.js +190 -0
- package/dist/scorers/base-scorer.js.map +1 -0
- package/dist/scorers/exact-match-scorer.d.ts +10 -0
- package/dist/scorers/exact-match-scorer.js +84 -0
- package/dist/scorers/exact-match-scorer.js.map +1 -0
- package/package.json +88 -0
package/LICENSE.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
1
|
+
|
|
2
|
+
Apache License
|
|
3
|
+
Version 2.0, January 2004
|
|
4
|
+
http://www.apache.org/licenses/
|
|
5
|
+
|
|
6
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
7
|
+
|
|
8
|
+
1. Definitions.
|
|
9
|
+
|
|
10
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
11
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
12
|
+
|
|
13
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
14
|
+
the copyright owner that is granting the License.
|
|
15
|
+
|
|
16
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
17
|
+
other entities that control, are controlled by, or are under common
|
|
18
|
+
control with that entity. For the purposes of this definition,
|
|
19
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
20
|
+
direction or management of such entity, whether by contract or
|
|
21
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
22
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
23
|
+
|
|
24
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
25
|
+
exercising permissions granted by this License.
|
|
26
|
+
|
|
27
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
28
|
+
including but not limited to software source code, documentation
|
|
29
|
+
source, and configuration files.
|
|
30
|
+
|
|
31
|
+
"Object" form shall mean any form resulting from mechanical
|
|
32
|
+
transformation or translation of a Source form, including but
|
|
33
|
+
not limited to compiled object code, generated documentation,
|
|
34
|
+
and conversions to other media types.
|
|
35
|
+
|
|
36
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
37
|
+
Object form, made available under the License, as indicated by a
|
|
38
|
+
copyright notice that is included in or attached to the work
|
|
39
|
+
(an example is provided in the Appendix below).
|
|
40
|
+
|
|
41
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
42
|
+
form, that is based on (or derived from) the Work and for which the
|
|
43
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
44
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
45
|
+
of this License, Derivative Works shall not include works that remain
|
|
46
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
47
|
+
the Work and Derivative Works thereof.
|
|
48
|
+
|
|
49
|
+
"Contribution" shall mean any work of authorship, including
|
|
50
|
+
the original version of the Work and any modifications or additions
|
|
51
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
52
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
53
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
54
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
55
|
+
means any form of electronic, verbal, or written communication sent
|
|
56
|
+
to the Licensor or its representatives, including but not limited to
|
|
57
|
+
communication on electronic mailing lists, source code control systems,
|
|
58
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
59
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
60
|
+
excluding communication that is conspicuously marked or otherwise
|
|
61
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
62
|
+
|
|
63
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
64
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
65
|
+
subsequently incorporated within the Work.
|
|
66
|
+
|
|
67
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
68
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
69
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
70
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
71
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
72
|
+
Work and such Derivative Works in Source or Object form.
|
|
73
|
+
|
|
74
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
75
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
76
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
77
|
+
(except as stated in this section) patent license to make, have made,
|
|
78
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
79
|
+
where such license applies only to those patent claims licensable
|
|
80
|
+
by such Contributor that are necessarily infringed by their
|
|
81
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
82
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
83
|
+
institute patent litigation against any entity (including a
|
|
84
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
85
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
86
|
+
or contributory patent infringement, then any patent licenses
|
|
87
|
+
granted to You under this License for that Work shall terminate
|
|
88
|
+
as of the date such litigation is filed.
|
|
89
|
+
|
|
90
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
91
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
92
|
+
modifications, and in Source or Object form, provided that You
|
|
93
|
+
meet the following conditions:
|
|
94
|
+
|
|
95
|
+
(a) You must give any other recipients of the Work or
|
|
96
|
+
Derivative Works a copy of this License; and
|
|
97
|
+
|
|
98
|
+
(b) You must cause any modified files to carry prominent notices
|
|
99
|
+
stating that You changed the files; and
|
|
100
|
+
|
|
101
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
102
|
+
that You distribute, all copyright, patent, trademark, and
|
|
103
|
+
attribution notices from the Source form of the Work,
|
|
104
|
+
excluding those notices that do not pertain to any part of
|
|
105
|
+
the Derivative Works; and
|
|
106
|
+
|
|
107
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
108
|
+
distribution, then any Derivative Works that You distribute must
|
|
109
|
+
include a readable copy of the attribution notices contained
|
|
110
|
+
within such NOTICE file, excluding those notices that do not
|
|
111
|
+
pertain to any part of the Derivative Works, in at least one
|
|
112
|
+
of the following places: within a NOTICE text file distributed
|
|
113
|
+
as part of the Derivative Works; within the Source form or
|
|
114
|
+
documentation, if provided along with the Derivative Works; or,
|
|
115
|
+
within a display generated by the Derivative Works, if and
|
|
116
|
+
wherever such third-party notices normally appear. The contents
|
|
117
|
+
of the NOTICE file are for informational purposes only and
|
|
118
|
+
do not modify the License. You may add Your own attribution
|
|
119
|
+
notices within Derivative Works that You distribute, alongside
|
|
120
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
121
|
+
that such additional attribution notices cannot be construed
|
|
122
|
+
as modifying the License.
