Skip to content

The agent engineering platform.

perf(.github): set a timeout on get min versions HTTP calls (#35851)

Tejas Attarded6dbcf6294da
diff --git a/.github/scripts/get_min_versions.py b/.github/scripts/get_min_versions.py
index dc173c2e0f..653f6902a4 100644
--- a/.github/scripts/get_min_versions.py
+++ b/.github/scripts/get_min_versions.py
@@ -48,7 +48,7 @@ def get_pypi_versions(package_name: str) -> List[str]:
KeyError: If package not found or response format unexpected
"""
pypi_url = f"https://pypi.org/pypi/{package_name}/json"
- response = requests.get(pypi_url)
+ response = requests.get(pypi_url, timeout=10.0)
response.raise_for_status()
return list(response.json()["releases"].keys())
diff --git a/libs/langchain/tests/unit_tests/test_pytest_config.py b/libs/langchain/tests/unit_tests/test_pytest_config.py
index c2b0af645f..b02d3d3dd5 100644
--- a/libs/langchain/tests/unit_tests/test_pytest_config.py
+++ b/libs/langchain/tests/unit_tests/test_pytest_config.py
@@ -8,4 +8,4 @@ def test_socket_disabled() -> None:
with pytest.raises(pytest_socket.SocketBlockedError):
# Ignore S113 since we don't need a timeout here as the request
# should fail immediately
- requests.get("https://www.example.com") # noqa: S113
+ requests.get("https://www.example.com", timeout=10.0) # noqa: S113
diff --git a/libs/partners/anthropic/tests/integration_tests/test_chat_models.py b/libs/partners/anthropic/tests/integration_tests/test_chat_models.py
index 8ef75edb45..6ab3b798fb 100644
--- a/libs/partners/anthropic/tests/integration_tests/test_chat_models.py
+++ b/libs/partners/anthropic/tests/integration_tests/test_chat_models.py
@@ -1231,7 +1231,7 @@ def test_image_tool_calling() -> None:
},
]
image_url = "https://raw.githubusercontent.com/langchain-ai/docs/4d11d08b6b0e210bd456943f7a22febbd168b543/src/images/agentic-rag-output.png"
- image_data = b64encode(httpx.get(image_url).content).decode("utf-8")
+ image_data = b64encode(httpx.get(image_url, timeout=10.0).content).decode("utf-8")
human_content.append(
{
"type": "image",
diff --git a/libs/partners/openai/tests/integration_tests/chat_models/test_base.py b/libs/partners/openai/tests/integration_tests/chat_models/test_base.py
index 26a8bb787a..28012204af 100644
--- a/libs/partners/openai/tests/integration_tests/chat_models/test_base.py
+++ b/libs/partners/openai/tests/integration_tests/chat_models/test_base.py
@@ -718,7 +718,7 @@ def test_image_token_counting_jpeg() -> None:
actual = model.get_num_tokens_from_messages([message])
assert expected == actual
- image_data = base64.b64encode(httpx.get(image_url).content).decode("utf-8")
+ image_data = base64.b64encode(httpx.get(image_url, timeout=10.0).content).decode("utf-8")
message = HumanMessage(
content=[
{"type": "text", "text": "describe the weather in this image"},
@@ -750,7 +750,7 @@ def test_image_token_counting_png() -> None:
actual = model.get_num_tokens_from_messages([message])
assert expected == actual
- image_data = base64.b64encode(httpx.get(image_url).content).decode("utf-8")
+ image_data = base64.b64encode(httpx.get(image_url, timeout=10.0).content).decode("utf-8")
message = HumanMessage(
content=[
{"type": "text", "text": "how many dice are in this image"},
diff --git a/libs/partners/openai/tests/integration_tests/chat_models/test_base_standard.py b/libs/partners/openai/tests/integration_tests/chat_models/test_base_standard.py
index c49d5a40e1..c572a850b6 100644
--- a/libs/partners/openai/tests/integration_tests/chat_models/test_base_standard.py
+++ b/libs/partners/openai/tests/integration_tests/chat_models/test_base_standard.py
@@ -92,7 +92,7 @@ class TestOpenAIStandard(ChatModelIntegrationTests):
def test_openai_pdf_inputs(self, model: BaseChatModel) -> None:
"""Test that the model can process PDF inputs."""
url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
- pdf_data = base64.b64encode(httpx.get(url).content).decode("utf-8")
+ pdf_data = base64.b64encode(httpx.get(url, timeout=10.0).content).decode("utf-8")
message = HumanMessage(
[
diff --git a/libs/partners/openai/tests/integration_tests/chat_models/test_responses_standard.py b/libs/partners/openai/tests/integration_tests/chat_models/test_responses_standard.py
index a2b63e1ab8..37466928ab 100644
--- a/libs/partners/openai/tests/integration_tests/chat_models/test_responses_standard.py
+++ b/libs/partners/openai/tests/integration_tests/chat_models/test_responses_standard.py
@@ -87,7 +87,7 @@ class TestOpenAIResponses(TestOpenAIStandard):
def test_openai_pdf_tool_messages(self, model: BaseChatModel) -> None:
"""Test that the model can process PDF inputs in `ToolMessage` objects."""
