aiagents4pharma 1.28.0__py3-none-any.whl → 1.29.0__py3-none-any.whl

aiagents4pharma/talk2scholars/tests/test_s2_query.py

@@ -0,0 +1,78 @@
+"""
+Unit tests for S2 tools functionality.
+"""
+
+# pylint: disable=redefined-outer-name
+from unittest.mock import patch
+from unittest.mock import MagicMock
+import pytest
+from ..tools.s2.query_results import query_results, NoPapersFoundError
+
+
+@pytest.fixture
+def initial_state():
+    """Provides an empty initial state for tests."""
+    return {"papers": {}, "multi_papers": {}}
+
+
+# Fixed test data for deterministic results
+MOCK_SEARCH_RESPONSE = {
+    "data": [
+        {
+            "paperId": "123",
+            "title": "Machine Learning Basics",
+            "abstract": "An introduction to ML",
+            "year": 2023,
+            "citationCount": 100,
+            "url": "https://example.com/paper1",
+            "authors": [{"name": "Test Author"}],
+        }
+    ]
+}
+
+MOCK_STATE_PAPER = {
+    "123": {
+        "Title": "Machine Learning Basics",
+        "Abstract": "An introduction to ML",
+        "Year": 2023,
+        "Citation Count": 100,
+        "URL": "https://example.com/paper1",
+    }
+}
+
+
+class TestS2Tools:
+    """Unit tests for individual S2 tools"""
+
+    def test_query_results_empty_state(self, initial_state):
+        """Tests query_results tool behavior when no papers are found."""
+        with pytest.raises(
+            NoPapersFoundError,
+            match="No papers found. A search needs to be performed first.",
+        ):
+            query_results.invoke(
+                {"question": "List all papers", "state": initial_state}
+            )
+
+    @patch(
+        "aiagents4pharma.talk2scholars.tools.s2.query_results.create_pandas_dataframe_agent"
+    )
+    def test_query_results_with_papers(self, mock_create_agent, initial_state):
+        """Tests querying papers when data is available."""
+        state = initial_state.copy()
+        state["last_displayed_papers"] = "papers"
+        state["papers"] = MOCK_STATE_PAPER
+
+        # Mock the dataframe agent instead of the LLM
+        mock_agent = MagicMock()
+        mock_agent.invoke.return_value = {"output": "Mocked response"}
+
+        mock_create_agent.return_value = (
+            mock_agent  # Mock the function returning the agent
+        )
+
+        # Ensure that the output of query_results is correctly structured
+        result = query_results.invoke({"question": "List all papers", "state": state})
+
+        assert isinstance(result, str)  # Ensure output is a string
+        assert result == "Mocked response"  # Validate the expected response

aiagents4pharma/talk2scholars/tests/test_s2_retrieve.py

@@ -0,0 +1,65 @@
+"""
+Unit tests for S2 tools functionality.
+"""
+
+# pylint: disable=redefined-outer-name
+from unittest.mock import patch
+import pytest
+from langgraph.types import Command
+from ..tools.s2.retrieve_semantic_scholar_paper_id import (
+    retrieve_semantic_scholar_paper_id,
+)
+
+
+# Fixed test data for deterministic results
+MOCK_SEARCH_RESPONSE = {
+    "data": [
+        {
+            "paperId": "123",
+            "title": "Machine Learning Basics",
+            "abstract": "An introduction to ML",
+            "year": 2023,
+            "citationCount": 100,
+            "url": "https://example.com/paper1",
+            "authors": [{"name": "Test Author"}],
+        }
+    ]
+}
+
+MOCK_STATE_PAPER = {
+    "123": {
+        "Title": "Machine Learning Basics",
+        "Abstract": "An introduction to ML",
+        "Year": 2023,
+        "Citation Count": 100,
+        "URL": "https://example.com/paper1",
+    }
+}
+
+
+class TestS2Tools:
+    """Unit tests for individual S2 tools"""
+
+    @patch("requests.get")
+    def test_retrieve_semantic_scholar_paper_id(self, mock_get):
+        """Tests retrieving a paper ID from Semantic Scholar."""
