langchain-core 1.0.0rc3__py3-none-any.whl → 1.0.1__py3-none-any.whl

langchain_core/caches.py

@@ -1,4 +1,6 @@
-"""`caches` provides an optional caching layer for language models.
+"""Optional caching layer for language models.
+
+Distinct from provider-based [prompt caching](https://docs.langchain.com/oss/python/langchain/models#prompt-caching).
 
 !!! warning
     This is a beta feature! Please be wary of deploying experimental code to production

langchain_core/callbacks/base.py

@@ -420,8 +420,6 @@ class RunManagerMixin:
                 (includes inherited tags).
             metadata: The metadata associated with the custom event
                 (includes inherited metadata).
-
-        !!! version-added "Added in version 0.2.15"
         """
 
 
@@ -882,8 +880,6 @@ class AsyncCallbackHandler(BaseCallbackHandler):
                 (includes inherited tags).
             metadata: The metadata associated with the custom event
                 (includes inherited metadata).
-
-        !!! version-added "Added in version 0.2.15"
         """
 
 

langchain_core/callbacks/manager.py

@@ -1566,9 +1566,6 @@ class CallbackManager(BaseCallbackManager):
 
         Raises:
             ValueError: If additional keyword arguments are passed.
-
-        !!! version-added "Added in version 0.2.14"
-
         """
         if not self.handlers:
             return
@@ -2042,8 +2039,6 @@ class AsyncCallbackManager(BaseCallbackManager):
 
         Raises:
             ValueError: If additional keyword arguments are passed.
-
-        !!! version-added "Added in version 0.2.14"
         """
         if not self.handlers:
             return
@@ -2555,9 +2550,6 @@ async def adispatch_custom_event(
         This is due to a limitation in asyncio for python <= 3.10 that prevents
         LangChain from automatically propagating the config object on the user's
         behalf.
-
-    !!! version-added "Added in version 0.2.15"
-
     """
     # Import locally to prevent circular imports.
     from langchain_core.runnables.config import (  # noqa: PLC0415
@@ -2630,9 +2622,6 @@ def dispatch_custom_event(
         foo_ = RunnableLambda(foo)
         foo_.invoke({"a": "1"}, {"callbacks": [CustomCallbackManager()]})
         ```
-
-    !!! version-added "Added in version 0.2.15"
-
     """
     # Import locally to prevent circular imports.
     from langchain_core.runnables.config import (  # noqa: PLC0415

langchain_core/document_loaders/langsmith.py

@@ -34,9 +34,6 @@ class LangSmithLoader(BaseLoader):
         ```python
         # -> [Document("...", metadata={"inputs": {...}, "outputs": {...}, ...}), ...]
         ```
-
-    !!! version-added "Added in version 0.2.34"
-
     """
 
     def __init__(

langchain_core/documents/base.py

@@ -38,8 +38,6 @@ class BaseMedia(Serializable):
 
     Ideally this should be unique across the document collection and formatted
     as a UUID, but this will not be enforced.
-
-    !!! version-added "Added in version 0.2.11"
     """
 
     metadata: dict = Field(default_factory=dict)

langchain_core/documents/transformers.py

@@ -57,10 +57,10 @@ class BaseDocumentTransformer(ABC):
         """Transform a list of documents.
 
         Args:
-            documents: A sequence of Documents to be transformed.
+            documents: A sequence of `Document` objects to be transformed.
 
         Returns:
-            A sequence of transformed Documents.
+            A sequence of transformed `Document` objects.
         """
 
     async def atransform_documents(
@@ -69,10 +69,10 @@ class BaseDocumentTransformer(ABC):
         """Asynchronously transform a list of documents.
 
         Args:
-            documents: A sequence of Documents to be transformed.
+            documents: A sequence of `Document` objects to be transformed.
 