|
|
123
|
+
|
|
124
|
+
You may add Your own copyright statement to Your modifications and
|
|
125
|
+
may provide additional or different license terms and conditions
|
|
126
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
127
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
128
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
129
|
+
the conditions stated in this License.
|
|
130
|
+
|
|
131
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
132
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
133
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
134
|
+
this License, without any additional terms or conditions.
|
|
135
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
136
|
+
the terms of any separate license agreement you may have executed
|
|
137
|
+
with Licensor regarding such Contributions.
|
|
138
|
+
|
|
139
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
140
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
141
|
+
except as required for reasonable and customary use in describing the
|
|
142
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
143
|
+
|
|
144
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
145
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
146
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
147
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
148
|
+
implied, including, without limitation, any warranties or conditions
|
|
149
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
150
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
151
|
+
appropriateness of using or redistributing the Work and assume any
|
|
152
|
+
risks associated with Your exercise of permissions under this License.
|
|
153
|
+
|
|
154
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
155
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
156
|
+
unless required by applicable law (such as deliberate and grossly
|
|
157
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
158
|
+
liable to You for damages, including any direct, indirect, special,
|
|
159
|
+
incidental, or consequential damages of any character arising as a
|
|
160
|
+
result of this License or out of the use or inability to use the
|
|
161
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
162
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
163
|
+
other commercial damages or losses), even if such Contributor
|
|
164
|
+
has been advised of the possibility of such damages.
|
|
165
|
+
|
|
166
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
167
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
168
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
169
|
+
or other liability obligations and/or rights consistent with this
|
|
170
|
+
License. However, in accepting such obligations, You may act only
|
|
171
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
172
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
173
|
+
defend, and hold each Contributor harmless for any liability
|
|
174
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
175
|
+
of your accepting any such warranty or additional liability.
|
|
176
|
+
|
|
177
|
+
END OF TERMS AND CONDITIONS
|
|
178
|
+
|
|
179
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
180
|
+
|
|
181
|
+
To apply the Apache License to your work, attach the following
|
|
182
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
183
|
+
replaced with your own identifying information. (Don't include
|
|
184
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
185
|
+
comment syntax for the file format. We also recommend that a
|
|
186
|
+
file or class name and description of purpose be included on the
|
|
187
|
+
same "printed page" as the copyright notice for easier
|
|
188
|
+
identification within third-party archives.
|
|
189
|
+
|
|
190
|
+
Copyright [2025] [Judgment Labs Inc.]
|
|
191
|
+
|
|
192
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
193
|
+
you may not use this file except in compliance with the License.
|
|
194
|
+
You may obtain a copy of the License at
|
|
195
|
+
|
|
196
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
197
|
+
|
|
198
|
+
Unless required by applicable law or agreed to in writing, software
|
|
199
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
200
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
201
|
+
See the License for the specific language governing permissions and
|
|
202
|
+
limitations under the License.
|
package/README.md
ADDED
|
@@ -0,0 +1,340 @@
|
|
|
1
|
+
# JudgEval TypeScript SDK
|
|
2
|
+
|
|
3
|
+
A TypeScript SDK for evaluating LLM outputs using the JudgmentLabs evaluation platform.
|
|
4
|
+
|
|
5
|
+
## Installation
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
npm install judgeval
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
## Quick Start
|
|
12
|
+
|
|
13
|
+
```typescript
|
|
14
|
+
import { JudgmentClient, ExampleBuilder, AnswerRelevancyScorer } from 'judgeval';
|
|
15
|
+
import dotenv from 'dotenv';
|
|
16
|
+
|
|
17
|
+
// Load environment variables
|
|
18
|
+
dotenv.config();
|
|
19
|
+
|
|
20
|
+
// Initialize client
|
|
21
|
+
const client = JudgmentClient.getInstance();
|
|
22
|
+
|
|
23
|
+
// Create example
|
|
24
|
+
const example = new ExampleBuilder()
|
|
25
|
+
.input("What's the capital of France?")
|
|
26
|
+
.actualOutput("The capital of France is Paris.")
