eval-ai-library 0.2.0__tar.gz → 0.2.2__tar.gz
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.
Potentially problematic release.
This version of eval-ai-library might be problematic. Click here for more details.
- {eval_ai_library-0.2.0/eval_ai_library.egg-info → eval_ai_library-0.2.2}/PKG-INFO +27 -1
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2/eval_ai_library.egg-info}/PKG-INFO +27 -1
- eval_ai_library-0.2.2/eval_ai_library.egg-info/requires.txt +45 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/__init__.py +1 -1
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/pyproject.toml +30 -2
- eval_ai_library-0.2.0/eval_ai_library.egg-info/requires.txt +0 -17
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/LICENSE +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/MANIFEST.in +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/README.md +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_ai_library.egg-info/SOURCES.txt +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_ai_library.egg-info/dependency_links.txt +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_ai_library.egg-info/top_level.txt +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/agent_metrics/__init__.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/agent_metrics/knowledge_retention_metric/knowledge_retention.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/agent_metrics/role_adherence_metric/role_adherence.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/agent_metrics/task_success_metric/task_success_rate.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/agent_metrics/tools_correctness_metric/tool_correctness.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/datagenerator/datagenerator.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/datagenerator/document_loader.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/datagenerator/prompts.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/evaluate.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/evaluation_schema.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/llm_client.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metric_pattern.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/__init__.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/answer_precision_metric/answer_precision.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/answer_relevancy_metric/answer_relevancy.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/bias_metric/bias.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/contextual_precision_metric/contextual_precision.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/contextual_recall_metric/contextual_recall.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/contextual_relevancy_metric/contextual_relevancy.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/custom_metric/custom_eval.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/faithfulness_metric/faithfulness.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/geval/geval.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/restricted_refusal_metric/restricted_refusal.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/toxicity_metric/toxicity.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/price.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/py.typed +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/testcases_schema.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/utils.py +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/setup.cfg +0 -0
- {eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/setup.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: eval-ai-library
|
|
3
|
-
Version: 0.2.
|
|
3
|
+
Version: 0.2.2
|
|
4
4
|
Summary: Comprehensive AI Model Evaluation Framework with support for multiple LLM providers
|
|
5
5
|
Author-email: Aleksandr Meshkov <alekslynx90@gmail.com>
|
|
6
6
|
License: MIT
|
|
@@ -38,6 +38,32 @@ Requires-Dist: isort>=5.12.0; extra == "dev"
|
|
|
38
38
|
Provides-Extra: docs
|
|
39
39
|
Requires-Dist: sphinx>=6.0.0; extra == "docs"
|
|
40
40
|
Requires-Dist: sphinx-rtd-theme>=1.2.0; extra == "docs"
|
|
41
|
+
Provides-Extra: data-generation
|
|
42
|
+
Requires-Dist: langchain>=0.1.0; extra == "data-generation"
|
|
43
|
+
Requires-Dist: langchain-community>=0.0.10; extra == "data-generation"
|
|
44
|
+
Requires-Dist: langchain-core>=0.1.0; extra == "data-generation"
|
|
45
|
+
Requires-Dist: pypdf2>=3.0.0; extra == "data-generation"
|
|
46
|
+
Requires-Dist: python-docx>=0.8.11; extra == "data-generation"
|
|
47
|
+
Requires-Dist: openpyxl>=3.1.0; extra == "data-generation"
|
|
48
|
+
Requires-Dist: pillow>=10.0.0; extra == "data-generation"
|
|
49
|
+
Requires-Dist: pytesseract>=0.3.10; extra == "data-generation"
|
|
50
|
+
Provides-Extra: all
|
|
51
|
+
Requires-Dist: pytest>=7.0.0; extra == "all"
|
|
52
|
+
Requires-Dist: pytest-asyncio>=0.21.0; extra == "all"
|
|
53
|
+
Requires-Dist: black>=23.0.0; extra == "all"
|
|
54
|
+
Requires-Dist: flake8>=6.0.0; extra == "all"
|
|
55
|
+
Requires-Dist: mypy>=1.0.0; extra == "all"
|
|
56
|
+
Requires-Dist: isort>=5.12.0; extra == "all"
|
|
57
|
+
Requires-Dist: sphinx>=6.0.0; extra == "all"
|
|
58
|
+
Requires-Dist: sphinx-rtd-theme>=1.2.0; extra == "all"
|
|
59
|
+
Requires-Dist: langchain>=0.1.0; extra == "all"
|
|
60
|
+
Requires-Dist: langchain-community>=0.0.10; extra == "all"
|
|
61
|
+
Requires-Dist: langchain-core>=0.1.0; extra == "all"
|
|
62
|
+
Requires-Dist: pypdf2>=3.0.0; extra == "all"
|
|
63
|
+
Requires-Dist: python-docx>=0.8.11; extra == "all"
|
|
64
|
+
Requires-Dist: openpyxl>=3.1.0; extra == "all"
|
|
65
|
+
Requires-Dist: pillow>=10.0.0; extra == "all"
|
|
66
|
+
Requires-Dist: pytesseract>=0.3.10; extra == "all"
|
|
41
67
|
Dynamic: license-file
|
|
42
68
|
|
|
43
69
|
# Eval AI Library
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: eval-ai-library
|
|
3
|
-
Version: 0.2.
