judgeval 0.0.6__py3-none-any.whl → 0.0.8__py3-none-any.whl

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.
Files changed (17) hide show
  1. judgeval/judgment_client.py +6 -5
  2. judgeval/scorers/judgeval_scorer.py +2 -0
  3. judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/answer_correctness_scorer.py +10 -5
  4. judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/answer_relevancy_scorer.py +11 -5
  5. judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/contextual_precision_scorer.py +10 -5
  6. judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/contextual_recall_scorer.py +10 -5
  7. judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/contextual_relevancy_scorer.py +10 -5
  8. judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/faithfulness_scorer.py +11 -6
  9. judgeval/scorers/judgeval_scorers/local_implementations/hallucination/hallucination_scorer.py +10 -5
  10. judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/__init__.py +5 -0
  11. judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/json_correctness_scorer.py +13 -6
  12. judgeval/scorers/judgeval_scorers/local_implementations/summarization/summarization_scorer.py +10 -1
  13. judgeval/scorers/judgeval_scorers/local_implementations/tool_correctness/tool_correctness_scorer.py +10 -4
  14. {judgeval-0.0.6.dist-info → judgeval-0.0.8.dist-info}/METADATA +3 -1
  15. {judgeval-0.0.6.dist-info → judgeval-0.0.8.dist-info}/RECORD +17 -16
  16. {judgeval-0.0.6.dist-info → judgeval-0.0.8.dist-info}/WHEEL +0 -0
  17. {judgeval-0.0.6.dist-info → judgeval-0.0.8.dist-info}/licenses/LICENSE.md +0 -0
judgeval/judgment_client.py CHANGED
@@ -267,7 +267,6 @@ class JudgmentClient:
267
267
 
268
268
  return response.json()["slug"]
269
269
 
270
-
271
270
  def assert_test(
272
271
  self,
273
272
  examples: List[Example],
@@ -275,12 +274,14 @@ class JudgmentClient:
275
274
  model: Union[str, List[str], JudgevalJudge],
276
275
  aggregator: Optional[str] = None,
277
276
  metadata: Optional[Dict[str, Any]] = None,
278
- log_results: bool = False,
279
- project_name: str = "",
280
- eval_run_name: str = "",
277
+ log_results: bool = True,
278
+ project_name: str = "default_project",
279
+ eval_run_name: str = "default_eval_run",
281
280
  override: bool = False,
282
281
  ) -> None:
283
-
282
+ """
283
+ Asserts a test by running the evaluation and checking the results for success
284
+ """
284
285
  results = self.run_evaluation(
285
286
  examples=examples,
286
287
  scorers=scorers,
judgeval/scorers/judgeval_scorer.py CHANGED
@@ -58,6 +58,8 @@ class JudgevalScorer:
58
58
  additional_metadata: Optional[Dict] = None
59
59
  ):
60
60
  debug(f"Initializing CustomScorer with score_type={score_type}, threshold={threshold}")
61
+ if not 0 <= threshold <= 1:
62
+ raise ValueError("Threshold must be between 0 and 1")
61
63
  if strict_mode:
62
64
  warning("Strict mode enabled - scoring will be more rigorous")
63
65
  info(f"CustomScorer initialized with evaluation_model: {evaluation_model}")
judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/answer_correctness_scorer.py CHANGED
@@ -1,6 +1,7 @@
1
1
  from typing import Optional, List, Union, Tuple
2
2
  from pydantic import BaseModel
3
3
 
4
+ from judgeval.constants import APIScorer
4
5
  from judgeval.judges import JudgevalJudge
5
6
  from judgeval.judges.utils import create_judge
6
7
  from judgeval.data import Example, ExampleParams
@@ -38,13 +39,17 @@ class AnswerCorrectnessScorer(JudgevalScorer):
38
39
  strict_mode: bool = False,
39
40
  verbose_mode: bool = False
40
41
  ):
41
- self.threshold = 1 if strict_mode else threshold
42
- self.include_reason = include_reason
42
+ super().__init__(
43
+ score_type=APIScorer.ANSWER_CORRECTNESS,
44
+ threshold=1 if strict_mode else threshold,
45
+ evaluation_model=None,
46
+ include_reason=include_reason,
47
+ async_mode=async_mode,
48
+ strict_mode=strict_mode,
49
+ verbose_mode=verbose_mode
50
+ )
43
51
  self.model, self.using_native_model = create_judge(model)
44
52
  self.evaluation_model = self.model.get_model_name()
45
- self.async_mode = async_mode
46
- self.strict_mode = strict_mode
47
- self.verbose_mode = verbose_mode
48
53
 
