From 317fb86fd9540370b035d8a4a9ff2918a30b74ac Mon Sep 17 00:00:00 2001
From: Bagatur <22008038+baskaryan@users.noreply.github.com>
Date: Thu, 23 Jan 2025 13:23:01 -0800
Subject: [PATCH] openai[patch]: fix int test (#29395)

---
 libs/partners/openai/Makefile                 |  2 +-
 libs/partners/openai/poetry.lock              | 36 ++++++++++++++++++-
 libs/partners/openai/pyproject.toml           |  1 +
 .../chat_models/test_base.py                  | 32 +----------------
 4 files changed, 38 insertions(+), 33 deletions(-)

diff --git a/libs/partners/openai/Makefile b/libs/partners/openai/Makefile
index 210bdb4479007..e44b876aea5c5 100644
--- a/libs/partners/openai/Makefile
+++ b/libs/partners/openai/Makefile
@@ -21,7 +21,7 @@ test tests:
 	TIKTOKEN_CACHE_DIR=tiktoken_cache poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	poetry run pytest $(TEST_FILE)
+	poetry run pytest -n auto $(TEST_FILE)
 
 test_watch:
 	poetry run ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/openai/poetry.lock b/libs/partners/openai/poetry.lock
index 04c907494cc81..09c56a32bfdbf 100644
--- a/libs/partners/openai/poetry.lock
+++ b/libs/partners/openai/poetry.lock
@@ -354,6 +354,20 @@ files = [
 [package.extras]
 test = ["pytest (>=6)"]
 
+[[package]]
+name = "execnet"
+version = "2.1.1"
+description = "execnet: rapid multi-Python deployment"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "execnet-2.1.1-py3-none-any.whl", hash = "sha256:26dee51f1b80cebd6d0ca8e74dd8745419761d3bef34163928cbebbdc4749fdc"},
+    {file = "execnet-2.1.1.tar.gz", hash = "sha256:5189b52c6121c24feae288166ab41b32549c7e2348652736540b9e6e7d4e72e3"},
+]
+
+[package.extras]
+testing = ["hatch", "pre-commit", "pytest", "tox"]
+
 [[package]]
 name = "freezegun"
 version = "1.5.1"
@@ -1234,6 +1248,26 @@ files = [
 tomli = {version = ">=2.0.1,<3.0.0", markers = "python_version < \"3.11\""}
 watchdog = ">=2.0.0"
 
+[[package]]
+name = "pytest-xdist"
+version = "3.6.1"
+description = "pytest xdist plugin for distributed testing, most importantly across multiple CPUs"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "pytest_xdist-3.6.1-py3-none-any.whl", hash = "sha256:9ed4adfb68a016610848639bb7e02c9352d5d9f03d04809919e2dafc3be4cca7"},
+    {file = "pytest_xdist-3.6.1.tar.gz", hash = "sha256:ead156a4db231eec769737f57668ef58a2084a34b2e55c4a8fa20d861107300d"},
+]
+
+[package.dependencies]
+execnet = ">=2.1"
+pytest = ">=7.0.0"
+
+[package.extras]
+psutil = ["psutil (>=3.0)"]
+setproctitle = ["setproctitle"]
+testing = ["filelock"]
+
 [[package]]
 name = "python-dateutil"
 version = "2.9.0.post0"
@@ -1848,4 +1882,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9,<4.0"
-content-hash = "cdb63207c1dc6597eb2ade4ef0f12e56ac128e7277c9952fa35bc6880b537c9e"
+content-hash = "164cc02f120947dbd289f2ad8aa10f714cf2a983121b4b9c088c07fb1e99e8a4"
diff --git a/libs/partners/openai/pyproject.toml b/libs/partners/openai/pyproject.toml
index 3f7a79d9d8426..a7ff513ecd288 100644
--- a/libs/partners/openai/pyproject.toml
+++ b/libs/partners/openai/pyproject.toml
@@ -67,6 +67,7 @@ pytest-watcher = "^0.3.4"
 pytest-asyncio = "^0.21.1"
 pytest-cov = "^4.1.0"
 pytest-socket = "^0.6.0"
+pytest-xdist = "^3.6.1"
 [[tool.poetry.group.test.dependencies.numpy]]
 version = "^1"
 python = "<3.12"
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 a60d60507e156..69cc3f5d0f5be 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
@@ -27,7 +27,6 @@
     magic_function as invalid_magic_function,
 )
 from pydantic import BaseModel, Field
-from typing_extensions import TypedDict
 
 from langchain_openai import ChatOpenAI
 from tests.unit_tests.fake.callbacks import FakeCallbackHandler
@@ -643,7 +642,7 @@ def test_disable_parallel_tool_calling() -> None:
     assert len(result.tool_calls) == 1
 
 
-@pytest.mark.parametrize("model", ["gpt-4o-mini", "o1"])
+@pytest.mark.parametrize("model", ["gpt-4o-mini", "o1", "gpt-4"])
 def test_openai_structured_output(model: str) -> None:
     class MyModel(BaseModel):
         """A Person"""
@@ -658,24 +657,6 @@ class MyModel(BaseModel):
     assert result.age == 27
 
 
-def test_structured_output_errors_with_legacy_models() -> None:
-    class MyModel(BaseModel):
-        """A Person"""
-
-        name: str
-        age: int
-
-    llm = ChatOpenAI(model="gpt-4").with_structured_output(MyModel)
-
-    with pytest.warns(UserWarning, match="with_structured_output"):
-        with pytest.raises(openai.BadRequestError):
-            _ = llm.invoke("I'm a 27 year old named Erick")
-
-    with pytest.warns(UserWarning, match="with_structured_output"):
-        with pytest.raises(openai.BadRequestError):
-            _ = list(llm.stream("I'm a 27 year old named Erick"))
-
-
 def test_openai_proxy() -> None:
     """Test ChatOpenAI with proxy."""
     chat_openai = ChatOpenAI(openai_proxy="http://localhost:8080")
@@ -1221,14 +1202,3 @@ def test_o1_doesnt_stream() -> None:
 def test_o1_stream_default_works() -> None:
     result = list(ChatOpenAI(model="o1").stream("say 'hi'"))
     assert len(result) > 0
-
-
-def test_structured_output_old_model() -> None:
-    class Output(TypedDict):
-        """output."""
-
-        foo: str
-
-    llm = ChatOpenAI(model="gpt-4").with_structured_output(Output)
-    output = llm.invoke("bar")
-    assert "foo" in output