         Returns:
-            A sequence of transformed Documents.
+            A sequence of transformed `Document` objects.
         """
         return await run_in_executor(
             None, self.transform_documents, documents, **kwargs

langchain_core/indexing/base.py

@@ -508,8 +508,6 @@ class DocumentIndex(BaseRetriever):
     1. Storing document in the index.
     2. Fetching document by ID.
     3. Searching for document using a query.
-
-    !!! version-added "Added in version 0.2.29"
     """
 
     @abc.abstractmethod
@@ -522,10 +520,10 @@ class DocumentIndex(BaseRetriever):
 
         When an ID is specified and the content already exists in the vectorstore,
         the upsert method should update the content with the new data. If the content
-        does not exist, the upsert method should add the item to the vectorstore.
+        does not exist, the upsert method should add the item to the `VectorStore`.
 
         Args:
-            items: Sequence of documents to add to the vectorstore.
+            items: Sequence of documents to add to the `VectorStore`.
             **kwargs: Additional keyword arguments.
 
         Returns:
@@ -545,10 +543,10 @@ class DocumentIndex(BaseRetriever):
 
         When an ID is specified and the item already exists in the vectorstore,
         the upsert method should update the item with the new data. If the item
-        does not exist, the upsert method should add the item to the vectorstore.
+        does not exist, the upsert method should add the item to the `VectorStore`.
 
         Args:
-            items: Sequence of documents to add to the vectorstore.
+            items: Sequence of documents to add to the `VectorStore`.
             **kwargs: Additional keyword arguments.
 
         Returns:

langchain_core/indexing/in_memory.py

@@ -23,8 +23,6 @@ class InMemoryDocumentIndex(DocumentIndex):
 
     It provides a simple search API that returns documents by the number of
     counts the given query appears in the document.
-
-    !!! version-added "Added in version 0.2.29"
     """
 
     store: dict[str, Document] = Field(default_factory=dict)

langchain_core/language_models/base.py

@@ -200,14 +200,14 @@ class BaseLanguageModel(
                 pure text generation models and `BaseMessage` objects for chat models).
             stop: Stop words to use when generating. Model output is cut off at the
                 first occurrence of any of these substrings.
-            callbacks: Callbacks to pass through. Used for executing additional
+            callbacks: `Callbacks` to pass through. Used for executing additional
                 functionality, such as logging or streaming, throughout generation.
             **kwargs: Arbitrary additional keyword arguments. These are usually passed
                 to the model provider API call.
 
         Returns:
             An `LLMResult`, which contains a list of candidate `Generation` objects for
-            each input prompt and additional model provider-specific output.
+                each input prompt and additional model provider-specific output.
 
         """
 
@@ -237,14 +237,14 @@ class BaseLanguageModel(
                 pure text generation models and `BaseMessage` objects for chat models).
             stop: Stop words to use when generating. Model output is cut off at the
                 first occurrence of any of these substrings.
-            callbacks: Callbacks to pass through. Used for executing additional
+            callbacks: `Callbacks` to pass through. Used for executing additional
                 functionality, such as logging or streaming, throughout generation.
             **kwargs: Arbitrary additional keyword arguments. These are usually passed
                 to the model provider API call.
 
         Returns:
             An `LLMResult`, which contains a list of candidate `Generation` objects for
-            each input prompt and additional model provider-specific output.
+                each input prompt and additional model provider-specific output.
 
         """
 
@@ -269,8 +269,7 @@ class BaseLanguageModel(
 
         Returns:
             A list of ids corresponding to the tokens in the text, in order they occur
-            in the text.
-
+                in the text.
         """
         if self.custom_get_token_ids is not None:
             return self.custom_get_token_ids(text)

langchain_core/language_models/chat_models.py

@@ -838,13 +838,13 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
         1. Take advantage of batched calls,
         2. Need more output from the model than just the top generated value,
         3. Are building chains that are agnostic to the underlying language model
-           type (e.g., pure text completion models vs chat models).
+            type (e.g., pure text completion models vs chat models).
 
         Args:
             messages: List of list of messages.
             stop: Stop words to use when generating. Model output is cut off at the
                 first occurrence of any of these substrings.
-            callbacks: Callbacks to pass through. Used for executing additional
+            callbacks: `Callbacks` to pass through. Used for executing additional
                 functionality, such as logging or streaming, throughout generation.
             tags: The tags to apply.
             metadata: The metadata to apply.
@@ -854,8 +854,8 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
                 to the model provider API call.
 