49
54
  async def _a_get_statements(self, expected_output: str) -> List[str]:
50
55
  prompt = AnswerCorrectnessTemplate.deduce_statements(
judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/answer_relevancy_scorer.py CHANGED
@@ -1,5 +1,6 @@
1
1
  from typing import Optional, List, Union, Tuple
2
2
 
3
+ from judgeval.constants import APIScorer
3
4
  from judgeval.scorers.utils import (get_or_create_event_loop,
4
5
  scorer_progress_meter,
5
6
  create_verbose_logs,
@@ -34,13 +35,18 @@ class AnswerRelevancyScorer(JudgevalScorer):
34
35
  strict_mode: bool = False,
35
36
  verbose_mode: bool = False,
36
37
  ):
37
- self.threshold = 1 if strict_mode else threshold
38
+ super().__init__(
39
+ score_type=APIScorer.ANSWER_RELEVANCY,
40
+ threshold=1 if strict_mode else threshold,
41
+ evaluation_model=None,
42
+ include_reason=include_reason,
43
+ async_mode=async_mode,
44
+ strict_mode=strict_mode,
45
+ verbose_mode=verbose_mode
46
+ )
38
47
  self.model, self.using_native_model = create_judge(model)
39
48
  self.evaluation_model = self.model.get_model_name()
40
- self.include_reason = include_reason
41
- self.async_mode = async_mode
42
- self.strict_mode = strict_mode
43
- self.verbose_mode = verbose_mode
49
+ print(self.model)
44
50
 
45
51
  def score_example(
46
52
  self,
judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/contextual_precision_scorer.py CHANGED
@@ -4,6 +4,7 @@ from judgeval.judges import JudgevalJudge
4
4
  from judgeval.judges.utils import create_judge
5
5
  from judgeval.data import Example, ExampleParams
6
6
  from judgeval.scorers import JudgevalScorer
7
+ from judgeval.constants import APIScorer
7
8
  from judgeval.scorers.utils import (
8
9
  get_or_create_event_loop,
9
10
  parse_response_json,
@@ -30,13 +31,17 @@ class ContextualPrecisionScorer(JudgevalScorer):
30
31
  strict_mode: bool = False,
31
32
  verbose_mode: bool = False,
32
33
  ):
33
- self.threshold = 1 if strict_mode else threshold
34
- self.include_reason = include_reason
34
+ super().__init__(
35
+ score_type=APIScorer.CONTEXTUAL_PRECISION,
36
+ threshold=1 if strict_mode else threshold,
37
+ evaluation_model=None,
38
+ include_reason=include_reason,
39
+ async_mode=async_mode,
40
+ strict_mode=strict_mode,
41
+ verbose_mode=verbose_mode
42
+ )
35
43
  self.model, self.using_native_model = create_judge(model)
36
44
  self.evaluation_model = self.model.get_model_name()
37
- self.async_mode = async_mode
38
- self.strict_mode = strict_mode
39
- self.verbose_mode = verbose_mode
40
45
 
41
46
  def score_example(
42
47
  self,
judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/contextual_recall_scorer.py CHANGED
@@ -1,5 +1,6 @@
1
1
  from typing import Optional, List, Union
2
2
 
3
+ from judgeval.constants import APIScorer
3
4
  from judgeval.scorers.utils import (
4
5
  get_or_create_event_loop,
5
6
  parse_response_json,
@@ -32,14 +33,18 @@ class ContextualRecallScorer(JudgevalScorer):
32
33
  verbose_mode: bool = False,
33
34
  user: Optional[str] = None
34
35
  ):
36
+ super().__init__(
37
+ score_type=APIScorer.CONTEXTUAL_RECALL,
38
+ threshold=1 if strict_mode else threshold,
39
+ evaluation_model=None,
40
+ include_reason=include_reason,
41
+ async_mode=async_mode,
42
+ strict_mode=strict_mode,
43
+ verbose_mode=verbose_mode
44
+ )
35
45
  self.user = user
36
- self.threshold = 1 if strict_mode else threshold
37
46
  self.model, self.using_native_model = create_judge(model)
38
47
  self.evaluation_model = self.model.get_model_name()
39
- self.include_reason = include_reason
40
- self.async_mode = async_mode
41
- self.strict_mode = strict_mode
42
- self.verbose_mode = verbose_mode
43
48
 