+        mock_get.return_value.json.return_value = MOCK_SEARCH_RESPONSE
+        mock_get.return_value.status_code = 200
+
+        result = retrieve_semantic_scholar_paper_id.invoke(
+            input={"paper_title": "Machine Learning Basics", "tool_call_id": "test123"}
+        )
+
+        assert isinstance(result, Command)
+        assert "messages" in result.update
+        assert (
+            "Paper ID for 'Machine Learning Basics' is: 123"
+            in result.update["messages"][0].content
+        )
+
+    def test_retrieve_semantic_scholar_paper_id_no_results(self):
+        """Test retrieving a paper ID when no results are found."""
+        with pytest.raises(ValueError, match="No papers found for query: UnknownPaper"):
+            retrieve_semantic_scholar_paper_id.invoke(
+                input={"paper_title": "UnknownPaper", "tool_call_id": "test123"}
+            )

aiagents4pharma/talk2scholars/tests/test_s2_search.py

@@ -0,0 +1,266 @@
+"""
+Unit tests for S2 tools functionality.
+"""
+
+from types import SimpleNamespace
+import pytest
+import hydra
+import requests
+from langgraph.types import Command
+from langchain_core.messages import ToolMessage
+from aiagents4pharma.talk2scholars.tools.s2.search import search_tool
+
+# --- Dummy Hydra Config Setup ---
+
+
+class DummyHydraContext:
+    """hydra.initialize context manager that does nothing."""
+
+    def __enter__(self):
+        return None
+
+    def __exit__(self, exc_type, exc_val, traceback):
+        return None
+
+
+# Create a dummy configuration that mimics the expected hydra config
+dummy_config = SimpleNamespace(
+    tools=SimpleNamespace(
+        search=SimpleNamespace(
+            api_endpoint="http://dummy.endpoint",
+            api_fields=["paperId", "title", "authors"],
+        )
+    )
+)
+
+# --- Dummy Response Classes and Functions for requests.get ---
+
+
+class DummyResponse:
+    """A dummy response class for mocking HTTP responses."""
+
+    def __init__(self, json_data, status_code=200):
+        """initialize a DummyResponse with the given JSON data and status code."""
+        self._json_data = json_data
+        self.status_code = status_code
+
+    def json(self):
+        """access the JSON data from the response."""
+        return self._json_data
+
+    def raise_for_status(self):
+        """Raise an HTTP error for status codes >= 400."""
+        if self.status_code >= 400:
+            raise requests.HTTPError("HTTP Error")
+
+
+def test_dummy_response_no_error():
+    """Test that raise_for_status does not raise an exception for a successful response."""
+    # Create a DummyResponse with a successful status code.
+    response = DummyResponse({"data": "success"}, status_code=200)
+    # Calling raise_for_status should not raise an exception and should return None.
+    assert response.raise_for_status() is None
+
+
+def test_dummy_response_raise_error():
+    """Test that raise_for_status raises an exception for a failing response."""
+    # Create a DummyResponse with a failing status code.
+    response = DummyResponse({"error": "fail"}, status_code=400)
+    # Calling raise_for_status should raise an HTTPError.
+    with pytest.raises(requests.HTTPError):
+        response.raise_for_status()
+
+
+def dummy_requests_get_success(url, params, timeout):
+    """A dummy requests.get function that returns a successful response."""
+    # Record call parameters for assertions
+    dummy_requests_get_success.called_url = url
+    dummy_requests_get_success.called_params = params
+    dummy_requests_get_success.called_timeout = timeout
+
+    # Simulate a valid API response with three papers;
+    # one paper missing authors should be filtered out.
