aiagents4pharma 1.42.0__py3-none-any.whl → 1.43.0__py3-none-any.whl

aiagents4pharma/talk2scholars/tests/test_paper_download_medrxiv.py

@@ -1,151 +0,0 @@
-"""
-Unit tests for medrXiv paper downloading functionality, including:
-- download_medrxiv_paper tool function.
-"""
-
-import unittest
-from unittest.mock import MagicMock, patch
-from langchain_core.messages import ToolMessage
-
-from aiagents4pharma.talk2scholars.tools.paper_download.download_medrxiv_input import (
-    download_medrxiv_paper,
-)
-
-
-class TestDownloadMedrxivPaper(unittest.TestCase):
-    """Tests for the download_medrxiv_paper tool."""
-
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_medrxiv_input.hydra.initialize"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_medrxiv_input.hydra.compose"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_medrxiv_input.requests.get"
-    )
-    def test_download_medrxiv_paper_success(self, mock_get, mock_compose, mock_initialize):
-        """Test successful metadata and PDF URL retrieval."""
-        dummy_cfg = MagicMock()
-        dummy_cfg.tools.download_medrxiv_paper.api_url = "http://dummy.medrxiv.org/api"
-        dummy_cfg.tools.download_medrxiv_paper.request_timeout = 10
-        mock_compose.return_value = dummy_cfg
-        mock_initialize.return_value.__enter__.return_value = None
-
-        doi = "10.1101/2025.04.25.25326432"
-
-        dummy_response = MagicMock()
-        dummy_response.status_code = 200
-        dummy_response.raise_for_status = MagicMock()
-        dummy_response.json.return_value = {
-            "collection": [
-                {
-                    "title": "Sample Medrxiv Paper",
-                    "authors": "Author One; Author Two",
-                    "abstract": "This is a medRxiv abstract.",
-                    "date": "2025-04-25",
-                    "doi": doi,
-                    "link": f"https://www.medrxiv.org/content/{doi}.full.pdf"
-                }
-            ]
-        }
-        mock_get.return_value = dummy_response
-
-        tool_input = {"doi": doi, "tool_call_id": "test_tool_id"}
-        result = download_medrxiv_paper.run(tool_input)
-        update = result.update
-
-        self.assertIn("article_data", update)
-        self.assertIn(doi, update["article_data"])
-        metadata = update["article_data"][doi]
-        self.assertEqual(metadata["Title"], "Sample Medrxiv Paper")
-        self.assertEqual(metadata["Authors"], "Author One; Author Two")
-        self.assertEqual(metadata["Abstract"], "This is a medRxiv abstract.")
-        self.assertEqual(metadata["Publication Date"], "2025-04-25")
-        self.assertEqual(metadata["URL"], f"https://www.medrxiv.org/content/{doi}.full.pdf")
-        self.assertEqual(metadata["pdf_url"], f"https://www.medrxiv.org/content/{doi}.full.pdf")
-        self.assertEqual(metadata["filename"], f"{doi.rsplit('/', maxsplit=1)[-1]}.pdf")
-        self.assertEqual(metadata["source"], "medrxiv")
-        self.assertEqual(metadata["medrxiv_id"], doi)
-
-        self.assertTrue(len(update["messages"]) >= 1)
-        self.assertIsInstance(update["messages"][0], ToolMessage)
-        self.assertIn("Successfully retrieved metadata and PDF URL", update["messages"][0].content)
-
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_medrxiv_input.hydra.initialize"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_medrxiv_input.hydra.compose"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_medrxiv_input.requests.get"
-    )
-    def test_no_entry_found(self, mock_get, mock_compose, mock_initialize):
-        """Test behavior when no 'entry' is in response."""
-        dummy_cfg = MagicMock()
-        dummy_cfg.tools.download_medrxiv_paper.api_url = "http://dummy.medrxiv.org/api"
-        dummy_cfg.tools.download_medrxiv_paper.request_timeout = 10
-        mock_compose.return_value = dummy_cfg
-        mock_initialize.return_value.__enter__.return_value = None
-
-        dummy_response = MagicMock()
-        dummy_response.status_code = 200
-        dummy_response.raise_for_status = MagicMock()
-        dummy_response.json.return_value = {}  # No entry
-        mock_get.return_value = dummy_response
-
-        doi = "10.1101/2025.04.25.25326432"
-        tool_input = {"doi": doi, "tool_call_id": "test_tool_id"}
-
-        with self.assertRaises(ValueError) as context:
-            download_medrxiv_paper.run(tool_input)
-
-        self.assertEqual(str(context.exception), f"No entry found for medRxiv ID {doi}")
-
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_medrxiv_input.hydra.initialize"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_medrxiv_input.hydra.compose"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_medrxiv_input.requests.get"
-    )
-    def test_no_pdf_url_found(self, mock_get, mock_compose, mock_initialize):
-        """Test fallback to DOI-based PDF URL construction when 'link' is missing."""