|
|
3
|
+
Version: 0.2.2
|
|
4
4
|
Summary: Comprehensive AI Model Evaluation Framework with support for multiple LLM providers
|
|
5
5
|
Author-email: Aleksandr Meshkov <alekslynx90@gmail.com>
|
|
6
6
|
License: MIT
|
|
@@ -38,6 +38,32 @@ Requires-Dist: isort>=5.12.0; extra == "dev"
|
|
|
38
38
|
Provides-Extra: docs
|
|
39
39
|
Requires-Dist: sphinx>=6.0.0; extra == "docs"
|
|
40
40
|
Requires-Dist: sphinx-rtd-theme>=1.2.0; extra == "docs"
|
|
41
|
+
Provides-Extra: data-generation
|
|
42
|
+
Requires-Dist: langchain>=0.1.0; extra == "data-generation"
|
|
43
|
+
Requires-Dist: langchain-community>=0.0.10; extra == "data-generation"
|
|
44
|
+
Requires-Dist: langchain-core>=0.1.0; extra == "data-generation"
|
|
45
|
+
Requires-Dist: pypdf2>=3.0.0; extra == "data-generation"
|
|
46
|
+
Requires-Dist: python-docx>=0.8.11; extra == "data-generation"
|
|
47
|
+
Requires-Dist: openpyxl>=3.1.0; extra == "data-generation"
|
|
48
|
+
Requires-Dist: pillow>=10.0.0; extra == "data-generation"
|
|
49
|
+
Requires-Dist: pytesseract>=0.3.10; extra == "data-generation"
|
|
50
|
+
Provides-Extra: all
|
|
51
|
+
Requires-Dist: pytest>=7.0.0; extra == "all"
|
|
52
|
+
Requires-Dist: pytest-asyncio>=0.21.0; extra == "all"
|
|
53
|
+
Requires-Dist: black>=23.0.0; extra == "all"
|
|
54
|
+
Requires-Dist: flake8>=6.0.0; extra == "all"
|
|
55
|
+
Requires-Dist: mypy>=1.0.0; extra == "all"
|
|
56
|
+
Requires-Dist: isort>=5.12.0; extra == "all"
|
|
57
|
+
Requires-Dist: sphinx>=6.0.0; extra == "all"
|
|
58
|
+
Requires-Dist: sphinx-rtd-theme>=1.2.0; extra == "all"
|
|
59
|
+
Requires-Dist: langchain>=0.1.0; extra == "all"
|
|
60
|
+
Requires-Dist: langchain-community>=0.0.10; extra == "all"
|
|
61
|
+
Requires-Dist: langchain-core>=0.1.0; extra == "all"
|
|
62
|
+
Requires-Dist: pypdf2>=3.0.0; extra == "all"
|
|
63
|
+
Requires-Dist: python-docx>=0.8.11; extra == "all"
|
|
64
|
+
Requires-Dist: openpyxl>=3.1.0; extra == "all"
|
|
65
|
+
Requires-Dist: pillow>=10.0.0; extra == "all"
|
|
66
|
+
Requires-Dist: pytesseract>=0.3.10; extra == "all"
|
|
41
67
|
Dynamic: license-file
|
|
42
68
|
|
|
43
69
|
# Eval AI Library
|
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
openai>=1.0.0
|
|
2
|
+
anthropic>=0.18.0
|
|
3
|
+
google-genai>=0.2.0
|
|
4
|
+
pydantic>=2.0.0
|
|
5
|
+
numpy>=1.24.0
|
|
6
|
+
|
|
7
|
+
[all]
|
|
8
|
+
pytest>=7.0.0
|
|
9
|
+
pytest-asyncio>=0.21.0
|
|
10
|
+
black>=23.0.0
|
|
11
|
+
flake8>=6.0.0
|
|
12
|
+
mypy>=1.0.0
|
|
13
|
+
isort>=5.12.0
|
|
14
|
+
sphinx>=6.0.0
|
|
15
|
+
sphinx-rtd-theme>=1.2.0
|
|
16
|
+
langchain>=0.1.0
|
|
17
|
+
langchain-community>=0.0.10
|
|
18
|
+
langchain-core>=0.1.0
|
|
19
|
+
pypdf2>=3.0.0
|
|
20
|
+
python-docx>=0.8.11
|
|
21
|
+
openpyxl>=3.1.0
|
|
22
|
+
pillow>=10.0.0
|
|
23
|
+
pytesseract>=0.3.10
|
|
24
|
+
|
|
25
|
+
[data-generation]
|
|
26
|
+
langchain>=0.1.0
|
|
27
|
+
langchain-community>=0.0.10
|
|
28
|
+
langchain-core>=0.1.0
|
|
29
|
+
pypdf2>=3.0.0
|
|
30
|
+
python-docx>=0.8.11
|
|
31
|
+
openpyxl>=3.1.0
|
|
32
|
+
pillow>=10.0.0
|
|
33
|
+
pytesseract>=0.3.10
|
|
34
|
+
|
|
35
|
+
[dev]
|
|
36
|
+
pytest>=7.0.0
|
|
37
|
+
pytest-asyncio>=0.21.0
|
|
38
|
+
black>=23.0.0
|
|
39
|
+
flake8>=6.0.0
|
|
40
|
+
mypy>=1.0.0
|
|
41
|
+
isort>=5.12.0
|
|
42
|
+
|
|
43
|
+
[docs]
|
|
44
|
+
sphinx>=6.0.0
|
|
45
|
+
sphinx-rtd-theme>=1.2.0
|
|
@@ -10,7 +10,7 @@ __author__ = "Aleksandr Meskov"
|
|
|
10
10
|
|
|
11
11
|
# Core evaluation functions
|
|
12
12
|
from eval_lib.evaluate import evaluate, evaluate_conversations
|
|
13
|
-
from eval_lib.utils import score_agg
|
|
13
|
+
from eval_lib.utils import score_agg
|
|
14
14
|
|
|
15
15
|
# Test case schemas
|
|
16
16
|
from eval_lib.testcases_schema import (
|
|
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "eval-ai-library"
|
|
7
|
-
version = "0.2.