         Returns:
-            An LLMResult, which contains a list of candidate Generations for each input
-            prompt and additional model provider-specific output.
+            An `LLMResult`, which contains a list of candidate `Generations` for each
+                input prompt and additional model provider-specific output.
 
         """
         ls_structured_output_format = kwargs.pop(
@@ -956,13 +956,13 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
         1. Take advantage of batched calls,
         2. Need more output from the model than just the top generated value,
         3. Are building chains that are agnostic to the underlying language model
-           type (e.g., pure text completion models vs chat models).
+            type (e.g., pure text completion models vs chat models).
 
         Args:
             messages: List of list of messages.
             stop: Stop words to use when generating. Model output is cut off at the
                 first occurrence of any of these substrings.
-            callbacks: Callbacks to pass through. Used for executing additional
+            callbacks: `Callbacks` to pass through. Used for executing additional
                 functionality, such as logging or streaming, throughout generation.
             tags: The tags to apply.
             metadata: The metadata to apply.
@@ -972,8 +972,8 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
                 to the model provider API call.
 
         Returns:
-            An LLMResult, which contains a list of candidate Generations for each input
-            prompt and additional model provider-specific output.
+            An `LLMResult`, which contains a list of candidate `Generations` for each
+                input prompt and additional model provider-specific output.
 
         """
         ls_structured_output_format = kwargs.pop(
@@ -1510,17 +1510,21 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
                 If `schema` is a Pydantic class then the model output will be a
                 Pydantic instance of that class, and the model-generated fields will be
                 validated by the Pydantic class. Otherwise the model output will be a
-                dict and will not be validated. See `langchain_core.utils.function_calling.convert_to_openai_tool`
-                for more on how to properly specify types and descriptions of
-                schema fields when specifying a Pydantic or `TypedDict` class.
+                dict and will not be validated.
+
+                See `langchain_core.utils.function_calling.convert_to_openai_tool` for
+                more on how to properly specify types and descriptions of schema fields
+                when specifying a Pydantic or `TypedDict` class.
 
             include_raw:
                 If `False` then only the parsed structured output is returned. If
                 an error occurs during model output parsing it will be raised. If `True`
                 then both the raw model response (a `BaseMessage`) and the parsed model
                 response will be returned. If an error occurs during output parsing it
-                will be caught and returned as well. The final output is always a dict
-                with keys `'raw'`, `'parsed'`, and `'parsing_error'`.
+                will be caught and returned as well.
+
+                The final output is always a `dict` with keys `'raw'`, `'parsed'`, and
+                `'parsing_error'`.
 
         Raises:
             ValueError: If there are any unsupported `kwargs`.
@@ -1528,97 +1532,99 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
                 `with_structured_output()`.
 
         Returns:
-            A Runnable that takes same inputs as a `langchain_core.language_models.chat.BaseChatModel`.
+            A `Runnable` that takes same inputs as a
+                `langchain_core.language_models.chat.BaseChatModel`. If `include_raw` is
+                `False` and `schema` is a Pydantic class, `Runnable` outputs an instance
+                of `schema` (i.e., a Pydantic object). Otherwise, if `include_raw` is
+                `False` then `Runnable` outputs a `dict`.
 
-                If `include_raw` is False and `schema` is a Pydantic class, Runnable outputs
-                an instance of `schema` (i.e., a Pydantic object).
+                If `include_raw` is `True`, then `Runnable` outputs a `dict` with keys:
 
-                Otherwise, if `include_raw` is False then Runnable outputs a dict.
+                - `'raw'`: `BaseMessage`
+                - `'parsed'`: `None` if there was a parsing error, otherwise the type
+                    depends on the `schema` as described above.
+                - `'parsing_error'`: `BaseException | None`
 
-                If `include_raw` is True, then Runnable outputs a dict with keys:
+        Example: Pydantic schema (`include_raw=False`):
 
-                - `'raw'`: BaseMessage
-                - `'parsed'`: None if there was a parsing error, otherwise the type
-                    depends on the `schema` as described above.
-                - `'parsing_error'`: BaseException | None
+        ```python
+        from pydantic import BaseModel
 
-        Example: Pydantic schema (include_raw=False):
-            ```python
-            from pydantic import BaseModel
 
+        class AnswerWithJustification(BaseModel):
+            '''An answer to the user question along with justification for the answer.'''
 