|
|
27
|
+
.build();
|
|
28
|
+
|
|
29
|
+
// Run evaluation
|
|
30
|
+
async function main() {
|
|
31
|
+
const results = await client.runEvaluation(
|
|
32
|
+
[example],
|
|
33
|
+
[new AnswerRelevancyScorer(0.7)],
|
|
34
|
+
"meta-llama/Meta-Llama-3-8B-Instruct-Turbo"
|
|
35
|
+
);
|
|
36
|
+
|
|
37
|
+
// Print results using standardized logger
|
|
38
|
+
logger.print(results);
|
|
39
|
+
}
|
|
40
|
+
|
|
41
|
+
main();
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
## Key Features
|
|
45
|
+
|
|
46
|
+
- **Standardized Logging**: Consistent logging across all examples with formatted output
|
|
47
|
+
- **Asynchronous Evaluation**: Support for both sync and async evaluation workflows
|
|
48
|
+
- **Comprehensive Scorers**: Multiple pre-built scorers for different evaluation aspects
|
|
49
|
+
- **Tracing Support**: Trace LLM workflows with spans and evaluation integration
|
|
50
|
+
- **Pay-as-you-go Integration**: Automatic handling of billing limits and resource allocation
|
|
51
|
+
|
|
52
|
+
## Core Components
|
|
53
|
+
|
|
54
|
+
### JudgmentClient
|
|
55
|
+
|
|
56
|
+
The main entry point for interacting with the JudgmentLabs API:
|
|
57
|
+
|
|
58
|
+
```typescript
|
|
59
|
+
// Get singleton instance
|
|
60
|
+
const client = JudgmentClient.getInstance();
|
|
61
|
+
|
|
62
|
+
// Or create with explicit credentials
|
|
63
|
+
const client = new JudgmentClient(process.env.JUDGMENT_API_KEY, process.env.JUDGMENT_ORG_ID);
|
|
64
|
+
```
|
|
65
|
+
|
|
66
|
+
### Examples
|
|
67
|
+
|
|
68
|
+
Create examples using the builder pattern:
|
|
69
|
+
|
|
70
|
+
```typescript
|
|
71
|
+
const example = new ExampleBuilder()
|
|
72
|
+
.input("What's the capital of France?")
|
|
73
|
+
.actualOutput("The capital of France is Paris.")
|
|
74
|
+
.expectedOutput("Paris is the capital of France.")
|
|
75
|
+
.retrievalContext(["France is a country in Western Europe."])
|
|
76
|
+
.build();
|
|
77
|
+
```
|
|
78
|
+
|
|
79
|
+
### Scorers
|
|
80
|
+
|
|
81
|
+
Available scorers include:
|
|
82
|
+
|
|
83
|
+
- `AnswerCorrectnessScorer`: Evaluates factual correctness
|
|
84
|
+
- `AnswerRelevancyScorer`: Measures relevance to the input
|
|
85
|
+
- `FaithfulnessScorer`: Checks adherence to provided context
|
|
86
|
+
- `HallucinationScorer`: Detects fabricated information
|
|
87
|
+
- `GroundednessScorer`: Evaluates grounding in context
|
|
88
|
+
- `InstructionAdherenceScorer`: Measures adherence to instructions
|
|
89
|
+
- `JsonCorrectnessScorer`: Validates JSON structure
|
|
90
|
+
- `ComparisonScorer`: Compares outputs on multiple criteria
|
|
91
|
+
- `ExecutionOrderScorer`: Evaluates tool usage sequences
|
|
92
|
+
|
|
93
|
+
### Evaluation Methods
|
|
94
|
+
|
|
95
|
+
```typescript
|
|
96
|
+
// Synchronous evaluation
|
|
97
|
+
const results = await client.runEvaluation(examples, scorers, model);
|
|
98
|
+
|
|
99
|
+
// Asynchronous evaluation
|
|
100
|
+
await client.aRunEvaluation(
|
|
101
|
+
examples,
|
|
102
|
+
scorers,
|
|
103
|
+
model,
|
|
104
|
+
projectName,
|
|
105
|
+
evalRunName
|
|
106
|
+
);
|
|
107
|
+
```
|
|
108
|
+
|
|
109
|
+
### Logging
|
|
110
|
+
|
|
111
|
+
```typescript
|
|
112
|
+
import logger from 'judgeval/common/logger';
|
|
113
|
+
|
|
114
|
+
// Enable logging
|
|
115
|
+
logger.enableLogging();
|
|
116
|
+
|
|
117
|
+
// Log messages
|
|
118
|
+
logger.info("Starting evaluation...");
|
|
119
|
+
|
|
120
|
+
// Print results in standardized format
|
|
121
|
+
logger.print(results);
|
|
122
|
+
```
|
|
123
|
+
|
|
124
|
+
### Tracing
|
|
125
|
+
|
|
126
|
+
```typescript
|
|
127
|
+
import { Tracer } from 'judgeval/common/tracer';
|
|
128
|
+
|
|
129
|
+
const tracer = Tracer.getInstance({
|
|
130
|
+
projectName: "my-project",
|
|
131
|
+
enableEvaluations: true
|
|
132
|
+
});
|
|
133
|
+
|
|
134
|
+
await tracer.runInTrace({ name: "my-trace" }, async (trace) => {
|
|
135
|
+
// Run operations within the trace
|
|