+    dummy_data = {
+        "data": [
+            {
+                "paperId": "1",
+                "title": "Paper 1",
+                "authors": ["Author A"],
+                "year": 2020,
+                "citationCount": 10,
+                "url": "http://paper1",
+                "externalIds": {"ArXiv": "arxiv1"},
+            },
+            {
+                "paperId": "2",
+                "title": "Paper 2",
+                "authors": ["Author B"],
+                "year": 2021,
+                "citationCount": 20,
+                "url": "http://paper2",
+                "externalIds": {},
+            },
+            {
+                "paperId": "3",
+                "title": "Paper 3",
+                "authors": None,  # This paper should be filtered out.
+                "year": 2022,
+                "citationCount": 30,
+                "url": "http://paper3",
+                "externalIds": {"ArXiv": "arxiv3"},
+            },
+        ]
+    }
+    return DummyResponse(dummy_data)
+
+
+def dummy_requests_get_no_data(url, params, timeout):
+    """A dummy requests.get function that returns a response without the expected 'data' key."""
+    dummy_requests_get_no_data.called_url = url
+    dummy_requests_get_no_data.called_params = params
+    dummy_requests_get_no_data.called_timeout = timeout
+    # Simulate a response with an unexpected format (missing "data" key)
+    return DummyResponse({"error": "Invalid format"})
+
+
+def dummy_requests_get_no_papers(url, params, timeout):
+    """A dummy requests.get function that returns a response with an empty papers list."""
+    dummy_requests_get_no_papers.called_url = url
+    dummy_requests_get_no_papers.called_params = params
+    dummy_requests_get_no_papers.called_timeout = timeout
+    # Simulate a response with an empty papers list.
+    return DummyResponse({"data": []})
+
+
+def dummy_requests_get_exception(url, params, timeout):
+    """A dummy requests.get function that raises an exception."""
+    dummy_requests_get_exception.called_url = url
+    dummy_requests_get_exception.called_params = params
+    dummy_requests_get_exception.called_timeout = timeout
+    # Simulate a network/connection exception.
+    raise requests.exceptions.RequestException("Connection error")
+
+
+# --- Pytest Fixture to Patch Hydra ---
+@pytest.fixture(autouse=True)
+def patch_hydra(monkeypatch):
+    """hydra patch to mock initialize and compose functions."""
+    # Patch hydra.initialize to return our dummy context manager.
+    monkeypatch.setattr(
+        hydra, "initialize", lambda version_base, config_path: DummyHydraContext()
+    )
+    # Patch hydra.compose to return our dummy config.
+    monkeypatch.setattr(hydra, "compose", lambda config_name, overrides: dummy_config)
+
+
+# --- Test Cases ---
+
+
+def test_search_tool_success(monkeypatch):
+    """
+    Test that search_tool returns a valid Command object when the API response is successful.
+    Also checks that papers without required fields are filtered out.
+    """
+    monkeypatch.setattr(requests, "get", dummy_requests_get_success)
+
+    tool_call_id = "test_tool_call_id"
+    # Invoke using .run() with a dictionary input.
+    result = search_tool.run(
+        {
+            "query": "machine learning",
+            "tool_call_id": tool_call_id,
+            "limit": 3,
+            "year": "2020",
+        }
+    )
+
+    # Check that a Command is returned with the expected update structure.
+    assert isinstance(result, Command)
+    update = result.update
+    assert "papers" in update
+
+    papers = update["papers"]
+    # Papers with valid 'title' and 'authors' should be included.
+    assert "1" in papers
+    assert "2" in papers
+    # Paper "3" is missing authors and should be filtered out.
+    assert "3" not in papers
+
+    # Check that a ToolMessage is included in the messages.
+    messages = update.get("messages", [])
+    assert len(messages) == 1
+    msg = messages[0]
+    assert isinstance(msg, ToolMessage)
+    assert "Number of papers found:" in msg.content
+
+    # Verify that the correct parameters were sent to requests.get.