44
49
  def score_example(
45
50
  self,
judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/contextual_relevancy_scorer.py CHANGED
@@ -1,6 +1,7 @@
1
1
  from typing import Optional, List, Union
2
2
  import asyncio
3
3
 
4
+ from judgeval.constants import APIScorer
4
5
  from judgeval.scorers.utils import (get_or_create_event_loop,
5
6
  scorer_progress_meter,
6
7
  create_verbose_logs,
@@ -32,14 +33,18 @@ class ContextualRelevancyScorer(JudgevalScorer):
32
33
  verbose_mode: bool = False,
33
34
  user: Optional[str] = None
34
35
  ):
36
+ super().__init__(
37
+ score_type=APIScorer.CONTEXTUAL_RELEVANCY,
38
+ threshold=1 if strict_mode else threshold,
39
+ evaluation_model=None,
40
+ include_reason=include_reason,
41
+ async_mode=async_mode,
42
+ strict_mode=strict_mode,
43
+ verbose_mode=verbose_mode
44
+ )
35
45
  self.user = user
36
- self.threshold = 1 if strict_mode else threshold
37
46
  self.model, self.using_native_model = create_judge(model)
38
47
  self.evaluation_model = self.model.get_model_name()
39
- self.include_reason = include_reason
40
- self.async_mode = async_mode
41
- self.strict_mode = strict_mode
42
- self.verbose_mode = verbose_mode
43
48
 
44
49
  def score_example(
45
50
  self,
judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/faithfulness_scorer.py CHANGED
@@ -3,7 +3,7 @@ Code for the local implementation of the Faithfulness metric.
3
3
  """
4
4
  from typing import List, Optional, Union
5
5
 
6
-
6
+ from judgeval.constants import APIScorer
7
7
  from judgeval.data import (
8
8
  Example,
9
9
  ExampleParams
@@ -47,14 +47,19 @@ class FaithfulnessScorer(JudgevalScorer):
47
47
  verbose_mode: bool = False,
48
48
  user: Optional[str] = None
49
49
  ):
50
- self.threshold = 1 if strict_mode else threshold
50
+ super().__init__(
51
+ score_type=APIScorer.FAITHFULNESS,
52
+ threshold=1 if strict_mode else threshold,
53
+ evaluation_model=None,
54
+ include_reason=include_reason,
55
+ async_mode=async_mode,
56
+ strict_mode=strict_mode,
57
+ verbose_mode=verbose_mode
58
+ )
59
+ self.user = user
51
60
  self.model, self.using_native_model = create_judge(model)
52
61
  self.using_native_model = True # NOTE: SETTING THIS FOR LITELLM and TOGETHER usage
53
62
  self.evaluation_model = self.model.get_model_name()
54
- self.include_reason = include_reason
55
- self.async_mode = async_mode
56
- self.strict_mode = strict_mode
57
- self.verbose_mode = verbose_mode
58
63
 
59
64
  def score_example(
60
65
  self,
judgeval/scorers/judgeval_scorers/local_implementations/hallucination/hallucination_scorer.py CHANGED
@@ -20,6 +20,7 @@ Hallucination is measuring the fraction of contexts that agree with output (do n
20
20
 
21
21
  from typing import Optional, Union, List
22
22
 
23
+ from judgeval.constants import APIScorer
23
24
  from judgeval.scorers.utils import (get_or_create_event_loop,
24
25
  scorer_progress_meter,
25
26
  create_verbose_logs,
@@ -50,13 +51,17 @@ class HallucinationScorer(JudgevalScorer):
50
51
  strict_mode: bool = False,
51
52
  verbose_mode: bool = False,
52
53
  ):
53
- self.threshold = 1 if strict_mode else threshold
54
+ super().__init__(
55
+ score_type=APIScorer.HALLUCINATION,
56
+ threshold=1 if strict_mode else threshold,
57
+ evaluation_model=None,
58
+ include_reason=include_reason,
59
+ async_mode=async_mode,
60
+ strict_mode=strict_mode,
61
+ verbose_mode=verbose_mode
62
+ )
54
63
  self.model, self.using_native_model = create_judge(model)
55
64
  self.evaluation_model = self.model.get_model_name()
56
- self.include_reason = include_reason
57
- self.async_mode = async_mode
58
- self.strict_mode = strict_mode
59
- self.verbose_mode = verbose_mode
60
65
 