136
|
+
await trace.runInSpan("operation", { spanType: "tool" }, async () => {
|
|
137
|
+
// Perform operations
|
|
138
|
+
});
|
|
139
|
+
});
|
|
140
|
+
```
|
|
141
|
+
|
|
142
|
+
## Result Retrieval
|
|
143
|
+
|
|
144
|
+
You can retrieve past evaluation results using several methods:
|
|
145
|
+
|
|
146
|
+
```typescript
|
|
147
|
+
// Initialize the JudgmentClient
|
|
148
|
+
const client = JudgmentClient.getInstance();
|
|
149
|
+
|
|
150
|
+
// Method 1: Using pullEval
|
|
151
|
+
const results = await client.pullEval('my-project', 'my-eval-run');
|
|
152
|
+
|
|
153
|
+
// Method 2: Using getEvalRun (alias for pullEval)
|
|
154
|
+
const results = await client.getEvalRun('my-project', 'my-eval-run');
|
|
155
|
+
|
|
156
|
+
// List all evaluation runs for a project
|
|
157
|
+
const evalRuns = await client.listEvalRuns('my-project', 100, 0); // limit=100, offset=0
|
|
158
|
+
|
|
159
|
+
// Get statistics for an evaluation run
|
|
160
|
+
const stats = await client.getEvalRunStats('my-project', 'my-eval-run');
|
|
161
|
+
|
|
162
|
+
// Export evaluation results to JSON or CSV
|
|
163
|
+
const jsonExport = await client.exportEvalResults('my-project', 'my-eval-run', 'json');
|
|
164
|
+
const csvExport = await client.exportEvalResults('my-project', 'my-eval-run', 'csv');
|
|
165
|
+
```
|
|
166
|
+
|
|
167
|
+
The returned results include the evaluation run ID and a list of scoring results:
|
|
168
|
+
|
|
169
|
+
```typescript
|
|
170
|
+
[
|
|
171
|
+
{
|
|
172
|
+
"id": "eval-run-id",
|
|
173
|
+
"results": [
|
|
174
|
+
{
|
|
175
|
+
// ScoringResult object with dataObject, scorersData, etc.
|
|
176
|
+
}
|
|
177
|
+
]
|
|
178
|
+
}
|
|
179
|
+
]
|
|
180
|
+
```
|
|
181
|
+
|
|
182
|
+
For a complete example of retrieving evaluation results, see `src/examples/result-retrieval.ts`.
|
|
183
|
+
|
|
184
|
+
## Custom Scorers
|
|
185
|
+
|
|
186
|
+
You can create custom scorers by extending the `JudgevalScorer` class. Here's an example of a custom scorer that checks for exact string matches:
|
|
187
|
+
|
|
188
|
+
```typescript
|
|
189
|
+
import { Example } from './data/example';
|
|
190
|
+
import { JudgevalScorer } from './scorers/base-scorer';
|
|
191
|
+
import { ScorerData } from './data/result';
|
|
192
|
+
|
|
193
|
+
/**
|
|
194
|
+
* ExactMatchScorer - A custom scorer that checks if the actual output exactly matches the expected output
|
|
195
|
+
*/
|
|
196
|
+
class ExactMatchScorer extends JudgevalScorer {
|
|
197
|
+
constructor(threshold: number, additionalMetadata?: Record<string, any>, verbose: boolean = false) {
|
|
198
|
+
super('exact_match', threshold, additionalMetadata, verbose);
|
|
199
|
+
}
|
|
200
|
+
|
|
201
|
+
async scoreExample(example: Example): Promise<ScorerData> {
|
|
202
|
+
try {
|
|
203
|
+
// Check if the example has expected output
|
|
204
|
+
if (!example.expectedOutput) {
|
|
205
|
+
return {
|
|
206
|
+
name: this.type,
|
|
207
|
+
threshold: this.threshold,
|
|
208
|
+
success: false,
|
|
209
|
+
score: 0,
|
|
210
|
+
reason: "Expected output is required for exact match scoring",
|
|
211
|
+
strict_mode: null,
|
|
212
|
+
evaluation_model: "exact-match",
|
|
213
|
+
error: "Missing expected output",
|
|
214
|
+
evaluation_cost: null,
|
|
215
|
+
verbose_logs: null,
|
|
216
|
+
additional_metadata: this.additional_metadata || {}
|
|
217
|
+
};
|
|
218
|
+
}
|
|
219
|
+
|
|
220
|
+
// Compare the actual output with the expected output
|
|
221
|
+
const actualOutput = example.actualOutput?.trim() || '';
|
|
222
|
+
const expectedOutput = example.expectedOutput.trim();
|
|
223
|
+
|
|
224
|
+
// Calculate the score (1 for exact match, 0 otherwise)
|
|
225
|
+
const isMatch = actualOutput === expectedOutput;
|
|
226
|
+
this.score = isMatch ? 1 : 0;
|
|
227
|
+
|
|
228
|
+
// Generate a reason for the score
|
|
229
|
+
const reason = isMatch
|
|
230
|
+
? "The actual output exactly matches the expected output."