url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
- pdf_data = base64.b64encode(httpx.get(url).content).decode("utf-8")
+ pdf_data = base64.b64encode(httpx.get(url, timeout=10.0).content).decode("utf-8")
tool_message = ToolMessage(
content_blocks=[
diff --git a/libs/standard-tests/langchain_tests/integration_tests/chat_models.py b/libs/standard-tests/langchain_tests/integration_tests/chat_models.py
index f014e37aae..9191fd61d5 100644
--- a/libs/standard-tests/langchain_tests/integration_tests/chat_models.py
+++ b/libs/standard-tests/langchain_tests/integration_tests/chat_models.py
@@ -151,7 +151,7 @@ def _get_base64_from_url(url: str) -> str:
)
warnings.warn(warning_message, stacklevel=2)
headers = {"User-Agent": user_agent} if user_agent else {}
- httpx_response = httpx.get(url, headers=headers).content
+ httpx_response = httpx.get(url, headers=headers, timeout=10.0).content
return base64.b64encode(httpx_response).decode("utf-8")
@@ -2583,7 +2583,7 @@ class ChatModelIntegrationTests(ChatModelTests):
pytest.skip("Model does not support PDF inputs.")
url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
- pdf_data = base64.b64encode(httpx.get(url).content).decode("utf-8")
+ pdf_data = base64.b64encode(httpx.get(url, timeout=10.0).content).decode("utf-8")
message = HumanMessage(
[
@@ -2781,7 +2781,7 @@ class ChatModelIntegrationTests(ChatModelTests):
pytest.skip("Model does not support image message.")
image_url = "https://raw.githubusercontent.com/langchain-ai/docs/4d11d08b6b0e210bd456943f7a22febbd168b543/src/images/agentic-rag-output.png"
- image_data = base64.b64encode(httpx.get(image_url).content).decode("utf-8")
+ image_data = base64.b64encode(httpx.get(image_url, timeout=10.0).content).decode("utf-8")
# OpenAI CC format, base64 data
message = HumanMessage(
@@ -2887,7 +2887,7 @@ class ChatModelIntegrationTests(ChatModelTests):
pytest.skip("Model does not support image tool message.")
image_url = "https://raw.githubusercontent.com/langchain-ai/docs/4d11d08b6b0e210bd456943f7a22febbd168b543/src/images/agentic-rag-output.png"
- image_data = base64.b64encode(httpx.get(image_url).content).decode("utf-8")
+ image_data = base64.b64encode(httpx.get(image_url, timeout=10.0).content).decode("utf-8")
# OpenAI CC format, base64 data
oai_format_message = ToolMessage(
@@ -2986,7 +2986,7 @@ class ChatModelIntegrationTests(ChatModelTests):
pytest.skip("Model does not support PDF tool message.")
url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
- pdf_data = base64.b64encode(httpx.get(url).content).decode("utf-8")
+ pdf_data = base64.b64encode(httpx.get(url, timeout=10.0).content).decode("utf-8")
tool_message = ToolMessage(
content_blocks=[
@@ -3122,7 +3122,7 @@ class ChatModelIntegrationTests(ChatModelTests):
]
if self.supports_image_inputs:
image_url = "https://raw.githubusercontent.com/langchain-ai/docs/4d11d08b6b0e210bd456943f7a22febbd168b543/src/images/agentic-rag-output.png"
- image_data = base64.b64encode(httpx.get(image_url).content).decode("utf-8")
+ image_data = base64.b64encode(httpx.get(image_url, timeout=10.0).content).decode("utf-8")
human_content.append(
{
"type": "image",
diff --git a/libs/text-splitters/langchain_text_splitters/base.py b/libs/text-splitters/langchain_text_splitters/base.py
index 19114b253d..fa94ee2d46 100644
--- a/libs/text-splitters/langchain_text_splitters/base.py
+++ b/libs/text-splitters/langchain_text_splitters/base.py
@@ -227,7 +227,7 @@ class TextSplitter(BaseDocumentTransformer, ABC):
cls,
encoding_name: str = "gpt2",
model_name: str | None = None,
- allowed_special: Literal["all"] | AbstractSet[str] = set(),
+ allowed_special: Literal["all"] | AbstractSet[str] = None,
disallowed_special: Literal["all"] | Collection[str] = "all",
**kwargs: Any,
) -> Self:
@@ -247,6 +247,8 @@ class TextSplitter(BaseDocumentTransformer, ABC):
Raises:
ImportError: If the tiktoken package is not installed.
"""
+ if allowed_special is None:
+ allowed_special = set()
if not _HAS_TIKTOKEN:
msg = (
"Could not import tiktoken python package. "
@@ -302,7 +304,7 @@ class TokenTextSplitter(TextSplitter):
self,
encoding_name: str = "gpt2",
model_name: str | None = None,
- allowed_special: Literal["all"] | AbstractSet[str] = set(),
+ allowed_special: Literal["all"] | AbstractSet[str] = None,
disallowed_special: Literal["all"] | Collection[str] = "all",
**kwargs: Any,
) -> None:
@@ -319,6 +321,8 @@ class TokenTextSplitter(TextSplitter):
Raises:
ImportError: If the tiktoken package is not installed.
"""
+ if allowed_special is None:
+ allowed_special = set()
super().__init__(**kwargs)
if not _HAS_TIKTOKEN:
msg = (