-            class AnswerWithJustification(BaseModel):
-                '''An answer to the user question along with justification for the answer.'''
+            answer: str
+            justification: str
 
-                answer: str
-                justification: str
 
+        model = ChatModel(model="model-name", temperature=0)
+        structured_model = model.with_structured_output(AnswerWithJustification)
 
-            model = ChatModel(model="model-name", temperature=0)
-            structured_model = model.with_structured_output(AnswerWithJustification)
+        structured_model.invoke(
+            "What weighs more a pound of bricks or a pound of feathers"
+        )
 
-            structured_model.invoke(
-                "What weighs more a pound of bricks or a pound of feathers"
-            )
+        # -> AnswerWithJustification(
+        #     answer='They weigh the same',
+        #     justification='Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ.'
+        # )
+        ```
 
-            # -> AnswerWithJustification(
-            #     answer='They weigh the same',
-            #     justification='Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ.'
-            # )
-            ```
+        Example: Pydantic schema (`include_raw=True`):
 
-        Example: Pydantic schema (include_raw=True):
-            ```python
-            from pydantic import BaseModel
+        ```python
+        from pydantic import BaseModel
 
 
-            class AnswerWithJustification(BaseModel):
-                '''An answer to the user question along with justification for the answer.'''
+        class AnswerWithJustification(BaseModel):
+            '''An answer to the user question along with justification for the answer.'''
 
-                answer: str
-                justification: str
+            answer: str
+            justification: str
 
 
-            model = ChatModel(model="model-name", temperature=0)
-            structured_model = model.with_structured_output(
-                AnswerWithJustification, include_raw=True
-            )
+        model = ChatModel(model="model-name", temperature=0)
+        structured_model = model.with_structured_output(
+            AnswerWithJustification, include_raw=True
+        )
 
-            structured_model.invoke(
-                "What weighs more a pound of bricks or a pound of feathers"
-            )
-            # -> {
-            #     'raw': AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Ao02pnFYXD6GN1yzc0uXPsvF', 'function': {'arguments': '{"answer":"They weigh the same.","justification":"Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ."}', 'name': 'AnswerWithJustification'}, 'type': 'function'}]}),
-            #     'parsed': AnswerWithJustification(answer='They weigh the same.', justification='Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ.'),
-            #     'parsing_error': None
-            # }
-            ```
+        structured_model.invoke(
+            "What weighs more a pound of bricks or a pound of feathers"
+        )
+        # -> {
+        #     'raw': AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Ao02pnFYXD6GN1yzc0uXPsvF', 'function': {'arguments': '{"answer":"They weigh the same.","justification":"Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ."}', 'name': 'AnswerWithJustification'}, 'type': 'function'}]}),
+        #     'parsed': AnswerWithJustification(answer='They weigh the same.', justification='Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ.'),
+        #     'parsing_error': None
+        # }
+        ```
 
-        Example: Dict schema (include_raw=False):
-            ```python
-            from pydantic import BaseModel
-            from langchain_core.utils.function_calling import convert_to_openai_tool
+        Example: `dict` schema (`include_raw=False`):
 
+        ```python
+        from pydantic import BaseModel
+        from langchain_core.utils.function_calling import convert_to_openai_tool
 
-            class AnswerWithJustification(BaseModel):
-                '''An answer to the user question along with justification for the answer.'''
 
-                answer: str
-                justification: str
+        class AnswerWithJustification(BaseModel):
+            '''An answer to the user question along with justification for the answer.'''
 