-        dummy_cfg = MagicMock()
-        dummy_cfg.tools.download_medrxiv_paper.api_url = "http://dummy.medrxiv.org/api"
-        dummy_cfg.tools.download_medrxiv_paper.request_timeout = 10
-        mock_compose.return_value = dummy_cfg
-        mock_initialize.return_value.__enter__.return_value = None
-
-        doi = "10.1101/2025.04.25.25326432"
-
-        dummy_response = MagicMock()
-        dummy_response.status_code = 200
-        dummy_response.raise_for_status = MagicMock()
-        dummy_response.json.return_value = {
-            "collection": [
-                {
-                    "title": "Sample Medrxiv Paper",
-                    "authors": "Author One; Author Two",
-                    "abstract": "This is a medRxiv abstract.",
-                    "date": "2025-04-25",
-                    "doi": doi
-                    # 'link' is intentionally omitted
-                }
-            ]
-        }
-        mock_get.return_value = dummy_response
-
-        tool_input = {"doi": doi, "tool_call_id": "test_tool_id"}
-        result = download_medrxiv_paper.run(tool_input)
-        update = result.update
-        metadata = update["article_data"][doi]
-
-        # Assert that the PDF URL was constructed from DOI
-        expected_suffix = doi.rsplit('/', maxsplit=1)[-1]
-        expected_url = f"https://www.medrxiv.org/content/10.1101/{expected_suffix}.full.pdf"
-
-        self.assertEqual(metadata["pdf_url"], expected_url)

aiagents4pharma/talk2scholars/tests/test_paper_download_tools.py

@@ -1,249 +0,0 @@
-"""
-Unit tests for arXiv paper downloading functionality, including:
-- download_arxiv_paper tool function.
-"""
-
-import unittest
-from unittest.mock import MagicMock, patch
-
-import pytest
-from langchain_core.messages import ToolMessage
-
-from aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input import (
-    _get_snippet,
-    download_arxiv_paper,
-)
-
-
-class TestDownloadArxivPaper(unittest.TestCase):
-    """tests for the download_arxiv_paper tool."""
-
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input.hydra.initialize"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input.hydra.compose"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input.requests.get"
-    )
-    def test_download_arxiv_paper_success(
-        self, mock_get, mock_compose, mock_initialize
-    ):
-        """test the download_arxiv_paper tool for successful retrieval of metadata and PDF URL."""
-        # Set up a dummy Hydra config.
-        dummy_cfg = MagicMock()
-        dummy_cfg.tools.download_arxiv_paper.api_url = "http://dummy.arxiv.org/api"
-        dummy_cfg.tools.download_arxiv_paper.request_timeout = 10
-        mock_compose.return_value = dummy_cfg
-        mock_initialize.return_value.__enter__.return_value = None
-
-        # Set up a dummy XML response with a valid entry including a pdf link.
-        arxiv_id = "1234.56789"
-        dummy_response = MagicMock()
-        dummy_response.text = (
-            f"""<?xml version=\"1.0\" encoding=\"UTF-8\"?>
-        <feed xmlns=\"http://www.w3.org/2005/Atom\">"""
-            f"            <entry>"
-            f"<title>Sample Paper Title</title>"
-            f"<author><name>Author One</name></author>"
-            f"<author><name>Author Two</name></author>"
-            f"<summary>This is a sample abstract.</summary>"
-            f"<published>2020-01-01T00:00:00Z</published>"
-            f'<link title="pdf" href="http://arxiv.org/pdf/{arxiv_id}v1"/>'
-            f"</entry></feed>"
-        )
-        dummy_response.raise_for_status = MagicMock()
-        mock_get.return_value = dummy_response
-
-        tool_call_id = "test_tool_id"
-        tool_input = {"arxiv_ids": [arxiv_id], "tool_call_id": tool_call_id}
-        result = download_arxiv_paper.run(tool_input)
-        update = result.update
-
-        # Check that article_data was correctly set.
-        self.assertIn("article_data", update)
-        self.assertIn(arxiv_id, update["article_data"])
-        metadata = update["article_data"][arxiv_id]
-        self.assertEqual(metadata["Title"], "Sample Paper Title")
-        self.assertEqual(metadata["Authors"], ["Author One", "Author Two"])
-        self.assertEqual(metadata["Abstract"], "This is a sample abstract.")