61
66
  def score_example(
62
67
  self,
judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/__init__.py ADDED
@@ -0,0 +1,5 @@
1
+ from judgeval.scorers.judgeval_scorers.local_implementations.json_correctness.json_correctness_scorer import JsonCorrectnessScorer
2
+
3
+ __all__ = [
4
+ "JsonCorrectnessScorer",
5
+ ]
judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/json_correctness_scorer.py CHANGED
@@ -1,7 +1,9 @@
1
1
  from typing import List, Optional, Union, Any
2
2
  from pydantic import BaseModel, ValidationError, create_model
3
3
 
4
+ from judgeval.constants import APIScorer
4
5
  from judgeval.judges import JudgevalJudge
6
+ from judgeval.judges.utils import create_judge
5
7
  from judgeval.scorers.utils import (get_or_create_event_loop,
6
8
  scorer_progress_meter,
7
9
  create_verbose_logs,
@@ -30,13 +32,18 @@ class JsonCorrectnessScorer(JudgevalScorer):
30
32
  verbose_mode: bool = False,
31
33
  user: Optional[str] = None
32
34
  ):
33
- self.score_type = "json_correctness"
34
- self.model = model
35
- self.threshold = threshold
36
- self.async_mode = async_mode
37
- self.strict_mode = strict_mode
38
- self.verbose_mode = verbose_mode
35
+ super().__init__(
36
+ score_type=APIScorer.JSON_CORRECTNESS,
37
+ threshold=1 if strict_mode else threshold,
38
+ evaluation_model=None,
39
+ include_reason=False,
40
+ async_mode=async_mode,
41
+ strict_mode=strict_mode,
42
+ verbose_mode=verbose_mode
43
+ )
39
44
  self.user = user
45
+ self.model, self.using_native_model = create_judge(model)
46
+ self.evaluation_model = self.model.get_model_name()
40
47
 
41
48
  if isinstance(json_schema, dict):
42
49
  # Convert to BaseModel
judgeval/scorers/judgeval_scorers/local_implementations/summarization/summarization_scorer.py CHANGED
@@ -1,6 +1,7 @@
1
1
  from typing import List, Optional, Union
2
2
  import asyncio
3
3
 
4
+ from judgeval.constants import APIScorer
4
5
  from judgeval.scorers.utils import (get_or_create_event_loop,
5
6
  scorer_progress_meter,
6
7
  create_verbose_logs,
@@ -36,7 +37,15 @@ class SummarizationScorer(JudgevalScorer):
36
37
  strict_mode: bool = False,
37
38
  verbose_mode: bool = False,
38
39
  ):
39
- self.threshold = 1 if strict_mode else threshold
40
+ super().__init__(
41
+ score_type=APIScorer.SUMMARIZATION,
42
+ threshold=1 if strict_mode else threshold,
43
+ evaluation_model=None,
44
+ include_reason=include_reason,
45
+ async_mode=async_mode,
46
+ strict_mode=strict_mode,
47
+ verbose_mode=verbose_mode
48
+ )
40
49
  self.model, self.using_native_model = create_judge(model)
41
50
  self.evaluation_model = self.model.get_model_name()
42
51
 
judgeval/scorers/judgeval_scorers/local_implementations/tool_correctness/tool_correctness_scorer.py CHANGED
@@ -1,5 +1,6 @@
1
1
  from typing import List, Union
2
2
 
3
+ from judgeval.constants import APIScorer
3
4
  from judgeval.scorers.utils import (
4
5
  scorer_progress_meter,
5
6
  create_verbose_logs,
@@ -55,10 +56,15 @@ class ToolCorrectnessScorer(JudgevalScorer):
55
56
  should_exact_match: bool = False,
56
57
  should_consider_ordering: bool = False,
57
58
  ):
58
- self.threshold = 1 if strict_mode else threshold
59
- self.include_reason = include_reason
60
- self.strict_mode = strict_mode
61
- self.verbose_mode = verbose_mode
59
+ super().__init__(
60
+ score_type=APIScorer.TOOL_CORRECTNESS,
61
+ threshold=1 if strict_mode else threshold,
62
+ evaluation_model=None,
63
+ include_reason=include_reason,
64
+ async_mode=False,
65
+ strict_mode=strict_mode,
66
+ verbose_mode=verbose_mode
67
+ )
62
68
  self.should_exact_match = should_exact_match
63
69
  self.should_consider_ordering = should_consider_ordering
64
70
 
