pydantic-ai 1.0.11__tar.gz → 1.0.13__tar.gz

{pydantic_ai-1.0.11 → pydantic_ai-1.0.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pydantic-ai
-Version: 1.0.11
+Version: 1.0.13
 Summary: Agent Framework / shim to use Pydantic with LLMs
 Project-URL: Homepage, https://ai.pydantic.dev
 Project-URL: Source, https://github.com/pydantic/pydantic-ai
@@ -26,13 +26,13 @@ Classifier: Topic :: Internet
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
-Requires-Dist: pydantic-ai-slim[ag-ui,anthropic,bedrock,cli,cohere,evals,google,groq,huggingface,logfire,mcp,mistral,openai,retries,temporal,vertexai]==1.0.11
+Requires-Dist: pydantic-ai-slim[ag-ui,anthropic,bedrock,cli,cohere,evals,google,groq,huggingface,logfire,mcp,mistral,openai,retries,temporal,vertexai]==1.0.13
 Provides-Extra: a2a
 Requires-Dist: fasta2a>=0.4.1; extra == 'a2a'
 Provides-Extra: dbos
-Requires-Dist: pydantic-ai-slim[dbos]==1.0.11; extra == 'dbos'
+Requires-Dist: pydantic-ai-slim[dbos]==1.0.13; extra == 'dbos'
 Provides-Extra: examples
-Requires-Dist: pydantic-ai-examples==1.0.11; extra == 'examples'
+Requires-Dist: pydantic-ai-examples==1.0.13; extra == 'examples'
 Description-Content-Type: text/markdown
 
 <div align="center">

pydantic_ai-1.0.13/tests/assets/dummy.txt

@@ -0,0 +1 @@
+Dummy TXT file

pydantic_ai-1.0.13/tests/cassettes/test_mcp/test_tool_returning_unstructured_dict.yaml