+            answer: str
+            justification: str
 
-            dict_schema = convert_to_openai_tool(AnswerWithJustification)
-            model = ChatModel(model="model-name", temperature=0)
-            structured_model = model.with_structured_output(dict_schema)
 
-            structured_model.invoke(
-                "What weighs more a pound of bricks or a pound of feathers"
-            )
-            # -> {
-            #     'answer': 'They weigh the same',
-            #     'justification': 'Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume and density of the two substances differ.'
-            # }
-            ```
+        dict_schema = convert_to_openai_tool(AnswerWithJustification)
+        model = ChatModel(model="model-name", temperature=0)
+        structured_model = model.with_structured_output(dict_schema)
+
+        structured_model.invoke(
+            "What weighs more a pound of bricks or a pound of feathers"
+        )
+        # -> {
+        #     'answer': 'They weigh the same',
+        #     'justification': 'Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume and density of the two substances differ.'
+        # }
+        ```
 
         !!! warning "Behavior changed in 0.2.26"
             Added support for TypedDict class.

langchain_core/language_models/llms.py

@@ -91,13 +91,17 @@ def create_base_retry_decorator(
             if isinstance(run_manager, AsyncCallbackManagerForLLMRun):
                 coro = run_manager.on_retry(retry_state)
                 try:
-                    loop = asyncio.get_event_loop()
-                    if loop.is_running():
-                        # TODO: Fix RUF006 - this task should have a reference
-                        #  and be awaited somewhere
-                        loop.create_task(coro)  # noqa: RUF006
-                    else:
+                    try:
+                        loop = asyncio.get_event_loop()
+                    except RuntimeError:
                         asyncio.run(coro)
+                    else:
+                        if loop.is_running():
+                            # TODO: Fix RUF006 - this task should have a reference
+                            #  and be awaited somewhere
+                            loop.create_task(coro)  # noqa: RUF006
+                        else:
+                            asyncio.run(coro)
                 except Exception as e:
                     _log_error_once(f"Error in on_retry: {e}")
             else:
@@ -841,7 +845,7 @@ class BaseLLM(BaseLanguageModel[str], ABC):
             prompts: List of string prompts.
             stop: Stop words to use when generating. Model output is cut off at the
                 first occurrence of any of these substrings.
-            callbacks: Callbacks to pass through. Used for executing additional
+            callbacks: `Callbacks` to pass through. Used for executing additional
                 functionality, such as logging or streaming, throughout generation.
             tags: List of tags to associate with each prompt. If provided, the length
                 of the list must match the length of the prompts list.
@@ -861,8 +865,8 @@ class BaseLLM(BaseLanguageModel[str], ABC):
                 `run_name` (if provided) does not match the length of prompts.
 
         Returns:
-            An LLMResult, which contains a list of candidate Generations for each input
-                prompt and additional model provider-specific output.
+            An `LLMResult`, which contains a list of candidate `Generations` for each
+                input prompt and additional model provider-specific output.
         """
         if not isinstance(prompts, list):
             msg = (
@@ -1111,7 +1115,7 @@ class BaseLLM(BaseLanguageModel[str], ABC):
             prompts: List of string prompts.
             stop: Stop words to use when generating. Model output is cut off at the
                 first occurrence of any of these substrings.
-            callbacks: Callbacks to pass through. Used for executing additional
+            callbacks: `Callbacks` to pass through. Used for executing additional
                 functionality, such as logging or streaming, throughout generation.
             tags: List of tags to associate with each prompt. If provided, the length
                 of the list must match the length of the prompts list.
@@ -1130,8 +1134,8 @@ class BaseLLM(BaseLanguageModel[str], ABC):
                 `run_name` (if provided) does not match the length of prompts.
 
         Returns:
-            An LLMResult, which contains a list of candidate Generations for each input
-                prompt and additional model provider-specific output.
+            An `LLMResult`, which contains a list of candidate `Generations` for each
+                input prompt and additional model provider-specific output.
         """
         if isinstance(metadata, list):
             metadata = [

langchain_core/load/dump.py

@@ -38,7 +38,7 @@ def _dump_pydantic_models(obj: Any) -> Any:
 
 
 def dumps(obj: Any, *, pretty: bool = False, **kwargs: Any) -> str:
-    """Return a json string representation of an object.
+    """Return a JSON string representation of an object.
 
