pydantic-ai-slim 0.4.2__py3-none-any.whl → 0.4.4__py3-none-any.whl

pydantic_ai/models/__init__.py

@@ -134,31 +134,15 @@ KnownModelName = TypeAliasType(
         'cohere:command-r7b-12-2024',
         'deepseek:deepseek-chat',
         'deepseek:deepseek-reasoner',
-        'google-gla:gemini-1.5-flash',
-        'google-gla:gemini-1.5-flash-8b',
-        'google-gla:gemini-1.5-pro',
-        'google-gla:gemini-1.0-pro',
         'google-gla:gemini-2.0-flash',
-        'google-gla:gemini-2.0-flash-lite-preview-02-05',
-        'google-gla:gemini-2.0-pro-exp-02-05',
-        'google-gla:gemini-2.5-flash-preview-05-20',
+        'google-gla:gemini-2.0-flash-lite',
         'google-gla:gemini-2.5-flash',
         'google-gla:gemini-2.5-flash-lite-preview-06-17',
-        'google-gla:gemini-2.5-pro-exp-03-25',
-        'google-gla:gemini-2.5-pro-preview-05-06',
         'google-gla:gemini-2.5-pro',
-        'google-vertex:gemini-1.5-flash',
-        'google-vertex:gemini-1.5-flash-8b',
-        'google-vertex:gemini-1.5-pro',
-        'google-vertex:gemini-1.0-pro',
         'google-vertex:gemini-2.0-flash',
-        'google-vertex:gemini-2.0-flash-lite-preview-02-05',
-        'google-vertex:gemini-2.0-pro-exp-02-05',
-        'google-vertex:gemini-2.5-flash-preview-05-20',
+        'google-vertex:gemini-2.0-flash-lite',
         'google-vertex:gemini-2.5-flash',
         'google-vertex:gemini-2.5-flash-lite-preview-06-17',
-        'google-vertex:gemini-2.5-pro-exp-03-25',
-        'google-vertex:gemini-2.5-pro-preview-05-06',
         'google-vertex:gemini-2.5-pro',
         'gpt-3.5-turbo',
         'gpt-3.5-turbo-0125',
@@ -192,6 +176,7 @@ KnownModelName = TypeAliasType(
         'gpt-4o-audio-preview',
         'gpt-4o-audio-preview-2024-10-01',
         'gpt-4o-audio-preview-2024-12-17',
+        'gpt-4o-audio-preview-2025-06-03',
         'gpt-4o-mini',
         'gpt-4o-mini-2024-07-18',
         'gpt-4o-mini-audio-preview',
@@ -200,6 +185,14 @@ KnownModelName = TypeAliasType(
         'gpt-4o-mini-search-preview-2025-03-11',
         'gpt-4o-search-preview',
         'gpt-4o-search-preview-2025-03-11',
+        'grok:grok-4',
+        'grok:grok-4-0709',
+        'grok:grok-3',
+        'grok:grok-3-mini',
+        'grok:grok-3-fast',
+        'grok:grok-3-mini-fast',
+        'grok:grok-2-vision-1212',
+        'grok:grok-2-image-1212',
         'groq:distil-whisper-large-v3-en',
         'groq:gemma2-9b-it',
         'groq:llama-3.3-70b-versatile',
@@ -207,6 +200,7 @@ KnownModelName = TypeAliasType(
         'groq:llama-guard-3-8b',
         'groq:llama3-70b-8192',
         'groq:llama3-8b-8192',
+        'groq:moonshotai/kimi-k2-instruct',