@@ -0,0 +1,520 @@
+interactions:
+- request:
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '3845'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+    method: POST
+    parsed_body:
+      messages:
+      - content: Get me an unstructured dict, respond on one line
+        role: user
+      model: gpt-4o
+      stream: false
+      tool_choice: auto
+      tools:
+      - function:
+          description: "Convert Celsius to Fahrenheit.\n\n    Args:\n        celsius: Temperature in Celsius\n\n    Returns:\n
+            \       Temperature in Fahrenheit\n    "
+          name: celsius_to_fahrenheit
+          parameters:
+            additionalProperties: false
+            properties:
+              celsius:
+                type: number
+            required:
+            - celsius
+            type: object
+          strict: true
+        type: function
+      - function:
+          description: "Get the weather forecast for a location.\n\n    Args:\n        location: The location to get the weather
+            forecast for.\n\n    Returns:\n        The weather forecast for the location.\n    "
+          name: get_weather_forecast
+          parameters:
+            additionalProperties: false
+            properties:
+              location:
+                type: string
+            required:
+            - location
+            type: object
+          strict: true
+        type: function
+      - function:
+          description: ''
+          name: get_image_resource
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_image_resource_link
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_audio_resource
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_audio_resource_link
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_product_name
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_product_name_link
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_image
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_dict
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_unstructured_dict
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_error
+          parameters:
+            additionalProperties: false
+            properties:
+              value:
+                default: false
+                type: boolean
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_none
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_multiple_items
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: "Get the current log level.\n\n    Returns:\n        The current log level.\n    "
+          name: get_log_level
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: "Echo the run context.\n\n    Args:\n        ctx: Context object containing request and session information.\n\n
+            \   Returns:\n        Dictionary with an echo message and the deps.\n    "
+          name: echo_deps
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: Use sampling callback.
+          name: use_sampling
+          parameters:
+            additionalProperties: false
+            properties:
+              foo:
+                type: string
+            required:
+            - foo
+            type: object
+          strict: true
+        type: function
+      - function:
+          description: Use elicitation callback to ask the user a question.
+          name: use_elicitation
+          parameters:
+            additionalProperties: false
+            properties:
+              question:
+                type: string
+            required:
+            - question
+            type: object
+          strict: true
+        type: function
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    headers:
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      connection:
+      - keep-alive
+      content-length:
+      - '1073'
+      content-type:
+      - application/json
+      openai-organization:
+      - pydantic-28gund
+      openai-processing-ms:
+      - '1521'
+      openai-project:
+      - proj_dKobscVY9YJxeEaDJen54e3d
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      transfer-encoding:
+      - chunked
+    parsed_body:
+      choices:
+      - finish_reason: tool_calls
+        index: 0
+        logprobs: null
+        message:
+          annotations: []
+          content: null
+          refusal: null
+          role: assistant
+          tool_calls:
+          - function:
+              arguments: '{}'
+              name: get_unstructured_dict
+            id: call_R0n2R7S9vL2aZOX25T9jahTd
+            type: function
+      created: 1759264706
+      id: chatcmpl-CLbP82ODQMEznhobUKdq6Rjn9Aa12
+      model: gpt-4o-2024-08-06
+      object: chat.completion
+      service_tier: default
+      system_fingerprint: fp_f33640a400
+      usage:
+        completion_tokens: 12
+        completion_tokens_details:
+          accepted_prediction_tokens: 0
+          audio_tokens: 0
+          reasoning_tokens: 0
+          rejected_prediction_tokens: 0
+        prompt_tokens: 343
+        prompt_tokens_details:
+          audio_tokens: 0
+          cached_tokens: 0
+        total_tokens: 355
+    status:
+      code: 200
+      message: OK
+- request:
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '4119'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=tGZk0hevqXH_kU7UScGt.EqwPxg4OTuqy4hBf.hGmwo-1759264708-1.0.1.1-dHK7SUjNTLSpKF9cvNn7RNdg6UBSqsWYbU7k7Dq5oE9NdDkkv4LRlBEYWPjFafQKjfrS_JgwrAIM5Je9qCJeucIatzS2M02wLccvrfU2c6k;
+        _cfuvid=d8Rl.NMqIC4giHLO2QsuslT6sliz_xnT6LK0PLEZEsA-1759264708042-0.0.1.1-604800000
+      host:
+      - api.openai.com
+    method: POST
+    parsed_body:
+      messages:
+      - content: Get me an unstructured dict, respond on one line
+        role: user
+      - content: null
+        role: assistant
+        tool_calls:
+        - function:
+            arguments: '{}'
+            name: get_unstructured_dict
+          id: call_R0n2R7S9vL2aZOX25T9jahTd
+          type: function
+      - content: '{"foo":"bar","baz":123}'
+        role: tool
+        tool_call_id: call_R0n2R7S9vL2aZOX25T9jahTd
+      model: gpt-4o
+      stream: false
+      tool_choice: auto
+      tools:
+      - function:
+          description: "Convert Celsius to Fahrenheit.\n\n    Args:\n        celsius: Temperature in Celsius\n\n    Returns:\n
+            \       Temperature in Fahrenheit\n    "
+          name: celsius_to_fahrenheit
+          parameters:
+            additionalProperties: false
+            properties:
+              celsius:
+                type: number
+            required:
+            - celsius
+            type: object
+          strict: true
+        type: function
+      - function:
+          description: "Get the weather forecast for a location.\n\n    Args:\n        location: The location to get the weather
+            forecast for.\n\n    Returns:\n        The weather forecast for the location.\n    "
+          name: get_weather_forecast
+          parameters:
+            additionalProperties: false
+            properties:
+              location:
+                type: string
+            required:
+            - location
+            type: object
+          strict: true
+        type: function
+      - function:
+          description: ''
+          name: get_image_resource
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_image_resource_link
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_audio_resource
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_audio_resource_link
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_product_name
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_product_name_link
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_image
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_dict
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_unstructured_dict
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_error
+          parameters:
+            additionalProperties: false
+            properties:
+              value:
+                default: false
+                type: boolean
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_none
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: ''
+          name: get_multiple_items
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: "Get the current log level.\n\n    Returns:\n        The current log level.\n    "
+          name: get_log_level
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: "Echo the run context.\n\n    Args:\n        ctx: Context object containing request and session information.\n\n
+            \   Returns:\n        Dictionary with an echo message and the deps.\n    "
+          name: echo_deps
+          parameters:
+            additionalProperties: false
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: Use sampling callback.
+          name: use_sampling
+          parameters:
+            additionalProperties: false
+            properties:
+              foo:
+                type: string
+            required:
+            - foo
+            type: object
+          strict: true
+        type: function
+      - function:
+          description: Use elicitation callback to ask the user a question.
+          name: use_elicitation
+          parameters:
+            additionalProperties: false
+            properties:
+              question:
+                type: string
+            required:
+            - question
+            type: object
+          strict: true
+        type: function
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    headers:
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      connection:
+      - keep-alive
+      content-length:
+      - '833'
+      content-type:
+      - application/json
+      openai-organization:
+      - pydantic-28gund
+      openai-processing-ms:
+      - '318'
+      openai-project:
+      - proj_dKobscVY9YJxeEaDJen54e3d
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      transfer-encoding:
+      - chunked
+    parsed_body:
+      choices:
+      - finish_reason: stop
+        index: 0
+        logprobs: null
+        message:
+          annotations: []
+          content: '{"foo":"bar","baz":123}'
+          refusal: null
+          role: assistant
+      created: 1759264708
+      id: chatcmpl-CLbPAOYN3jPYdvYeD8JNOOXF5N554
+      model: gpt-4o-2024-08-06
+      object: chat.completion
+      service_tier: default
+      system_fingerprint: fp_f33640a400
+      usage:
+        completion_tokens: 10
+        completion_tokens_details:
+          accepted_prediction_tokens: 0
+          audio_tokens: 0
+          reasoning_tokens: 0
+          rejected_prediction_tokens: 0
+        prompt_tokens: 374
+        prompt_tokens_details:
+          audio_tokens: 0
+          cached_tokens: 0
+        total_tokens: 384
+    status:
+      code: 200
+      message: OK
+version: 1