+    called_params = dummy_requests_get_success.called_params
+    assert called_params["query"] == "machine learning"
+    # The "year" parameter should have been added.
+    assert called_params["year"] == "2020"
+    # The limit is set to min(limit, 100) so it should be 3.
+    assert called_params["limit"] == 3
+    # The fields should be a comma-separated string from the dummy config.
+    assert called_params["fields"] == "paperId,title,authors"
+
+
+def test_search_tool_unexpected_format(monkeypatch):
+    """
+    Test that search_tool raises a RuntimeError when the API response
+    does not include the expected 'data' key.
+    """
+    monkeypatch.setattr(requests, "get", dummy_requests_get_no_data)
+    tool_call_id = "test_tool_call_id"
+    with pytest.raises(
+        RuntimeError,
+        match=(
+            "Unexpected response from Semantic Scholar API. The results could not be "
+            "retrieved due to an unexpected format. "
+            "Please modify your search query and try again."
+        ),
+    ):
+        search_tool.run(
+            {
+                "query": "test",
+                "tool_call_id": tool_call_id,
+            }
+        )
+
+
+def test_search_tool_no_papers(monkeypatch):
+    """
+    Test that search_tool raises a RuntimeError when the API returns no papers.
+    """
+    monkeypatch.setattr(requests, "get", dummy_requests_get_no_papers)
+    tool_call_id = "test_tool_call_id"
+    with pytest.raises(
+        RuntimeError,
+        match=(
+            "No papers were found for your query. Consider refining your search "
+            "by using more specific keywords or different terms."
+        ),
+    ):
+        search_tool.run(
+            {
+                "query": "test",
+                "tool_call_id": tool_call_id,
+            }
+        )
+
+
+def test_search_tool_requests_exception(monkeypatch):
+    """
+    Test that search_tool raises a RuntimeError when requests.get throws an exception.
+    """
+    monkeypatch.setattr(requests, "get", dummy_requests_get_exception)
+    tool_call_id = "test_tool_call_id"
+    with pytest.raises(
+        RuntimeError,
+        match="Failed to connect to Semantic Scholar API. Please retry the same query.",
+    ):
+        search_tool.run(
+            {
+                "query": "test",
+                "tool_call_id": tool_call_id,
+            }
+        )

aiagents4pharma/talk2scholars/tests/test_s2_single.py

@@ -0,0 +1,274 @@
+"""
+Unit tests for S2 tools functionality.
+"""
+
+from types import SimpleNamespace
+import pytest
+import requests
+import hydra
+from langgraph.types import Command
+from langchain_core.messages import ToolMessage
+from aiagents4pharma.talk2scholars.tools.s2.single_paper_rec import (
+    get_single_paper_recommendations,
+)
+
+# --- Dummy Hydra Config Setup ---
+
+
+class DummyHydraContext:
+    """
+    A dummy context manager for mocking Hydra's initialize and compose functions.
+    """
+
+    def __enter__(self):
+        return None
+
+    def __exit__(self, exc_val, exc_type, traceback):
+        pass
+
+
+# Create a dummy configuration that mimics the expected Hydra config
+dummy_config = SimpleNamespace(
+    tools=SimpleNamespace(
+        single_paper_recommendation=SimpleNamespace(
+            api_endpoint="http://dummy.endpoint",
+            api_fields=["paperId", "title", "authors"],
+            recommendation_params=SimpleNamespace(from_pool="default_pool"),
+            request_timeout=10,
+        )
+    )
+)
+
+# --- Dummy Response Classes and Functions for requests.get ---
+
+
+class DummyResponse:
+    """
+    A dummy response class for mocking HTTP responses.
+    """
+
+    def __init__(self, json_data, status_code=200):
+        """Initialize a DummyResponse with the given JSON data and status code."""
+        self._json_data = json_data
+        self.status_code = status_code
+
+    def json(self):
+        """Return the JSON data from the response."""
