Add summarization task type for HuggingFace APIs (#4721)

# Add summarization task type for HuggingFace APIs

Add summarization task type for HuggingFace APIs.
This task type is described by [HuggingFace inference
API](https://huggingface.co/docs/api-inference/detailed_parameters#summarization-task)

My project utilizes LangChain to connect multiple LLMs, including
various HuggingFace models that support the summarization task.
Integrating this task type is highly convenient and beneficial.

Fixes #4720

tests/integration_tests/llms/test_huggingface_endpoint.py

@@ -33,6 +33,16 @@ def test_huggingface_endpoint_text2text_generation() -> None:
     assert output == "Albany"
 
 
+@unittest.skip(
+    "This test requires an inference endpoint. Tested with Hugging Face endpoints"
+)
+def test_huggingface_endpoint_summarization() -> None:
+    """Test valid call to HuggingFace summarization model."""
+    llm = HuggingFaceEndpoint(endpoint_url="", task="summarization")
+    output = llm("Say foo:")
+    assert isinstance(output, str)
+
+
 def test_huggingface_endpoint_call_error() -> None:
     """Test valid call to HuggingFace that errors."""
     llm = HuggingFaceEndpoint(model_kwargs={"max_new_tokens": -1})

tests/integration_tests/llms/test_huggingface_hub.py

@@ -23,6 +23,13 @@ def test_huggingface_text2text_generation() -> None:
     assert output == "Albany"
 
 
+def test_huggingface_summarization() -> None:
+    """Test valid call to HuggingFace summarization model."""
+    llm = HuggingFaceHub(repo_id="facebook/bart-large-cnn")
+    output = llm("Say foo:")
+    assert isinstance(output, str)
+
+
 def test_huggingface_call_error() -> None:
     """Test valid call to HuggingFace that errors."""
     llm = HuggingFaceHub(model_kwargs={"max_new_tokens": -1})

tests/integration_tests/llms/test_huggingface_pipeline.py

@@ -27,6 +27,15 @@ def test_huggingface_pipeline_text2text_generation() -> None:
     assert isinstance(output, str)
 
 
+def text_huggingface_pipeline_summarization() -> None:
+    """Test valid call to HuggingFace summarization model."""
+    llm = HuggingFacePipeline.from_model_id(
+        model_id="facebook/bart-large-cnn", task="summarization"
+    )
+    output = llm("Say foo:")
+    assert isinstance(output, str)
+
+
 def test_saving_loading_llm(tmp_path: Path) -> None:
     """Test saving/loading an HuggingFaceHub LLM."""
     llm = HuggingFacePipeline.from_model_id(

tests/integration_tests/llms/test_self_hosted_llm.py

@@ -43,6 +43,19 @@ def test_self_hosted_huggingface_pipeline_text2text_generation() -> None:
     assert isinstance(output, str)
 
 
+def test_self_hosted_huggingface_pipeline_summarization() -> None:
+    """Test valid call to self-hosted HuggingFace summarization model."""
+    gpu = get_remote_instance()
+    llm = SelfHostedHuggingFaceLLM(
+        model_id="facebook/bart-large-cnn",
+        task="summarization",
+        hardware=gpu,
+        model_reqs=model_reqs,
+    )
+    output = llm("Say foo:")
+    assert isinstance(output, str)
+
+
 def load_pipeline() -> Any:
     """Load pipeline for testing."""
     model_id = "gpt2"