{judgeval-0.0.6.dist-info → judgeval-0.0.8.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: judgeval
3
- Version: 0.0.6
3
+ Version: 0.0.8
4
4
  Summary: Judgeval Package
5
5
  Project-URL: Homepage, https://github.com/JudgmentLabs/judgeval
6
6
  Project-URL: Issues, https://github.com/JudgmentLabs/judgeval/issues
@@ -14,9 +14,11 @@ Requires-Dist: anthropic
14
14
  Requires-Dist: fastapi
15
15
  Requires-Dist: langfuse==2.50.3
16
16
  Requires-Dist: litellm
17
+ Requires-Dist: nest-asyncio
17
18
  Requires-Dist: openai
18
19
  Requires-Dist: pandas
19
20
  Requires-Dist: patronus
21
+ Requires-Dist: pika
20
22
  Requires-Dist: python-dotenv==1.0.1
21
23
  Requires-Dist: requests
22
24
  Requires-Dist: supabase
{judgeval-0.0.6.dist-info → judgeval-0.0.8.dist-info}/RECORD RENAMED
@@ -2,7 +2,7 @@ judgeval/__init__.py,sha256=xiiG4CkeaOtey4fusCd9CBz0BVqzTIbV-K2EFIU0rUM,283
2
2
  judgeval/clients.py,sha256=Ns5ljrgPPXUMo7fSPJxO12H64lcPyKeQPIVG_RMi2cM,1162
3
3
  judgeval/constants.py,sha256=5O1jWvxMCRyMSWhmkrvPqfBctx42c7kMtgTS7ORVcFw,1965
4
4
  judgeval/evaluation_run.py,sha256=KcIS7mDR_9XEdqYrJXFcrLz5IDMof34HcD5VtjZgV8w,5884
5
- judgeval/judgment_client.py,sha256=8Z4Woiv56qphYqlMI3bNy4rvQItZl_z9vNNd3UdrCes,11241
5
+ judgeval/judgment_client.py,sha256=lVVVDxRQ750nd0wT827dca94YzThNjuFWWJ-BTFW7lg,11367
6
6
  judgeval/run_evaluation.py,sha256=A9jjtWPH2_5W43a1f98R8u-8PuVczoJZNCZIyCoRqi8,18918
7
7
  judgeval/common/__init__.py,sha256=7d24BRxtncpMj3AAJCj8RS7TqgjXmW777HVZH6-3sBs,289
8
8
  judgeval/common/exceptions.py,sha256=U-TxHLn7oVMezsMuoYouNDb2XuS8RCggfntYf5_6u4E,565
@@ -28,7 +28,7 @@ judgeval/scorers/__init__.py,sha256=3rq2VtszrJk9gZ3oAMVd7EGlSugr8aRlHWprMDgQPaQ,
28
28
  judgeval/scorers/api_scorer.py,sha256=88kCWr6IetLFn3ziTPG-lwDWvMhFUC6xfINU1MJBoho,2125
29
29
  judgeval/scorers/base_scorer.py,sha256=mbOReG88fWaqCnC8F0u5QepRlzgVkuOz89KEKYxrmMc,1794
30
30
  judgeval/scorers/exceptions.py,sha256=eGW5CuJgZ5YJBFrE4FHDSF651PO1dKAZ379mJ8gOsfo,178
31
- judgeval/scorers/judgeval_scorer.py,sha256=qpjyj7JZEgxoF8LR3pwkKeebmVC8qlITnKFN4YOUKXc,6165
31
+ judgeval/scorers/judgeval_scorer.py,sha256=14SZ3sBZtGNM3BCegKebkNad9LTs5Tyhs0kD6l3wLAA,6275
32
32
  judgeval/scorers/prompt_scorer.py,sha256=bUv8eZNy1XGVM1gNMt33dgIVX6zj63bGAV6O0o0c7yg,17821
33
33
  judgeval/scorers/score.py,sha256=zJKG21h9Njyj2vS36CAFK2wlbOcHSKgrLgHV5_25KKw,18630
34
34
  judgeval/scorers/utils.py,sha256=dtueaJm8e3Ph3wj1vC-srzadgK_CoIlOefdvMQ-cwK8,6826
@@ -46,33 +46,34 @@ judgeval/scorers/judgeval_scorers/api_scorers/summarization.py,sha256=-E3oxYbI0D
46
46
  judgeval/scorers/judgeval_scorers/api_scorers/tool_correctness.py,sha256=17ppPXm962ew67GU5m0npzbPu3CuhgdKY_KmfPvKfu4,457
47
47
  judgeval/scorers/judgeval_scorers/local_implementations/__init__.py,sha256=ZDbmYHwIbPD75Gj9JKtEWnpBdSVGGRmbn1_IOR6GR-c,1627
48
48
  judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/__init__.py,sha256=cxxUEspgoIdSzJbwIIioamC0-xDqhYVfYAWxaYF-D_Y,177