|
|
7
|
+
version = "0.2.2"
|
|
8
8
|
description = "Comprehensive AI Model Evaluation Framework with support for multiple LLM providers"
|
|
9
9
|
readme = "README.md"
|
|
10
10
|
authors = [
|
|
@@ -47,6 +47,34 @@ docs = [
|
|
|
47
47
|
"sphinx>=6.0.0",
|
|
48
48
|
"sphinx-rtd-theme>=1.2.0",
|
|
49
49
|
]
|
|
50
|
+
data-generation = [
|
|
51
|
+
"langchain>=0.1.0",
|
|
52
|
+
"langchain-community>=0.0.10",
|
|
53
|
+
"langchain-core>=0.1.0",
|
|
54
|
+
"pypdf2>=3.0.0",
|
|
55
|
+
"python-docx>=0.8.11",
|
|
56
|
+
"openpyxl>=3.1.0",
|
|
57
|
+
"pillow>=10.0.0",
|
|
58
|
+
"pytesseract>=0.3.10",
|
|
59
|
+
]
|
|
60
|
+
all = [
|
|
61
|
+
"pytest>=7.0.0",
|
|
62
|
+
"pytest-asyncio>=0.21.0",
|
|
63
|
+
"black>=23.0.0",
|
|
64
|
+
"flake8>=6.0.0",
|
|
65
|
+
"mypy>=1.0.0",
|
|
66
|
+
"isort>=5.12.0",
|
|
67
|
+
"sphinx>=6.0.0",
|
|
68
|
+
"sphinx-rtd-theme>=1.2.0",
|
|
69
|
+
"langchain>=0.1.0",
|
|
70
|
+
"langchain-community>=0.0.10",
|
|
71
|
+
"langchain-core>=0.1.0",
|
|
72
|
+
"pypdf2>=3.0.0",
|
|
73
|
+
"python-docx>=0.8.11",
|
|
74
|
+
"openpyxl>=3.1.0",
|
|
75
|
+
"pillow>=10.0.0",
|
|
76
|
+
"pytesseract>=0.3.10",
|
|
77
|
+
]
|
|
50
78
|
|
|
51
79
|
[project.urls]
|
|
52
80
|
Homepage = "https://github.com/meshkovQA/Eval-ai-library"
|
|
@@ -99,4 +127,4 @@ asyncio_mode = "auto"
|
|
|
99
127
|
testpaths = ["tests"]
|
|
100
128
|
python_files = ["test_*.py"]
|
|
101
129
|
python_classes = ["Test*"]
|
|
102
|
-
python_functions = ["test_*"]
|
|
130
|
+
python_functions = ["test_*"]
|
|
@@ -1,17 +0,0 @@
|
|
|
1
|
-
openai>=1.0.0
|
|
2
|
-
anthropic>=0.18.0
|
|
3
|
-
google-genai>=0.2.0
|
|
4
|
-
pydantic>=2.0.0
|
|
5
|
-
numpy>=1.24.0
|
|
6
|
-
|
|
7
|
-
[dev]
|
|
8
|
-
pytest>=7.0.0
|
|
9
|
-
pytest-asyncio>=0.21.0
|
|
10
|
-
black>=23.0.0
|
|
11
|
-
flake8>=6.0.0
|
|
12
|
-
mypy>=1.0.0
|
|
13
|
-
isort>=5.12.0
|
|
14
|
-
|
|
15
|
-
[docs]
|
|
16
|
-
sphinx>=6.0.0
|
|
17
|
-
sphinx-rtd-theme>=1.2.0
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_ai_library.egg-info/dependency_links.txt
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/custom_metric/custom_eval.py
RENAMED
|
File without changes
|
{eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/faithfulness_metric/faithfulness.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_ai_library-0.2.0 → eval_ai_library-0.2.2}/eval_lib/metrics/toxicity_metric/toxicity.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|