diff --git a/langchain_benchmarks/__init__.py b/langchain_benchmarks/__init__.py
index f7922812..3dc67486 100644
--- a/langchain_benchmarks/__init__.py
+++ b/langchain_benchmarks/__init__.py
@@ -1,3 +1,5 @@
+from importlib import metadata
+
 from langchain_benchmarks.model_registration import model_registry
 from langchain_benchmarks.rate_limiting import RateLimiter
 from langchain_benchmarks.registration import registry
@@ -6,8 +8,17 @@
     download_public_dataset,
 )
 
+try:
+    __version__ = metadata.version(__package__)
+except metadata.PackageNotFoundError:
+    # Case where package metadata is not available.
+    __version__ = ""
+del metadata  # optional, avoids polluting the results of dir(__package__)
+
+
 # Please keep this list sorted!
 __all__ = [
+    "__version__",
     "clone_public_dataset",
     "download_public_dataset",
     "model_registry",
diff --git a/langchain_benchmarks/tool_usage/agents/adapters.py b/langchain_benchmarks/tool_usage/agents/adapters.py
index 29bd3ddf..be060f8e 100644
--- a/langchain_benchmarks/tool_usage/agents/adapters.py
+++ b/langchain_benchmarks/tool_usage/agents/adapters.py
@@ -1,4 +1,4 @@
-from typing import Optional, Callable, Any
+from typing import Any, Callable, Optional
 
 from langchain.agents import AgentExecutor
 from langchain_core.runnables import Runnable, RunnableLambda, RunnablePassthrough
diff --git a/langchain_benchmarks/tool_usage/agents/experimental/agent.py b/langchain_benchmarks/tool_usage/agents/experimental/agent.py
index 14ba932d..87ada85e 100644
--- a/langchain_benchmarks/tool_usage/agents/experimental/agent.py
+++ b/langchain_benchmarks/tool_usage/agents/experimental/agent.py
@@ -6,7 +6,7 @@
 from langchain.tools import StructuredTool
 from langchain_core.agents import AgentAction, AgentFinish
 from langchain_core.language_models import BaseChatModel, BaseLanguageModel
-from langchain_core.messages import BaseMessage, HumanMessage, AIMessage
+from langchain_core.messages import AIMessage, BaseMessage, HumanMessage
 from langchain_core.prompts import MessagesPlaceholder
 from typing_extensions import NotRequired, TypedDict
 
@@ -14,10 +14,10 @@
 from langchain_benchmarks.rate_limiting import with_rate_limit
 from langchain_benchmarks.tool_usage.agents.experimental.encoder import (
     AstPrinter,
+    FunctionResult,
     TypeScriptEncoder,
     XMLEncoder,
 )
-from langchain_benchmarks.tool_usage.agents.experimental.encoder import FunctionResult
 from langchain_benchmarks.tool_usage.agents.experimental.prompts import (
     _AGENT_INSTRUCTIONS_BLOB_STYLE,
 )
diff --git a/langchain_benchmarks/tool_usage/agents/experimental/parser.py b/langchain_benchmarks/tool_usage/agents/experimental/parser.py
index 7be09776..002ddf02 100644
--- a/langchain_benchmarks/tool_usage/agents/experimental/parser.py
+++ b/langchain_benchmarks/tool_usage/agents/experimental/parser.py
@@ -1,6 +1,6 @@
 import ast
 import re
-from typing import Union, Dict, Optional
+from typing import Dict, Optional, Union
 
 from langchain.agents import AgentOutputParser
 from langchain.pydantic_v1 import BaseModel, Field
diff --git a/langchain_benchmarks/tool_usage/agents/experimental/tool_utils.py b/langchain_benchmarks/tool_usage/agents/experimental/tool_utils.py
index 976fc061..04fed82b 100644
--- a/langchain_benchmarks/tool_usage/agents/experimental/tool_utils.py
+++ b/langchain_benchmarks/tool_usage/agents/experimental/tool_utils.py
@@ -6,8 +6,8 @@
 from langchain.tools.base import StructuredTool
 
 from langchain_benchmarks.tool_usage.agents.experimental.encoder import (
-    Parameter,
     FunctionDefinition,
+    Parameter,
 )
 
 # PUBLIC API
diff --git a/langchain_benchmarks/tool_usage/agents/openai_functions.py b/langchain_benchmarks/tool_usage/agents/openai_functions.py
index 32186d02..46389ca8 100644
--- a/langchain_benchmarks/tool_usage/agents/openai_functions.py
+++ b/langchain_benchmarks/tool_usage/agents/openai_functions.py
@@ -13,7 +13,6 @@
 from langchain_benchmarks.schema import ToolUsageTask
 from langchain_benchmarks.tool_usage.agents.adapters import apply_agent_executor_adapter
 
-
 # PUBLIC API
 
 
diff --git a/tests/unit_tests/agents/encoding_and_decoding/test_decoding.py b/tests/unit_tests/agents/encoding_and_decoding/test_decoding.py
index 5a416cfa..5ed5da7a 100644
--- a/tests/unit_tests/agents/encoding_and_decoding/test_decoding.py
+++ b/tests/unit_tests/agents/encoding_and_decoding/test_decoding.py
@@ -1,5 +1,5 @@
 import pytest
-from langchain_core.agents import AgentFinish, AgentActionMessageLog
+from langchain_core.agents import AgentActionMessageLog, AgentFinish
 from langchain_core.exceptions import OutputParserException
 from langchain_core.messages import AIMessage
 
diff --git a/tests/unit_tests/test_public_api.py b/tests/unit_tests/test_public_api.py
index b6b57651..4134e77c 100644
--- a/tests/unit_tests/test_public_api.py
+++ b/tests/unit_tests/test_public_api.py
@@ -7,6 +7,7 @@ def test_public_api() -> None:
     # Please keep it sorted!
     assert __all__ == sorted(
         [
+            "__version__",
             "clone_public_dataset",
             "download_public_dataset",
             "model_registry",