aiagents4pharma 1.39.0__py3-none-any.whl → 1.39.1__py3-none-any.whl

aiagents4pharma/talk2scholars/tests/test_routing_logic.py

@@ -1,74 +0,0 @@
-"""
-Routing logic for zotero_agent through the main_agent
-"""
-
-import pytest
-from langgraph.types import Command
-from langgraph.graph import END
-from langchain_core.messages import HumanMessage
-from aiagents4pharma.talk2scholars.state.state_talk2scholars import Talk2Scholars
-
-# pylint: disable=redefined-outer-name
-
-
-@pytest.fixture
-def mock_state():
-    """Creates a mock state to simulate an ongoing conversation."""
-    return Talk2Scholars(messages=[])
-
-
-@pytest.fixture
-def mock_router():
-    """Creates a mock supervisor router that routes based on keyword matching."""
-
-    def mock_supervisor_node(state):
-        """Mock supervisor node that routes based on keyword matching."""
-        query = state["messages"][-1].content.lower()
-        # Define keywords for each sub-agent.
-        s2_keywords = [
-            "paper",
-            "research",
-            "citations",
-            "journal",
-            "articles",
-            "references",
-        ]
-        zotero_keywords = ["zotero", "library", "saved papers", "academic library"]
-        pdf_keywords = ["pdf", "document", "read pdf"]
-        paper_download_keywords = ["download", "arxiv", "fetch paper", "paper download"]
-
-        # Priority ordering: Zotero, then paper download, then PDF, then S2.
-        if any(keyword in query for keyword in zotero_keywords):
-            return Command(goto="zotero_agent")
-        if any(keyword in query for keyword in paper_download_keywords):
-            return Command(goto="paper_download_agent")
-        if any(keyword in query for keyword in pdf_keywords):
-            return Command(goto="pdf_agent")
-        if any(keyword in query for keyword in s2_keywords):
-            return Command(goto="s2_agent")
-        # Default to end if no keyword matches.
-        return Command(goto=END)
-
-    return mock_supervisor_node
-
-
-@pytest.mark.parametrize(
-    "user_query,expected_agent",
-    [
-        ("Find papers on deep learning.", "s2_agent"),
-        ("Show me my saved references in Zotero.", "zotero_agent"),
-        ("I need some research articles.", "s2_agent"),
-        ("Fetch my academic library.", "zotero_agent"),
-        ("Retrieve citations.", "s2_agent"),
-        ("Can you get journal articles?", "s2_agent"),
-        ("I want to read the PDF document.", "pdf_agent"),
-        ("Download the paper from arxiv.", "paper_download_agent"),
-        ("Completely unrelated query.", "__end__"),
-    ],
-)
-def test_routing_logic(mock_state, mock_router, user_query, expected_agent):
-    """Tests that the routing logic correctly assigns the right agent or ends conversation."""
-    mock_state["messages"].append(HumanMessage(content=user_query))
-    result = mock_router(mock_state)
-
-    assert result.goto == expected_agent, f"Failed for query: {user_query}"

aiagents4pharma/talk2scholars/tests/test_s2_query.py

@@ -1,95 +0,0 @@
-"""
-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_dataframe import query_dataframe, 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_dataframe_empty_state(self, initial_state):
-        """Tests query_dataframe tool behavior when no papers are found."""
-        with pytest.raises(
-            NoPapersFoundError,
-            match="No papers found. A search needs to be performed first.",
-        ):
-            query_dataframe.invoke(
-                {"question": "List all papers", "state": initial_state}
-            )
-
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.s2.query_dataframe.create_pandas_dataframe_agent"
-    )
-    def test_query_dataframe_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_dataframe is correctly structured
-        result = query_dataframe.invoke({"question": "List all papers", "state": state})
-
-        assert isinstance(result, str)  # Ensure output is a string
-        assert result == "Mocked response"  # Validate the expected response
-
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.s2.query_dataframe.create_pandas_dataframe_agent"
-    )
-    def test_query_dataframe_direct_mapping(self, mock_create_agent, initial_state):
-        """Tests query_dataframe when last_displayed_papers is a direct dict mapping."""
-        # Prepare state with direct mapping
-        state = initial_state.copy()
-        state["last_displayed_papers"] = MOCK_STATE_PAPER
-        # Mock the dataframe agent
-        mock_agent = MagicMock()
-        mock_agent.invoke.return_value = {"output": "Direct mapping response"}
-        mock_create_agent.return_value = mock_agent
-        # Invoke tool
-        result = query_dataframe.invoke({"question": "Filter papers", "state": state})
-        assert isinstance(result, str)
-        assert result == "Direct mapping response"