         'groq:whisper-large-v3',
         'groq:whisper-large-v3-turbo',
         'groq:playai-tts',
@@ -227,6 +221,14 @@ KnownModelName = TypeAliasType(
         'heroku:claude-3-7-sonnet',
         'heroku:claude-4-sonnet',
         'heroku:claude-3-haiku',
+        'huggingface:Qwen/QwQ-32B',
+        'huggingface:Qwen/Qwen2.5-72B-Instruct',
+        'huggingface:Qwen/Qwen3-235B-A22B',
+        'huggingface:Qwen/Qwen3-32B',
+        'huggingface:deepseek-ai/DeepSeek-R1',
+        'huggingface:meta-llama/Llama-3.3-70B-Instruct',
+        'huggingface:meta-llama/Llama-4-Maverick-17B-128E-Instruct',
+        'huggingface:meta-llama/Llama-4-Scout-17B-16E-Instruct',
         'mistral:codestral-latest',
         'mistral:mistral-large-latest',
         'mistral:mistral-moderation-latest',
@@ -237,11 +239,18 @@ KnownModelName = TypeAliasType(
         'o1-mini-2024-09-12',
         'o1-preview',
         'o1-preview-2024-09-12',
+        'o1-pro',
+        'o1-pro-2025-03-19',
         'o3',
         'o3-2025-04-16',
+        'o3-deep-research',
+        'o3-deep-research-2025-06-26',
         'o3-mini',
         'o3-mini-2025-01-31',
+        'o3-pro',
+        'o3-pro-2025-06-10',
         'openai:chatgpt-4o-latest',
+        'openai:codex-mini-latest',
         'openai:gpt-3.5-turbo',
         'openai:gpt-3.5-turbo-0125',
         'openai:gpt-3.5-turbo-0301',
@@ -274,6 +283,7 @@ KnownModelName = TypeAliasType(
         'openai:gpt-4o-audio-preview',
         'openai:gpt-4o-audio-preview-2024-10-01',
         'openai:gpt-4o-audio-preview-2024-12-17',
+        'openai:gpt-4o-audio-preview-2025-06-03',
         'openai:gpt-4o-mini',
         'openai:gpt-4o-mini-2024-07-18',
         'openai:gpt-4o-mini-audio-preview',
@@ -288,12 +298,22 @@ KnownModelName = TypeAliasType(
         'openai:o1-mini-2024-09-12',
         'openai:o1-preview',
         'openai:o1-preview-2024-09-12',
+        'openai:o1-pro',
+        'openai:o1-pro-2025-03-19',
         'openai:o3',
         'openai:o3-2025-04-16',
+        'openai:o3-deep-research',
+        'openai:o3-deep-research-2025-06-26',
         'openai:o3-mini',
         'openai:o3-mini-2025-01-31',
         'openai:o4-mini',
         'openai:o4-mini-2025-04-16',
+        'openai:o4-mini-deep-research',
+        'openai:o4-mini-deep-research-2025-06-26',
+        'openai:o3-pro',
+        'openai:o3-pro-2025-06-10',
+        'openai:computer-use-preview',
+        'openai:computer-use-preview-2025-03-11',
         'test',
     ],
 )
@@ -560,7 +580,7 @@ def override_allow_model_requests(allow_model_requests: bool) -> Iterator[None]:
         ALLOW_MODEL_REQUESTS = old_value  # pyright: ignore[reportConstantRedefinition]
 
