huggingface[patch]: add integration tests (#26269)

Add standard tests for ChatHuggingFace. About half of these fail
currently.

.github/workflows/_integration_test.yml

@@ -67,6 +67,7 @@ jobs:
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
+          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
           NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
           WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}

.github/workflows/_release.yml

@@ -273,6 +273,7 @@ jobs:
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
           GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
           NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
           WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}

.github/workflows/scheduled_test.yml

@@ -90,6 +90,7 @@ jobs:
           AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
           GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}

libs/partners/huggingface/tests/integration_tests/test_standard.py

@@ -0,0 +1,78 @@
+"""Standard LangChain interface tests"""
+
+from typing import Type
+
+import pytest
+from langchain_core.language_models import BaseChatModel
+from langchain_standard_tests.integration_tests import ChatModelIntegrationTests
+
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
+
+
+class TestHuggingFaceEndpoint(ChatModelIntegrationTests):
+    @property
+    def chat_model_class(self) -> Type[BaseChatModel]:
+        return ChatHuggingFace
+
+    @property
+    def chat_model_params(self) -> dict:
+        return {}
+
+    @pytest.fixture
+    def model(self) -> BaseChatModel:
+        llm = HuggingFaceEndpoint(  # type: ignore[call-arg]
+            repo_id="HuggingFaceH4/zephyr-7b-beta",
+            task="text-generation",
+            max_new_tokens=512,
+            do_sample=False,
+            repetition_penalty=1.03,
+        )
+        return self.chat_model_class(llm=llm)  # type: ignore[call-arg]
+
+    @pytest.mark.xfail(reason=("Not implemented"))
+    def test_stream(self, model: BaseChatModel) -> None:
+        super().test_stream(model)
+
+    @pytest.mark.xfail(reason=("Not implemented"))
+    async def test_astream(self, model: BaseChatModel) -> None:
+        await super().test_astream(model)
+
+    @pytest.mark.xfail(reason=("Not implemented"))
+    def test_usage_metadata(self, model: BaseChatModel) -> None:
+        super().test_usage_metadata(model)
+
+    @pytest.mark.xfail(reason=("Not implemented"))
+    def test_usage_metadata_streaming(self, model: BaseChatModel) -> None:
+        super().test_usage_metadata_streaming(model)
+
+    @pytest.mark.xfail(reason=("Not implemented"))
+    def test_stop_sequence(self, model: BaseChatModel) -> None:
+        super().test_stop_sequence(model)
+
+    @pytest.mark.xfail(reason=("Not implemented"))
+    def test_tool_calling(self, model: BaseChatModel) -> None:
+        super().test_tool_calling(model)
+
+    @pytest.mark.xfail(reason=("Not implemented"))
+    def test_tool_calling_with_no_arguments(self, model: BaseChatModel) -> None:
+        super().test_tool_calling_with_no_arguments(model)
+
+    @pytest.mark.xfail(reason=("Not implemented"))
+    def test_bind_runnables_as_tools(self, model: BaseChatModel) -> None:
+        super().test_bind_runnables_as_tools(model)
+
+    @pytest.mark.xfail(reason=("Not implemented"))
+    def test_structured_output(self, model: BaseChatModel) -> None:
+        super().test_structured_output(model)
+
+    @pytest.mark.xfail(reason=("Not implemented"))
+    def test_structured_output_pydantic_2_v1(self, model: BaseChatModel) -> None:
+        super().test_structured_output_pydantic_2_v1(model)
+
+    @pytest.mark.xfail(reason=("Not implemented"))
+    def test_tool_message_histories_list_content(self, model: BaseChatModel) -> None:
+        super().test_tool_message_histories_list_content(model)
+
+    @pytest.mark.xfail(reason=("Not implemented"))
+    def test_structured_few_shot_examples(self, model: BaseChatModel) -> None:
+        super().test_structured_few_shot_examples(model)