pydantic-evals 0.4.2__py3-none-any.whl → 0.4.4__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.

Potentially problematic release.


This version of pydantic-evals might be problematic. Click here for more details.

@@ -47,7 +47,7 @@ async def generate_dataset(
47
47
  path: Optional path to save the generated dataset. If provided, the dataset will be saved to this location.
48
48
  dataset_type: The type of dataset to generate, with the desired input, output, and metadata types.
49
49
  custom_evaluator_types: Optional sequence of custom evaluator classes to include in the schema.
50
- model: The PydanticAI model to use for generation. Defaults to 'gpt-4o'.
50
+ model: The Pydantic AI model to use for generation. Defaults to 'gpt-4o'.
51
51
  n_examples: Number of examples to generate. Defaults to 3.
52
52
  extra_instructions: Optional additional instructions to provide to the LLM.
53
53
 
@@ -59,7 +59,7 @@ async def generate_dataset(
59
59
  """
60
60
  output_schema = dataset_type.model_json_schema_with_evaluators(custom_evaluator_types)
61
61
 
62
- # TODO(DavidM): Update this once we add better response_format and/or ResultTool support to PydanticAI
62
+ # TODO(DavidM): Update this once we add better response_format and/or ResultTool support to Pydantic AI
63
63
  agent = Agent(
64
64
  model,
65
65
  system_prompt=(
@@ -1,12 +1,12 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: pydantic-evals
3
- Version: 0.4.2
3
+ Version: 0.4.4
4
4
  Summary: Framework for evaluating stochastic code execution, especially code making use of LLMs
5
5
  Project-URL: Homepage, https://ai.pydantic.dev/evals
6
6
  Project-URL: Source, https://github.com/pydantic/pydantic-ai
7
7
  Project-URL: Documentation, https://ai.pydantic.dev/evals
8
8
  Project-URL: Changelog, https://github.com/pydantic/pydantic-ai/releases
9
- Author-email: David Montague <david@pydantic.dev>
9
+ Author-email: Samuel Colvin <samuel@pydantic.dev>, Marcelo Trylesinski <marcelotryle@gmail.com>, David Montague <david@pydantic.dev>, Alex Hall <alex@pydantic.dev>, Douwe Maan <douwe@pydantic.dev>
10
10
  License-Expression: MIT
11
11
  License-File: LICENSE
12
12
  Classifier: Development Status :: 4 - Beta
@@ -32,7 +32,7 @@ Requires-Python: >=3.9
32
32
  Requires-Dist: anyio>=0
33
33
  Requires-Dist: eval-type-backport>=0; python_version < '3.11'
34
34
  Requires-Dist: logfire-api>=1.2.0
35
- Requires-Dist: pydantic-ai-slim==0.4.2
35
+ Requires-Dist: pydantic-ai-slim==0.4.4
36
36
  Requires-Dist: pydantic>=2.10
37
37
  Requires-Dist: pyyaml>=6.0.2
38
38
  Requires-Dist: rich>=13.9.4
@@ -51,18 +51,18 @@ Description-Content-Type: text/markdown
51
51
  This is a library for evaluating non-deterministic (or "stochastic") functions in Python. It provides a simple,
52
52
  Pythonic interface for defining and running stochastic functions, and analyzing the results of running those functions.
53
53
 
54
- While this library is developed as part of [PydanticAI](https://ai.pydantic.dev), it only uses PydanticAI for a small
54
+ While this library is developed as part of [Pydantic AI](https://ai.pydantic.dev), it only uses Pydantic AI for a small
55
55
  subset of generative functionality internally, and it is designed to be used with arbitrary "stochastic function"
56
- implementations. In particular, it can be used with other (non-PydanticAI) AI libraries, agent frameworks, etc.
56
+ implementations. In particular, it can be used with other (non-Pydantic AI) AI libraries, agent frameworks, etc.
57
57
 
58
- As with PydanticAI, this library prioritizes type safety and use of common Python syntax over esoteric, domain-specific
58
+ As with Pydantic AI, this library prioritizes type safety and use of common Python syntax over esoteric, domain-specific
59
59
  use of Python syntax.
60
60
 