 
-def infer_model(model: Model | KnownModelName | str) -> Model:
+def infer_model(model: Model | KnownModelName | str) -> Model:  # noqa: C901
     """Infer the model from the name."""
     if isinstance(model, Model):
         return model
@@ -624,6 +644,10 @@ def infer_model(model: Model | KnownModelName | str) -> Model:
         from .bedrock import BedrockConverseModel
 
         return BedrockConverseModel(model_name, provider=provider)
+    elif provider == 'huggingface':
+        from .huggingface import HuggingFaceModel
+
+        return HuggingFaceModel(model_name, provider=provider)
     else:
         raise UserError(f'Unknown model: {model}')  # pragma: no cover
 

pydantic_ai/models/anthropic.py

@@ -256,7 +256,7 @@ class AnthropicModel(Model):
         except APIStatusError as e:
             if (status_code := e.status_code) >= 400:
                 raise ModelHTTPError(status_code=status_code, model_name=self.model_name, body=e.body) from e
-            raise  # pragma: lax no cover
+            raise  # pragma: no cover
 
     def _process_response(self, response: BetaMessage) -> ModelResponse:
         """Process a non-streamed response, and prepare a message to return."""
@@ -266,7 +266,7 @@ class AnthropicModel(Model):
                 items.append(TextPart(content=item.text))
             elif isinstance(item, BetaRedactedThinkingBlock):  # pragma: no cover
                 warnings.warn(
-                    'PydanticAI currently does not handle redacted thinking blocks. '
+                    'Pydantic AI currently does not handle redacted thinking blocks. '
                     'If you have a suggestion on how we should handle them, please open an issue.',
                     UserWarning,
                 )

pydantic_ai/models/bedrock.py

@@ -663,4 +663,4 @@ class _AsyncIteratorWrapper(Generic[T]):
             if type(e.__cause__) is StopIteration:
                 raise StopAsyncIteration
             else:
-                raise e  # pragma: lax no cover
+                raise e  # pragma: no cover

pydantic_ai/models/cohere.py

@@ -183,7 +183,7 @@ class CohereModel(Model):
         except ApiError as e:
             if (status_code := e.status_code) and status_code >= 400:
                 raise ModelHTTPError(status_code=status_code, model_name=self.model_name, body=e.body) from e
-            raise  # pragma: lax no cover
+            raise  # pragma: no cover
 
     def _process_response(self, response: ChatResponse) -> ModelResponse:
         """Process a non-streamed response, and prepare a message to return."""

pydantic_ai/models/function.py

@@ -214,21 +214,39 @@ class DeltaToolCall:
     """Incremental change to the tool call ID."""
 
 
+@dataclass
+class DeltaThinkingPart:
+    """Incremental change to a thinking part.
+
+    Used to describe a chunk when streaming thinking responses.
+    """
+
+    content: str | None = None
+    """Incremental change to the thinking content."""
+    signature: str | None = None
+    """Incremental change to the thinking signature."""
+
+
 DeltaToolCalls: TypeAlias = dict[int, DeltaToolCall]
 """A mapping of tool call IDs to incremental changes."""
 
+DeltaThinkingCalls: TypeAlias = dict[int, DeltaThinkingPart]
+"""A mapping of thinking call IDs to incremental changes."""
+
 # TODO: Change the signature to Callable[[list[ModelMessage], ModelSettings, ModelRequestParameters], ...]
 FunctionDef: TypeAlias = Callable[[list[ModelMessage], AgentInfo], Union[ModelResponse, Awaitable[ModelResponse]]]
 """A function used to generate a non-streamed response."""
 
 # TODO: Change signature as indicated above
-StreamFunctionDef: TypeAlias = Callable[[list[ModelMessage], AgentInfo], AsyncIterator[Union[str, DeltaToolCalls]]]
+StreamFunctionDef: TypeAlias = Callable[
+    [list[ModelMessage], AgentInfo], AsyncIterator[Union[str, DeltaToolCalls, DeltaThinkingCalls]]
+]
 """A function used to generate a streamed response.
 
-While this is defined as having return type of `AsyncIterator[Union[str, DeltaToolCalls]]`, it should
-really be considered as `Union[AsyncIterator[str], AsyncIterator[DeltaToolCalls]`,
+While this is defined as having return type of `AsyncIterator[Union[str, DeltaToolCalls, DeltaThinkingCalls]]`, it should
+really be considered as `Union[AsyncIterator[str], AsyncIterator[DeltaToolCalls], AsyncIterator[DeltaThinkingCalls]]`,
 
-E.g. you need to yield all text or all `DeltaToolCalls`, not mix them.
+E.g. you need to yield all text, all `DeltaToolCalls`, or all `DeltaThinkingCalls`, not mix them.
 """
 
 
@@ -237,7 +255,7 @@ class FunctionStreamedResponse(StreamedResponse):
     """Implementation of `StreamedResponse` for [FunctionModel][pydantic_ai.models.function.FunctionModel]."""
 