49
- judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/answer_correctness_scorer.py,sha256=ZjLw3Usx3SsSRXGXLItNL_IEWo_UV8dxhc2mS9j-nGM,10073
49
+ judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/answer_correctness_scorer.py,sha256=PDThn6SzqxgMXT7BpQs2TEBOsgfD5fi6fnKk31qaCTo,10227
50
50
  judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/prompts.py,sha256=5B_G7PPEsfLq6cwWkKWcLuy2k_5RgoOzsW3wOZLIeMk,6703
51
51
  judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/__init__.py,sha256=r6yae5iaWtlBL_cP8I-1SuhS9dulsy1e7W9Rcz82v6E,169
52
- judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/answer_relevancy_scorer.py,sha256=3T3pDxJde6M8RxsPLXvQA16Dpo-sLECEnMCe7rpvNcY,10536
52
+ judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/answer_relevancy_scorer.py,sha256=QG-oxa6-c74VzTuni17RQ9aeT0t1lCuxQXDMznqX8rc,10714
53
53
  judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/prompts.py,sha256=GfbKv595s1a0dB1No_kDsap6gfcr6dYRGiXx0PDb89k,6557
54
54
  judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/__init__.py,sha256=J6tc-T60AVOEaNVuoVU0XIG6dvQri99Q0tnX_Tm-0vc,108
55
- judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/contextual_precision_scorer.py,sha256=5EYjUusMyDfiqatg8-_OJg8IDax-8Ib6aI1sQgi-6JA,9493
55
+ judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/contextual_precision_scorer.py,sha256=tRgRyjGpc4Pe3nQ1c-5NeNYFvbulL7YEnoRa9zLp1gc,9649
56
56
  judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/prompts.py,sha256=gddK6BQAFcW04vAad81kxIXCHJQp8CbCqMwudWKy7aM,4892
57
57
  judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/__init__.py,sha256=4kjfqD_95muHZFo75S8_fbTcC1DI1onNIfMmr8gMZaI,99
58
- judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/contextual_recall_scorer.py,sha256=u8sknD9IsPfU7iF4725w5OmFKe1JEZbOYwsLcAy4m3E,9107
58
+ judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/contextual_recall_scorer.py,sha256=hwAv_x3XwGDnSW3a75CTCgIW6eVg8ymdjDdJQvw5p0Y,9260
59
59
  judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/prompts.py,sha256=boVq6IM7Iambc1ky_JJQ4ejnYoQQtYreG0SjO4iMyFU,6558
60
60
  judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/__init__.py,sha256=JPCvrekKLbl_xdD49evhtiFIVocuegCpCBkn1auzTSE,184
61
- judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/contextual_relevancy_scorer.py,sha256=NCGFLrdkpEK_LPVQC21qY-0pEOrsdVC0RRcNn9IdREE,8759
61
+ judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/contextual_relevancy_scorer.py,sha256=BtVgE7z-9PHfFRcvn96aEG5mXVcWBweVyty934hZdiU,8915
62
62
  judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/prompts.py,sha256=6EHBfxWvhur9z14l8zCw5Z4Hb2uRo9Yv7qIhTRT7-aM,4591
63
63
  judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/__init__.py,sha256=NbkSqPwxgF4T8KsvuIWhVyRwdOlo7mNHMFuRStTFnvk,154
64
- judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/faithfulness_scorer.py,sha256=HdpxzQVYs79AdoNWmInS6yNYwPdwgqN23OHSzo1e9_4,11169