     Args:
         obj: The object to dump.
@@ -47,7 +47,7 @@ def dumps(obj: Any, *, pretty: bool = False, **kwargs: Any) -> str:
         **kwargs: Additional arguments to pass to `json.dumps`
 
     Returns:
-        A json string representation of the object.
+        A JSON string representation of the object.
 
     Raises:
         ValueError: If `default` is passed as a kwarg.
@@ -71,14 +71,12 @@ def dumps(obj: Any, *, pretty: bool = False, **kwargs: Any) -> str:
 def dumpd(obj: Any) -> Any:
     """Return a dict representation of an object.
 
-    !!! note
-        Unfortunately this function is not as efficient as it could be because it first
-        dumps the object to a json string and then loads it back into a dictionary.
-
     Args:
         obj: The object to dump.
 
     Returns:
-        dictionary that can be serialized to json using json.dumps
+        Dictionary that can be serialized to json using `json.dumps`.
     """
+    # Unfortunately this function is not as efficient as it could be because it first
+    # dumps the object to a json string and then loads it back into a dictionary.
     return json.loads(dumps(obj))

langchain_core/messages/block_translators/google_genai.py

@@ -282,7 +282,7 @@ def _convert_to_v1_from_genai(message: AIMessage) -> list[types.ContentBlock]:
     standard content blocks for returning.
 
     Args:
-        message: The AIMessage or AIMessageChunk to convert.
+        message: The `AIMessage` or `AIMessageChunk` to convert.
 
     Returns:
         List of standard content blocks derived from the message content.

langchain_core/messages/utils.py

@@ -439,8 +439,8 @@ def filter_messages(
         exclude_ids: Message IDs to exclude.
         exclude_tool_calls: Tool call IDs to exclude.
             Can be one of the following:
-            - `True`: all `AIMessage`s with tool calls and all
-                `ToolMessage` objects will be excluded.
+            - `True`: All `AIMessage` objects with tool calls and all `ToolMessage`
+                objects will be excluded.
             - a sequence of tool call IDs to exclude:
                 - `ToolMessage` objects with the corresponding tool call ID will be
                     excluded.
@@ -1678,11 +1678,11 @@ def count_tokens_approximately(
         messages: List of messages to count tokens for.
         chars_per_token: Number of characters per token to use for the approximation.
             One token corresponds to ~4 chars for common English text.
-            You can also specify float values for more fine-grained control.
+            You can also specify `float` values for more fine-grained control.
             [See more here](https://platform.openai.com/tokenizer).
         extra_tokens_per_message: Number of extra tokens to add per message, e.g.
             special tokens, including beginning/end of message.
-            You can also specify float values for more fine-grained control.
+            You can also specify `float` values for more fine-grained control.
             [See more here](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb).
         count_name: Whether to include message names in the count.
             Enabled by default.

langchain_core/prompts/string.py

@@ -122,13 +122,16 @@ def mustache_formatter(template: str, /, **kwargs: Any) -> str:
 def mustache_template_vars(
     template: str,
 ) -> set[str]:
-    """Get the variables from a mustache template.
+    """Get the top-level variables from a mustache template.
+
+    For nested variables like `{{person.name}}`, only the top-level
+    key (`person`) is returned.
 
     Args:
         template: The template string.
 
     Returns:
-        The variables from the template.
+       The top-level variables from the template.
     """
     variables: set[str] = set()
     section_depth = 0

langchain_core/rate_limiters.py

@@ -105,9 +105,7 @@ class InMemoryRateLimiter(BaseRateLimiter):
 
         from langchain_anthropic import ChatAnthropic
 
-        model = ChatAnthropic(
-            model_name="claude-sonnet-4-5-20250929", rate_limiter=rate_limiter
-        )
+        model = ChatAnthropic(model_name="claude-sonnet-4-5", rate_limiter=rate_limiter)
 
         for _ in range(5):
             tic = time.time()