     _model_name: str
-    _iter: AsyncIterator[str | DeltaToolCalls]
+    _iter: AsyncIterator[str | DeltaToolCalls | DeltaThinkingCalls]
     _timestamp: datetime = field(default_factory=_utils.now_utc)
 
     def __post_init__(self):
@@ -249,20 +267,31 @@ class FunctionStreamedResponse(StreamedResponse):
                 response_tokens = _estimate_string_tokens(item)
                 self._usage += usage.Usage(response_tokens=response_tokens, total_tokens=response_tokens)
                 yield self._parts_manager.handle_text_delta(vendor_part_id='content', content=item)
-            else:
-                delta_tool_calls = item
-                for dtc_index, delta_tool_call in delta_tool_calls.items():
-                    if delta_tool_call.json_args:
-                        response_tokens = _estimate_string_tokens(delta_tool_call.json_args)
-                        self._usage += usage.Usage(response_tokens=response_tokens, total_tokens=response_tokens)
-                    maybe_event = self._parts_manager.handle_tool_call_delta(
-                        vendor_part_id=dtc_index,
-                        tool_name=delta_tool_call.name,
-                        args=delta_tool_call.json_args,
-                        tool_call_id=delta_tool_call.tool_call_id,
-                    )
-                    if maybe_event is not None:
-                        yield maybe_event
+            elif isinstance(item, dict) and item:
+                for dtc_index, delta in item.items():
+                    if isinstance(delta, DeltaThinkingPart):
+                        if delta.content:  # pragma: no branch
+                            response_tokens = _estimate_string_tokens(delta.content)
+                            self._usage += usage.Usage(response_tokens=response_tokens, total_tokens=response_tokens)
+                        yield self._parts_manager.handle_thinking_delta(
+                            vendor_part_id=dtc_index,
+                            content=delta.content,
+                            signature=delta.signature,
+                        )
+                    elif isinstance(delta, DeltaToolCall):
+                        if delta.json_args:
+                            response_tokens = _estimate_string_tokens(delta.json_args)
+                            self._usage += usage.Usage(response_tokens=response_tokens, total_tokens=response_tokens)
+                        maybe_event = self._parts_manager.handle_tool_call_delta(
+                            vendor_part_id=dtc_index,
+                            tool_name=delta.name,
+                            args=delta.json_args,
+                            tool_call_id=delta.tool_call_id,
+                        )
+                        if maybe_event is not None:
+                            yield maybe_event
+                    else:
+                        assert_never(delta)
 
     @property
     def model_name(self) -> str:
@@ -299,12 +328,9 @@ def _estimate_usage(messages: Iterable[ModelMessage]) -> usage.Usage:
                 if isinstance(part, TextPart):
                     response_tokens += _estimate_string_tokens(part.content)
                 elif isinstance(part, ThinkingPart):
-                    # NOTE: We don't send ThinkingPart to the providers yet.
-                    # If you are unsatisfied with this, please open an issue.
-                    pass
+                    response_tokens += _estimate_string_tokens(part.content)
                 elif isinstance(part, ToolCallPart):
-                    call = part
-                    response_tokens += 1 + _estimate_string_tokens(call.args_as_json_str())
+                    response_tokens += 1 + _estimate_string_tokens(part.args_as_json_str())
                 else:
                     assert_never(part)
         else:

pydantic_ai/models/gemini.py

@@ -48,18 +48,10 @@ from . import (
 )
 