64
+ judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/faithfulness_scorer.py,sha256=4XqdcdgHg3evrg-IQwXmUHEyee1lZUjXRNEiQSvdpmQ,11341
65
65
  judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/prompts.py,sha256=oxmCsouh5ExUMmlSuCDolpYR2y9c-yKth6PHrdsCH_g,11387
66
66
  judgeval/scorers/judgeval_scorers/local_implementations/hallucination/__init__.py,sha256=fZk3UQxI9Nljf5qjCRLRkF0D-AERFHElI9cC83_cgV8,158
67
- judgeval/scorers/judgeval_scorers/local_implementations/hallucination/hallucination_scorer.py,sha256=ud-P20erpiLR-i-ycma7Bg8M_mxJ2yQliXPXr-Iwq3M,9521
67
+ judgeval/scorers/judgeval_scorers/local_implementations/hallucination/hallucination_scorer.py,sha256=orCrEe1IH4NE7m-AkKMX0EHbysTuAwIqfohcQaU7XxQ,9670
68
68
  judgeval/scorers/judgeval_scorers/local_implementations/hallucination/prompts.py,sha256=BkEu7Q_jIVdcdZSq37tMjitZFzACd8-iBTDDXfGbZig,4346
69
- judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/json_correctness_scorer.py,sha256=eYqHTWiw0NOPHueswknmpdxrmrmSm6Jadq56Ncmv9B0,4218
69
+ judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/__init__.py,sha256=xQDw7o9JQ6qajusPnBH0MWBRJ5ct_Ao3pJELXxxVMRo,175
70
+ judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/json_correctness_scorer.py,sha256=WxIIK_sgHMQ3aLGvkzvYpcmUm6r62gvrAELimMLw3iM,4529
70
71
  judgeval/scorers/judgeval_scorers/local_implementations/summarization/__init__.py,sha256=mv6-XeLSV5yj1H98YYV2iTYVd88zKftZJP42Lgl6R80,89
71
72
  judgeval/scorers/judgeval_scorers/local_implementations/summarization/prompts.py,sha256=6GnRz2h-6Fwt4sl__0RgQOyo3n3iDO4MNuHWxdu-rrM,10242
72
- judgeval/scorers/judgeval_scorers/local_implementations/summarization/summarization_scorer.py,sha256=3FMn7EhM5IxNwJLGTcpeHODaOPJefMHW6rRizmlA93U,20775
73
+ judgeval/scorers/judgeval_scorers/local_implementations/summarization/summarization_scorer.py,sha256=CBuE6oCxMzTdJoXFt_YPWBte88kedEQ9t3g52ZRztGY,21086
73
74
  judgeval/scorers/judgeval_scorers/local_implementations/tool_correctness/__init__.py,sha256=JUB3TMqS1OHr6PqpIGqkyiBNbyfUaw7lZuUATjU3_ek,168
74
- judgeval/scorers/judgeval_scorers/local_implementations/tool_correctness/tool_correctness_scorer.py,sha256=oxhVDR3Pb55Kxp9KsvmuvHWKtMiV1BQRG6yaXEr5Bp8,5309
75
- judgeval-0.0.6.dist-info/METADATA,sha256=2FbgDSASPozNG1ENnqljY9sptDu2omTYhRkCeVD3lQQ,1156
76
- judgeval-0.0.6.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
77
- judgeval-0.0.6.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
78
- judgeval-0.0.6.dist-info/RECORD,,
75
+ judgeval/scorers/judgeval_scorers/local_implementations/tool_correctness/tool_correctness_scorer.py,sha256=CYGRJY5EuyICYzHrmFdLykwXakX8AC7G3Bhj7p6szfY,5493
76
+ judgeval-0.0.8.dist-info/METADATA,sha256=91SMIPO60Q_Ab7yTjL2sKmPgmfl6Bji6_QAzkjaOHlk,1204
77
+ judgeval-0.0.8.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
78
+ judgeval-0.0.8.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
79
+ judgeval-0.0.8.dist-info/RECORD,,