61
61
  Full documentation is available at [ai.pydantic.dev/evals](https://ai.pydantic.dev/evals).
62
62
 
63
63
  ## Example
64
64
 
65
- While you'd typically use Pydantic Evals with more complex functions (such as PydanticAI agents or graphs), here's a
65
+ While you'd typically use Pydantic Evals with more complex functions (such as Pydantic AI agents or graphs), here's a
66
66
  quick example that evaluates a simple function against a test case using both custom and built-in evaluators:
67
67
 
68
68
  ```python
@@ -110,7 +110,7 @@ report.print(include_input=True, include_output=True)
110
110
  """
111
111
  ```
112
112
 
113
- Using the library with more complex functions, such as PydanticAI agents, is similar — all you need to do is define a
113
+ Using the library with more complex functions, such as Pydantic AI agents, is similar — all you need to do is define a
114
114
  task function wrapping the function you want to evaluate, with a signature that matches the inputs and outputs of your
115
115
  test cases.
116
116
 
@@ -1,7 +1,7 @@
1
1
  pydantic_evals/__init__.py,sha256=OKRbfhdc8UZPzrPJMZUQwvzIxLhXmEZxz1ZuD921fy4,839
2
2
  pydantic_evals/_utils.py,sha256=PfhmPbdQp-q90s568LuG45zDDXxgO13BEz8MQJK8qw4,2922
3
3
  pydantic_evals/dataset.py,sha256=SY0k2htYG0d0KRRem3pnQdN7rPztJ_TCFnCb0zkXbCk,46477
4
- pydantic_evals/generation.py,sha256=-w-4-zpJuW8mLj5ed60LUYm--b-2G42p-UDuPhOQgRE,3492
4
+ pydantic_evals/generation.py,sha256=Yd1rfbsDjjBBHDk-1KDu48hlITjM2-74rTnPBD_sqbA,3494
5
5
  pydantic_evals/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
6
6
  pydantic_evals/evaluators/__init__.py,sha256=uj110viFiDvqrIcuDcWexk_uBgJqhKMGPHT2YvDb7LA,624
7
7
  pydantic_evals/evaluators/_run_evaluator.py,sha256=Dsnqxno7CrcKWYcnkLuwvPKWQGDRBmbBTwwstcmc0ak,2448
@@ -17,7 +17,7 @@ pydantic_evals/otel/_errors.py,sha256=aW1414eTofpA7R_DUgOeT-gj7YA6OXmm8Y4oYeFukD
17
17
  pydantic_evals/otel/span_tree.py,sha256=LV5Hsyo4riJzevHyBz8wxP82S-ry5zeKYi9bKWjGCS8,23057
18
18
  pydantic_evals/reporting/__init__.py,sha256=k_3tteqXGh0yGvgpN68gB0CjG9wzrakzDTve2GHend4,42148
19
19
  pydantic_evals/reporting/render_numbers.py,sha256=8SKlK3etbD7HnSWWHCE993ceCNLZCepVQ-SsqUIhyxk,6916
20
- pydantic_evals-0.4.2.dist-info/METADATA,sha256=P5kQ1Zg4iax0dCQB2ZVmbz2YDCpfo6M9993QzdlT0hQ,7785
21
- pydantic_evals-0.4.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
22
- pydantic_evals-0.4.2.dist-info/licenses/LICENSE,sha256=vA6Jc482lEyBBuGUfD1pYx-cM7jxvLYOxPidZ30t_PQ,1100
23
- pydantic_evals-0.4.2.dist-info/RECORD,,
20
+ pydantic_evals-0.4.4.dist-info/METADATA,sha256=DyDqmxe9d_3gC3QhRuUffzRb1O5Ul9bT_xRNb9_9Rr4,7938
21
+ pydantic_evals-0.4.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
22
+ pydantic_evals-0.4.4.dist-info/licenses/LICENSE,sha256=vA6Jc482lEyBBuGUfD1pYx-cM7jxvLYOxPidZ30t_PQ,1100
23
+ pydantic_evals-0.4.4.dist-info/RECORD,,