 LatestGeminiModelNames = Literal[
-    'gemini-1.5-flash',
-    'gemini-1.5-flash-8b',
-    'gemini-1.5-pro',
-    'gemini-1.0-pro',
     'gemini-2.0-flash',
-    'gemini-2.0-flash-lite-preview-02-05',
-    'gemini-2.0-pro-exp-02-05',
-    'gemini-2.5-flash-preview-05-20',
+    'gemini-2.0-flash-lite',
     'gemini-2.5-flash',
     'gemini-2.5-flash-lite-preview-06-17',
-    'gemini-2.5-pro-exp-03-25',
-    'gemini-2.5-pro-preview-05-06',
     'gemini-2.5-pro',
 ]
 """Latest Gemini models."""
@@ -253,7 +245,7 @@ class GeminiModel(Model):
 
         if gemini_labels := model_settings.get('gemini_labels'):
             if self._system == 'google-vertex':
-                request_data['labels'] = gemini_labels  # pragma: lax no cover
+                request_data['labels'] = gemini_labels
 
         headers = {'Content-Type': 'application/json', 'User-Agent': get_user_agent()}
         url = f'/{self._model_name}:{"streamGenerateContent" if streamed else "generateContent"}'
@@ -415,7 +407,7 @@ def _settings_to_generation_config(model_settings: GeminiModelSettings) -> _Gemi
     if (frequency_penalty := model_settings.get('frequency_penalty')) is not None:
         config['frequency_penalty'] = frequency_penalty
     if (thinkingConfig := model_settings.get('gemini_thinking_config')) is not None:
-        config['thinking_config'] = thinkingConfig  # pragma: lax no cover
+        config['thinking_config'] = thinkingConfig
     return config
 
 

pydantic_ai/models/google.py

@@ -73,18 +73,10 @@ except ImportError as _import_error:
     ) from _import_error
 
 LatestGoogleModelNames = Literal[
-    'gemini-1.5-flash',
-    'gemini-1.5-flash-8b',
-    'gemini-1.5-pro',
-    'gemini-1.0-pro',
     'gemini-2.0-flash',
-    'gemini-2.0-flash-lite-preview-02-05',
-    'gemini-2.0-pro-exp-02-05',
-    'gemini-2.5-flash-preview-05-20',
+    'gemini-2.0-flash-lite',
     'gemini-2.5-flash',
     'gemini-2.5-flash-lite-preview-06-17',
-    'gemini-2.5-pro-exp-03-25',
-    'gemini-2.5-pro-preview-05-06',
     'gemini-2.5-pro',
 ]
 """Latest Gemini models."""
@@ -166,7 +158,7 @@ class GoogleModel(Model):
         self._model_name = model_name
 
         if isinstance(provider, str):
-            provider = GoogleProvider(vertexai=provider == 'google-vertex')  # pragma: lax no cover
+            provider = GoogleProvider(vertexai=provider == 'google-vertex')
 
         self._provider = provider
         self._system = provider.name
@@ -492,8 +484,7 @@ def _content_model_response(m: ModelResponse) -> ContentDict:
             function_call = FunctionCallDict(name=item.tool_name, args=item.args_as_dict(), id=item.tool_call_id)
             parts.append({'function_call': function_call})
         elif isinstance(item, TextPart):
-            if item.content:  # pragma: no branch
-                parts.append({'text': item.content})
+            parts.append({'text': item.content})
         elif isinstance(item, ThinkingPart):  # pragma: no cover
             # NOTE: We don't send ThinkingPart to the providers yet. If you are unsatisfied with this,
             # please open an issue. The below code is the code to send thinking to the provider.

pydantic_ai/models/groq.py

@@ -79,6 +79,7 @@ PreviewGroqModelNames = Literal[
     'llama-3.2-3b-preview',
     'llama-3.2-11b-vision-preview',
     'llama-3.2-90b-vision-preview',
+    'moonshotai/kimi-k2-instruct',
 ]
 """Preview Groq models from <https://console.groq.com/docs/models#preview-models>."""
 
@@ -248,7 +249,7 @@ class GroqModel(Model):
         except APIStatusError as e:
             if (status_code := e.status_code) >= 400:
                 raise ModelHTTPError(status_code=status_code, model_name=self.model_name, body=e.body) from e
-            raise  # pragma: lax no cover
+            raise  # pragma: no cover
 
     def _process_response(self, response: chat.ChatCompletion) -> ModelResponse:
         """Process a non-streamed response, and prepare a message to return."""