|
|
231
|
+
: `The actual output "${actualOutput}" does not match the expected output "${expectedOutput}".`;
|
|
232
|
+
|
|
233
|
+
// Return the scorer data
|
|
234
|
+
return {
|
|
235
|
+
name: this.type,
|
|
236
|
+
threshold: this.threshold,
|
|
237
|
+
success: this.successCheck(),
|
|
238
|
+
score: this.score,
|
|
239
|
+
reason: reason,
|
|
240
|
+
strict_mode: null,
|
|
241
|
+
evaluation_model: "exact-match",
|
|
242
|
+
error: null,
|
|
243
|
+
evaluation_cost: null,
|
|
244
|
+
verbose_logs: this.verbose ? `Comparing: "${actualOutput}" with "${expectedOutput}"` : null,
|
|
245
|
+
additional_metadata: this.additional_metadata || {}
|
|
246
|
+
};
|
|
247
|
+
} catch (error) {
|
|
248
|
+
// Handle any errors during scoring
|
|
249
|
+
const errorMessage = error instanceof Error ? error.message : String(error);
|
|
250
|
+
|
|
251
|
+
return {
|
|
252
|
+
name: this.type,
|
|
253
|
+
threshold: this.threshold,
|
|
254
|
+
success: false,
|
|
255
|
+
score: 0,
|
|
256
|
+
reason: `Error during scoring: ${errorMessage}`,
|
|
257
|
+
strict_mode: null,
|
|
258
|
+
evaluation_model: "exact-match",
|
|
259
|
+
error: errorMessage,
|
|
260
|
+
evaluation_cost: null,
|
|
261
|
+
verbose_logs: null,
|
|
262
|
+
additional_metadata: this.additional_metadata || {}
|
|
263
|
+
};
|
|
264
|
+
}
|
|
265
|
+
}
|
|
266
|
+
}
|
|
267
|
+
```
|
|
268
|
+
|
|
269
|
+
### Using Custom Scorers
|
|
270
|
+
|
|
271
|
+
You can use custom scorers with the JudgmentClient just like any other scorer:
|
|
272
|
+
|
|
273
|
+
```typescript
|
|
274
|
+
// Create examples
|
|
275
|
+
const examples = [
|
|
276
|
+
new ExampleBuilder()
|
|
277
|
+
.input("What is the capital of France?")
|
|
278
|
+
.actualOutput("Paris is the capital of France.")
|
|
279
|
+
.expectedOutput("Paris is the capital of France.")
|
|
280
|
+
.exampleIndex(0)
|
|
281
|
+
.build(),
|
|
282
|
+
// Add more examples...