+        return self._json_data
+
+    def raise_for_status(self):
+        """Raise an HTTP error for status codes >= 400."""
+        if self.status_code >= 400:
+            raise requests.HTTPError("HTTP Error")
+
+
+def test_dummy_response_no_error():
+    """Test DummyResponse does not raise an error for 200 status code."""
+    response = DummyResponse({"data": "success"}, status_code=200)
+    # Calling raise_for_status should not raise an exception and should return None.
+    assert response.raise_for_status() is None
+
+
+def test_dummy_response_raise_error():
+    """Test DummyResponse raises an HTTPError for status codes >= 400."""
+    response = DummyResponse({"error": "fail"}, status_code=400)
+    # Calling raise_for_status should raise an HTTPError.
+    with pytest.raises(requests.HTTPError):
+        response.raise_for_status()
+
+
+def dummy_requests_get_success(url, params, timeout):
+    """
+    Dummy function to simulate a successful API request returning recommended papers.
+    """
+    dummy_requests_get_success.called_url = url
+    dummy_requests_get_success.called_params = params
+    dummy_requests_get_success.called_timeout = timeout
+
+    # Simulate a valid API response with three recommended papers;
+    # one paper missing authors should be filtered out.
+    dummy_data = {
+        "recommendedPapers": [
+            {
+                "paperId": "paper1",
+                "title": "Recommended Paper 1",
+                "authors": ["Author A"],
+                "year": 2020,
+                "citationCount": 15,
+                "url": "http://paper1",
+                "externalIds": {"ArXiv": "arxiv1"},
+            },
+            {
+                "paperId": "paper2",
+                "title": "Recommended Paper 2",
+                "authors": ["Author B"],
+                "year": 2021,
+                "citationCount": 25,
+                "url": "http://paper2",
+                "externalIds": {},
+            },
+            {
+                "paperId": "paper3",
+                "title": "Recommended Paper 3",
+                "authors": None,  # This paper should be filtered out.
+                "year": 2022,
+                "citationCount": 35,
+                "url": "http://paper3",
+                "externalIds": {"ArXiv": "arxiv3"},
+            },
+        ]
+    }
+    return DummyResponse(dummy_data)
+
+
+def dummy_requests_get_unexpected(url, params, timeout):
+    """
+    Dummy function to simulate an API response with an unexpected format.
+    """
+    dummy_requests_get_unexpected.called_url = url
+    dummy_requests_get_unexpected.called_params = params
+    dummy_requests_get_unexpected.called_timeout = timeout
+    return DummyResponse({"error": "Invalid format"})
+
+
+def dummy_requests_get_no_recs(url, params, timeout):
+    """
+    Dummy function to simulate an API response returning no recommendations.
+    """
+    dummy_requests_get_no_recs.called_url = url
+    dummy_requests_get_no_recs.called_params = params
+    dummy_requests_get_no_recs.called_timeout = timeout
+    return DummyResponse({"recommendedPapers": []})
+
+
+def dummy_requests_get_exception(url, params, timeout):
+    """
+    Dummy function to simulate a request exception (e.g., network failure).
+    """
+    dummy_requests_get_exception.called_url = url
+    dummy_requests_get_exception.called_params = params
+    dummy_requests_get_exception.called_timeout = timeout
+    raise requests.exceptions.RequestException("Connection error")
+
+
+# --- Pytest Fixture to Patch Hydra ---
+@pytest.fixture(autouse=True)
+def patch_hydra(monkeypatch):
+    """Patch Hydra's initialize and compose functions with dummy implementations."""
+    monkeypatch.setattr(
+        hydra, "initialize", lambda version_base, config_path: DummyHydraContext()
+    )
+    # Patch hydra.compose to return our dummy config.