{pydantic_ai-1.0.11 → pydantic_ai-1.0.13}/tests/conftest.py

@@ -23,8 +23,7 @@ from pytest_mock import MockerFixture
 from vcr import VCR, request as vcr_request
 
 import pydantic_ai.models
-from pydantic_ai import Agent
-from pydantic_ai.messages import BinaryContent
+from pydantic_ai import Agent, BinaryContent
 from pydantic_ai.models import Model, cached_async_http_client
 
 __all__ = 'IsDatetime', 'IsFloat', 'IsNow', 'IsStr', 'IsInt', 'IsInstance', 'TestEnv', 'ClientWithHandler', 'try_import'
@@ -339,6 +338,13 @@ def document_content(assets_path: Path) -> BinaryContent:
     return BinaryContent(data=pdf_bytes, media_type='application/pdf')
 
 
+@pytest.fixture(scope='session')
+def text_document_content(assets_path: Path) -> BinaryContent:
+    content = assets_path.joinpath('dummy.txt').read_text()
+    bin_content = BinaryContent(data=content.encode(), media_type='text/plain')
+    return bin_content
+
+
 @pytest.fixture(scope='session')
 def deepseek_api_key() -> str:
     return os.getenv('DEEPSEEK_API_KEY', 'mock-api-key')

{pydantic_ai-1.0.11 → pydantic_ai-1.0.13}/tests/evals/test_dataset.py

@@ -7,6 +7,7 @@ from pathlib import Path
 from typing import Any
 
 import pytest
+import yaml
 from dirty_equals import HasRepr, IsNumber
 from inline_snapshot import snapshot
 from pydantic import BaseModel, TypeAdapter
@@ -106,7 +107,7 @@ def example_cases() -> list[Case[TaskInput, TaskOutput, TaskMetadata]]:
 def example_dataset(
     example_cases: list[Case[TaskInput, TaskOutput, TaskMetadata]],
 ) -> Dataset[TaskInput, TaskOutput, TaskMetadata]:
-    return Dataset[TaskInput, TaskOutput, TaskMetadata](cases=example_cases)
+    return Dataset[TaskInput, TaskOutput, TaskMetadata](name='example', cases=example_cases)
 