|
|
283
|
+
];
|
|
284
|
+
|
|
285
|
+
// Create a custom scorer
|
|
286
|
+
const exactMatchScorer = new ExactMatchScorer(1.0, { description: "Checks for exact string match" }, true);
|
|
287
|
+
|
|
288
|
+
// Initialize the JudgmentClient
|
|
289
|
+
const client = JudgmentClient.getInstance();
|
|
290
|
+
|
|
291
|
+
// Run evaluation with the custom scorer
|
|
292
|
+
const results = await client.runEvaluation(
|
|
293
|
+
examples,
|
|
294
|
+
[exactMatchScorer],
|
|
295
|
+
"gpt-3.5-turbo", // Specify a valid model name
|
|
296
|
+
"my-project",
|
|
297
|
+
{
|
|
298
|
+
evalRunName: "custom-scorer-test",
|
|
299
|
+
logResults: true
|
|
300
|
+
}
|
|
301
|
+
);
|
|
302
|
+
```
|
|
303
|
+
|
|
304
|
+
### Viewing Results
|
|
305
|
+
|
|
306
|
+
After running an evaluation with custom scorers, you can view the results in the Judgment platform:
|
|
307
|
+
|
|
308
|
+
```
|
|
309
|
+
https://app.judgmentlabs.ai/app/experiment?project_name=my-project&eval_run_name=custom-scorer-test
|
|
310
|
+
```
|
|
311
|
+
|
|
312
|
+
You can also access the results programmatically:
|
|
313
|
+
|
|
314
|
+
```typescript
|
|
315
|
+
// Print the results
|
|
316
|
+
console.log(results);
|
|
317
|
+
|
|
318
|
+
// Get success rate
|
|
319
|
+
const successCount = results.filter(r => {
|
|
320
|
+
return r.scorersData?.every(s => s.success) ?? false;
|
|
321
|
+
}).length;
|
|
322
|
+
|
|
323
|
+
console.log(`Success rate: ${successCount}/${examples.length} (${(successCount/examples.length*100).toFixed(2)}%)`);
|
|
324
|
+
```
|
|
325
|
+
|
|
326
|
+
For a complete example of using custom scorers, see `src/examples/custom-scorer.ts`.
|
|
327
|
+
|
|
328
|
+
## Examples
|
|
329
|
+
|
|
330
|
+
See the `/examples` directory for complete usage examples:
|
|
331
|
+
- `basic-evaluation.ts`: Simple evaluation workflow
|
|
332
|
+
- `async-evaluation.ts`: Asynchronous evaluation
|
|
333
|
+
- `llm-async-tracer.ts`: Workflow tracing with evaluation
|
|
334
|
+
- `simple-async.ts`: Simplified async evaluation
|
|
335
|
+
- `custom-scorer.ts`: Custom scorer implementation
|
|
336
|
+
|
|
337
|
+
## Environment Variables
|
|
338
|
+
|
|
339
|
+
- `JUDGMENT_API_KEY`: Your JudgmentLabs API key
|
|
340
|
+
- `JUDGMENT_ORG_ID`: Your organization ID
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
import OpenAI from 'openai';
|
|
2
|
+
import Anthropic from '@anthropic-ai/sdk';
|
|
3
|
+
import Together from 'together-ai';
|
|
4
|
+
declare let openaiClient: OpenAI | null;
|
|
5
|
+
declare let anthropicClient: Anthropic | null;
|
|
6
|
+
declare let togetherClient: Together | null;
|
|
7
|
+
export { openaiClient, anthropicClient, togetherClient };
|
package/dist/clients.js
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
1
|
+
"use strict";
|
|
2
|
+
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
|
|
3
|
+
if (k2 === undefined) k2 = k;
|
|
4
|
+
var desc = Object.getOwnPropertyDescriptor(m, k);
|
|
5
|
+
if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
|
|
6
|
+
desc = { enumerable: true, get: function() { return m[k]; } };
|
|
7
|
+
}
|
|
8
|
+
Object.defineProperty(o, k2, desc);
|
|
9
|
+
}) : (function(o, m, k, k2) {
|
|
10
|
+
if (k2 === undefined) k2 = k;
|
|
11
|
+
o[k2] = m[k];
|
|
12
|
+
}));
|
|
13
|
+
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
|
|
14
|
+
Object.defineProperty(o, "default", { enumerable: true, value: v });
|
|
15
|
+
}) : function(o, v) {
|
|
16
|
+
o["default"] = v;
|
|
17
|
+
});
|
|
18
|
+
var __importStar = (this && this.__importStar) || function (mod) {
|
|
19
|
+
if (mod && mod.__esModule) return mod;
|
|
20
|
+
var result = {};
|
|
21
|
+