+    monkeypatch.setattr(hydra, "compose", lambda config_name, overrides: dummy_config)
+
+
+# --- Test Cases ---
+
+
+def test_single_paper_rec_success(monkeypatch):
+    """
+    Test that get_single_paper_recommendations returns a valid Command object
+    when the API response is successful. Also, ensure that recommendations missing
+    required fields (like authors) are filtered out.
+    """
+    monkeypatch.setattr(requests, "get", dummy_requests_get_success)
+
+    tool_call_id = "test_tool_call_id"
+    input_data = {
+        "paper_id": "12345",
+        "tool_call_id": tool_call_id,
+        "limit": 3,
+        "year": "2020",
+    }
+    # Invoke the tool using .run() with a single dictionary as input.
+    result = get_single_paper_recommendations.run(input_data)
+
+    # Validate that the result is a Command with the expected structure.
+    assert isinstance(result, Command)
+    update = result.update
+    assert "papers" in update
+
+    papers = update["papers"]
+    # Papers with valid 'title' and 'authors' should be included.
+    assert "paper1" in papers
+    assert "paper2" in papers
+    # Paper "paper3" is missing authors and should be filtered out.
+    assert "paper3" not in papers
+
+    # Check that a ToolMessage is included in the messages.
+    messages = update.get("messages", [])
+    assert len(messages) == 1
+    msg = messages[0]
+    assert isinstance(msg, ToolMessage)
+    assert "Recommendations based on the single paper were successful" in msg.content
+
+    # Verify that the correct parameters were sent to requests.get.
+    called_params = dummy_requests_get_success.called_params
+    assert called_params["limit"] == 3  # limited to min(limit, 500)
+    # "fields" should be a comma-separated string from the dummy config.
+    assert called_params["fields"] == "paperId,title,authors"
+    # Check that the "from" parameter is set from our dummy config.
+    assert called_params["from"] == "default_pool"
+    # The year parameter should be present.
+    assert called_params["year"] == "2020"
+
+
+def test_single_paper_rec_unexpected_format(monkeypatch):
+    """
+    Test that get_single_paper_recommendations raises a RuntimeError when the API
+    response does not include the expected 'recommendedPapers' key.
+    """
+    monkeypatch.setattr(requests, "get", dummy_requests_get_unexpected)
+    tool_call_id = "test_tool_call_id"
+    input_data = {
+        "paper_id": "12345",
+        "tool_call_id": tool_call_id,
+    }
+    with pytest.raises(
+        RuntimeError,
+        match=(
+            "Unexpected response from Semantic Scholar API. The results could not be "
+            "retrieved due to an unexpected format. "
+            "Please modify your search query and try again."
+        ),
+    ):
+        get_single_paper_recommendations.run(input_data)
+
+
+def test_single_paper_rec_no_recommendations(monkeypatch):
+    """
+    Test that get_single_paper_recommendations raises a RuntimeError when the API
+    returns no recommendations.
+    """
+    monkeypatch.setattr(requests, "get", dummy_requests_get_no_recs)
+    tool_call_id = "test_tool_call_id"
+    input_data = {
+        "paper_id": "12345",
+        "tool_call_id": tool_call_id,
+    }
+    with pytest.raises(
+        RuntimeError,
+        match=(
+            "No recommendations were found for your query. Consider refining your search "
+            "by using more specific keywords or different terms."
+        ),
+    ):
+        get_single_paper_recommendations.run(input_data)
+
+
+def test_single_paper_rec_requests_exception(monkeypatch):
+    """
+    Test that get_single_paper_recommendations raises a RuntimeError when requests.get
+    throws an exception.
+    """
+    monkeypatch.setattr(requests, "get", dummy_requests_get_exception)
+    tool_call_id = "test_tool_call_id"
+    input_data = {
+        "paper_id": "12345",
+        "tool_call_id": tool_call_id,
+    }
+    with pytest.raises(
+        RuntimeError,
+        match="Failed to connect to Semantic Scholar API. Please retry the same query.",
+    ):
+        get_single_paper_recommendations.run(input_data)