 
 @pytest.fixture
@@ -764,6 +765,7 @@ async def test_genai_attribute_collection(example_dataset: Dataset[TaskInput, Ta
                 'gen_ai.usage.input_tokens': 1,
                 'gen_ai.usage.details.special_tokens': 2,
                 'other_attribute': 3,
+                'operation.cost': 1.23,
             },
         ):
             with logfire.span('some other span'):
@@ -779,7 +781,7 @@ async def test_genai_attribute_collection(example_dataset: Dataset[TaskInput, Ta
                 metadata=TaskMetadata(difficulty='easy', category='general'),
                 expected_output=TaskOutput(answer='4', confidence=1.0),
                 output=TaskOutput(answer='answer to What is 2+2?', confidence=1.0),
-                metrics={'requests': 1, 'input_tokens': 1, 'special_tokens': 2},
+                metrics={'cost': 1.23, 'requests': 1, 'input_tokens': 1, 'special_tokens': 2},
                 attributes={},
                 scores={},
                 labels={},
@@ -795,7 +797,7 @@ async def test_genai_attribute_collection(example_dataset: Dataset[TaskInput, Ta
                 metadata=TaskMetadata(difficulty='medium', category='geography'),
                 expected_output=TaskOutput(answer='Paris', confidence=1.0),
                 output=TaskOutput(answer='answer to What is the capital of France?', confidence=1.0),
-                metrics={'requests': 1, 'input_tokens': 1, 'special_tokens': 2},
+                metrics={'cost': 1.23, 'requests': 1, 'input_tokens': 1, 'special_tokens': 2},
                 attributes={},
                 scores={},
                 labels={},
@@ -819,10 +821,29 @@ async def test_serialization_to_yaml(example_dataset: Dataset[TaskInput, TaskOut
     # Test loading back
     loaded_dataset = Dataset[TaskInput, TaskOutput, TaskMetadata].from_file(yaml_path)
     assert len(loaded_dataset.cases) == 2
+    assert loaded_dataset.name == 'example'
     assert loaded_dataset.cases[0].name == 'case1'
     assert loaded_dataset.cases[0].inputs.query == 'What is 2+2?'
 
 
+async def test_deserializing_without_name(
+    example_dataset: Dataset[TaskInput, TaskOutput, TaskMetadata], tmp_path: Path
+):
+    """Test serializing a dataset to YAML."""
+    # Save the dataset
+    yaml_path = tmp_path / 'test_cases.yaml'
+    example_dataset.to_file(yaml_path)
+
+    # Rewrite the file _without_ a name to test deserializing a name-less file
+    obj = yaml.safe_load(yaml_path.read_text())
+    obj.pop('name', None)
+    yaml_path.write_text(yaml.dump(obj))
+
+    # Test loading results in the name coming from the filename stem
+    loaded_dataset = Dataset[TaskInput, TaskOutput, TaskMetadata].from_file(yaml_path)
+    assert loaded_dataset.name == 'test_cases'
+
+
 async def test_serialization_to_json(example_dataset: Dataset[TaskInput, TaskOutput, TaskMetadata], tmp_path: Path):
     """Test serializing a dataset to JSON."""
     json_path = tmp_path / 'test_cases.json'
@@ -854,6 +875,7 @@ def test_serialization_errors(tmp_path: Path):
 async def test_from_text():
     """Test creating a dataset from text."""
     dataset_dict = {
+        'name': 'my dataset',
         'cases': [
             {
                 'name': '1',
@@ -873,6 +895,7 @@ async def test_from_text():
     }
 
     loaded_dataset = Dataset[TaskInput, TaskOutput, TaskMetadata].from_text(json.dumps(dataset_dict))
+    assert loaded_dataset.name == 'my dataset'
     assert loaded_dataset.cases == snapshot(
         [
             Case(
@@ -1240,7 +1263,7 @@ async def test_dataset_evaluate_with_custom_name(example_dataset: Dataset[TaskIn
     async def task(inputs: TaskInput) -> TaskOutput:
         return TaskOutput(answer=inputs.query.upper())
 
-    report = await example_dataset.evaluate(task, name='custom_task')
+    report = await example_dataset.evaluate(task, task_name='custom_task')
     assert report.name == 'custom_task'
 
 
@@ -1490,16 +1513,26 @@ async def test_evaluate_async_logfire(
             (
                 'evaluate {name}',
                 {
-                    'name': 'mock_async_task',
-                    'n_cases': 2,
                     'assertion_pass_rate': 1.0,
-                    'logfire.msg_template': 'evaluate {name}',
-                    'logfire.msg': 'evaluate mock_async_task',
-                    'logfire.span_type': 'span',
+                    'dataset_name': 'example',
+                    'gen_ai.operation.name': 'experiment',
                     'logfire.json_schema': {
+                        'properties': {
+                            'assertion_pass_rate': {},
+                            'dataset_name': {},
+                            'gen_ai.operation.name': {},
+                            'n_cases': {},
+                            'name': {},
+                            'task_name': {},
+                        },
                         'type': 'object',
-                        'properties': {'name': {}, 'n_cases': {}, 'assertion_pass_rate': {}},
                     },
+                    'logfire.msg': 'evaluate mock_async_task',
+                    'logfire.msg_template': 'evaluate {name}',
+                    'logfire.span_type': 'span',
+                    'n_cases': 2,
+                    'name': 'mock_async_task',
+                    'task_name': 'mock_async_task',
                 },
             ),
             (