if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
|
|
22
|
+
__setModuleDefault(result, mod);
|
|
23
|
+
return result;
|
|
24
|
+
};
|
|
25
|
+
var __importDefault = (this && this.__importDefault) || function (mod) {
|
|
26
|
+
return (mod && mod.__esModule) ? mod : { "default": mod };
|
|
27
|
+
};
|
|
28
|
+
Object.defineProperty(exports, "__esModule", { value: true });
|
|
29
|
+
exports.togetherClient = exports.anthropicClient = exports.openaiClient = void 0;
|
|
30
|
+
const dotenv = __importStar(require("dotenv"));
|
|
31
|
+
const openai_1 = __importDefault(require("openai"));
|
|
32
|
+
const sdk_1 = __importDefault(require("@anthropic-ai/sdk"));
|
|
33
|
+
const together_ai_1 = __importDefault(require("together-ai"));
|
|
34
|
+
// Load environment variables
|
|
35
|
+
dotenv.config();
|
|
36
|
+
// Initialize optional OpenAI client
|
|
37
|
+
let openaiClient = null;
|
|
38
|
+
exports.openaiClient = openaiClient;
|
|
39
|
+
if (process.env.OPENAI_API_KEY) {
|
|
40
|
+
try {
|
|
41
|
+
exports.openaiClient = openaiClient = new openai_1.default({
|
|
42
|
+
apiKey: process.env.OPENAI_API_KEY,
|
|
43
|
+
});
|
|
44
|
+
}
|
|
45
|
+
catch (error) {
|
|
46
|
+
// OpenAI package not installed or error initializing
|
|
47
|
+
console.warn('Error initializing OpenAI client:', error);
|
|
48
|
+
}
|
|
49
|
+
}
|
|
50
|
+
// Initialize optional Anthropic client
|
|
51
|
+
let anthropicClient = null;
|
|
52
|
+
exports.anthropicClient = anthropicClient;
|
|
53
|
+
if (process.env.ANTHROPIC_API_KEY) {
|
|
54
|
+
try {
|
|
55
|
+
exports.anthropicClient = anthropicClient = new sdk_1.default({
|
|
56
|
+
apiKey: process.env.ANTHROPIC_API_KEY,
|
|
57
|
+
});
|
|
58
|
+
}
|
|
59
|
+
catch (error) {
|
|
60
|
+
// Anthropic package not installed or error initializing
|
|
61
|
+
console.warn('Error initializing Anthropic client:', error);
|
|
62
|
+
}
|
|
63
|
+
}
|
|
64
|
+
// Initialize optional Together client
|
|
65
|
+
let togetherClient = null;
|
|
66
|
+
exports.togetherClient = togetherClient;
|
|
67
|
+
if (process.env.TOGETHER_API_KEY) {
|
|
68
|
+
try {
|
|
69
|
+
exports.togetherClient = togetherClient = new together_ai_1.default({
|
|
70
|
+
auth: process.env.TOGETHER_API_KEY,
|
|
71
|
+
});
|
|
72
|
+
}
|
|
73
|
+
catch (error) {
|
|
74
|
+
// Together package not installed or error initializing
|
|
75
|
+
console.warn('Error initializing Together client:', error);
|
|
76
|
+
}
|
|
77
|
+
}
|
|
78
|
+
//# sourceMappingURL=clients.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"clients.js","sourceRoot":"","sources":["../src/clients.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAAA,+CAAiC;AACjC,oDAA4B;AAC5B,4DAA0C;AAC1C,8DAAmC;AAEnC,6BAA6B;AAC7B,MAAM,CAAC,MAAM,EAAE,CAAC;AAEhB,oCAAoC;AACpC,IAAI,YAAY,GAAkB,IAAI,CAAC;AAsC9B,oCAAY;AArCrB,IAAI,OAAO,CAAC,GAAG,CAAC,cAAc,EAAE,CAAC;IAC/B,IAAI,CAAC;QACH,uBAAA,YAAY,GAAG,IAAI,gBAAM,CAAC;YACxB,MAAM,EAAE,OAAO,CAAC,GAAG,CAAC,cAAc;SACnC,CAAC,CAAC;IACL,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,qDAAqD;QACrD,OAAO,CAAC,IAAI,CAAC,mCAAmC,EAAE,KAAK,CAAC,CAAC;IAC3D,CAAC;AACH,CAAC;AAED,uCAAuC;AACvC,IAAI,eAAe,GAAqB,IAAI,CAAC;AAyBtB,0CAAe;AAxBtC,IAAI,OAAO,CAAC,GAAG,CAAC,iBAAiB,EAAE,CAAC;IAClC,IAAI,CAAC;QACH,0BAAA,eAAe,GAAG,IAAI,aAAS,CAAC;YAC9B,MAAM,EAAE,OAAO,CAAC,GAAG,CAAC,iBAAiB;SACtC,CAAC,CAAC;IACL,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,wDAAwD;QACxD,OAAO,CAAC,IAAI,CAAC,sCAAsC,EAAE,KAAK,CAAC,CAAC;IAC9D,CAAC;AACH,CAAC;AAED,sCAAsC;AACtC,IAAI,cAAc,GAAoB,IAAI,CAAC;AAYH,wCAAc;AAXtD,IAAI,OAAO,CAAC,GAAG,CAAC,gBAAgB,EAAE,CAAC;IACjC,IAAI,CAAC;QACH,yBAAA,cAAc,GAAG,IAAI,qBAAQ,CAAC;YAC5B,IAAI,EAAE,OAAO,CAAC,GAAG,CAAC,gBAAgB;SACnC,CAAC,CAAC;IACL,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,uDAAuD;QACvD,OAAO,CAAC,IAAI,CAAC,qCAAqC,EAAE,KAAK,CAAC,CAAC;IAC7D,CAAC;AACH,CAAC"}
|
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
import { BaseCallbackHandler } from "@langchain/core/callbacks/base";
|
|
2
|
+
import type { LLMResult } from "@langchain/core/outputs";
|
|
3
|
+
import { BaseMessage } from "@langchain/core/messages";
|
|
4
|
+
import type { Document } from "@langchain/core/documents";
|
|
5
|
+
import type { Serialized } from "@langchain/core/load/serializable";
|
|
6
|
+
import { Tracer } from "../tracer";
|
|
7
|
+
export declare class JudgevalLanggraphCallbackHandler extends BaseCallbackHandler {
|
|
8
|
+
name: string;
|
|
9
|
+
private tracer;
|
|
10
|
+
private spanStartTimes;
|
|
11
|
+
private runIdToSpanId;
|
|
12
|
+
constructor(tracer?: Tracer);
|
|
13
|
+
private _getActiveTraceClient;
|
|
14
|
+
private _generateSpanId;
|
|
15
|
+
private _startSpan;
|
|
16
|
+
private _endSpan;
|
|
17
|
+
onChainStart(serialized: Serialized, inputs: Record<string, unknown>, runId: string, parentRunId?: string | undefined, tags?: string[] | undefined, metadata?: Record<string, unknown> | undefined, options?: Record<string, any>): Promise<void>;
|
|
18
|
+
onChainEnd(outputs: Record<string, unknown> | string, // Output can sometimes be a simple string
|
|
19
|
+
runId: string, parentRunId?: string | undefined, tags?: string[] | undefined): Promise<void>;
|
|
20
|
+
onChainError(error: Error | any, runId: string, parentRunId?: string | undefined, tags?: string[] | undefined): Promise<void>;
|
|
21
|
+
private _getLlmSpanName;
|
|
22
|
+
private _handleLlmStart;
|
|
23
|
+
onLlmStart(serialized: Serialized, prompts: string[], runId: string, parentRunId?: string | undefined, extraParams?: Record<string, unknown> | undefined, tags?: string[] | undefined, metadata?: Record<string, unknown> | undefined, options?: Record<string, any>): Promise<void>;
|
|
24
|
+
onChatModelStart(serialized: Serialized, messages: BaseMessage[][], runId: string, parentRunId?: string | undefined, extraParams?: Record<string, unknown> | undefined, tags?: string[] | undefined, metadata?: Record<string, unknown> | undefined, options?: Record<string, any>): Promise<void>;
|
|
25
|
+
/**
|
|
26
|
+
* Handles the end of an LLM call. Extracts the output, usage data, and ends the corresponding span.
|
|
27
|
+
* @param output The result from the LLM call.
|
|
28
|
+
* @param runId The unique ID of the run.
|
|
29
|
+
*/
|
|
30
|
+
onLlmEnd(output: LLMResult, runId: string): Promise<void>;
|
|
31
|
+
onLlmError(error: Error | any, runId: string, parentRunId?: string | undefined): Promise<void>;
|
|
32
|
+
onToolStart(serialized: Serialized, inputStr: string, // input is often a stringified object
|
|
33
|
+
runId: string, parentRunId?: string | undefined, tags?: string[] | undefined, metadata?: Record<string, unknown> | undefined): Promise<void>;
|
|
34
|
+
onToolEnd(output: string, // Tool output is typically a string
|
|
35
|
+
runId: string, parentRunId?: string | undefined): Promise<void>;
|
|
36
|
+
onToolError(error: Error | any, runId: string, parentRunId?: string | undefined): Promise<void>;
|
|
37
|
+
onRetrieverStart(serialized: Serialized, query: string, runId: string, parentRunId?: string | undefined, tags?: string[] | undefined, metadata?: Record<string, unknown> | undefined): Promise<void>;
|
|
38
|
+
onRetrieverEnd(documents: Document[], runId: string, parentRunId?: string | undefined, tags?: string[] | undefined): Promise<void>;
|
|
39
|
+
onRetrieverError(error: Error | any, runId: string, parentRunId?: string | undefined, tags?: string[] | undefined): Promise<void>;
|
|
40
|
+
}
|