-        self.assertEqual(metadata["Publication Date"], "2020-01-01T00:00:00Z")
-        self.assertEqual(metadata["URL"], f"http://arxiv.org/pdf/{arxiv_id}v1")
-        self.assertEqual(metadata["pdf_url"], f"http://arxiv.org/pdf/{arxiv_id}v1")
-        self.assertEqual(metadata["filename"], f"{arxiv_id}.pdf")
-        self.assertEqual(metadata["source"], "arxiv")
-        self.assertEqual(metadata["arxiv_id"], arxiv_id)
-
-        # Check that the message content matches the new summary format
-        messages = update["messages"]
-        self.assertEqual(len(messages), 1)
-        self.assertIsInstance(messages[0], ToolMessage)
-        content = messages[0].content
-        # Build expected summary
-        expected = (
-            "Download was successful. Papers metadata are attached as an artifact. "
-            "Here is a summary of the results:\n"
-            f"Number of papers found: 1\n"
-            "Top 3 papers:\n"
-            f"1. Sample Paper Title (2020-01-01T00:00:00Z)\n"
-            f"   View PDF: http://arxiv.org/pdf/{arxiv_id}v1\n"
-            "   Abstract snippet: This is a sample abstract."
-        )
-        self.assertEqual(content, expected)
-
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input.hydra.initialize"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input.hydra.compose"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input.requests.get"
-    )
-    def test_no_entry_found(self, mock_get, mock_compose, mock_initialize):
-        """test the download_arxiv_paper tool for no entry found in XML response."""
-        # Dummy config as before.
-        dummy_cfg = MagicMock()
-        dummy_cfg.tools.download_arxiv_paper.api_url = "http://dummy.arxiv.org/api"
-        dummy_cfg.tools.download_arxiv_paper.request_timeout = 10
-        mock_compose.return_value = dummy_cfg
-        mock_initialize.return_value.__enter__.return_value = None
-
-        # Set up XML with no entry element.
-        arxiv_id = "1234.56789"
-        dummy_xml = (
-            """<?xml version="1.0" encoding="UTF-8"?>"""
-            """<feed xmlns="http://www.w3.org/2005/Atom"></feed>"""
-        )
-        dummy_response = MagicMock()
-        dummy_response.text = dummy_xml
-        dummy_response.raise_for_status = MagicMock()
-        mock_get.return_value = dummy_response
-
-        tool_call_id = "test_tool_id"
-        tool_input = {"arxiv_ids": [arxiv_id], "tool_call_id": tool_call_id}
-        # No entry found should result in empty article_data and header-only summary
-        result = download_arxiv_paper.run(tool_input)
-        update = result.update
-        self.assertIn("article_data", update)
-        self.assertEqual(update["article_data"], {})
-        messages = update.get("messages", [])
-        self.assertEqual(len(messages), 1)
-        content = messages[0].content
-        expected = (
-            "Download was successful. Papers metadata are attached as an artifact. "
-            "Here is a summary of the results:\n"
-            "Number of papers found: 0\n"
-            "Top 3 papers:\n"
-        )
-        self.assertEqual(content, expected)
-
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input.hydra.initialize"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input.hydra.compose"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input.requests.get"
-    )
-    def test_no_pdf_url_found(self, mock_get, mock_compose, mock_initialize):
-        """test the download_arxiv_paper tool for no PDF URL found in XML response."""
-        # Dummy config.
-        dummy_cfg = MagicMock()
-        dummy_cfg.tools.download_arxiv_paper.api_url = "http://dummy.arxiv.org/api"
-        dummy_cfg.tools.download_arxiv_paper.request_timeout = 10
-        mock_compose.return_value = dummy_cfg
-        mock_initialize.return_value.__enter__.return_value = None
-
-        # Set up XML with an entry that does not contain a pdf link.
-        arxiv_id = "1234.56789"
-        dummy_xml = """<?xml version="1.0" encoding="UTF-8"?>
-        <feed xmlns="http://www.w3.org/2005/Atom">
-            <entry>
-                <title>Sample Paper Title</title>
-                <author>
-                    <name>Author One</name>
-                </author>
-                <summary>This is a sample abstract.</summary>
-                <published>2020-01-01T00:00:00Z</published>
-                <!-- Missing pdf link -->
-            </entry>
-        </feed>
-        """
-        dummy_response = MagicMock()
-        dummy_response.text = dummy_xml
-        dummy_response.raise_for_status = MagicMock()
-        mock_get.return_value = dummy_response
-
-        tool_call_id = "test_tool_id"
-        tool_input = {"arxiv_ids": [arxiv_id], "tool_call_id": tool_call_id}
-        with self.assertRaises(RuntimeError) as context:
-            download_arxiv_paper.run(tool_input)
-        self.assertEqual(
-            str(context.exception), f"Could not find PDF URL for arXiv ID {arxiv_id}"
-        )
-
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input.extract_metadata"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_"
-        "arxiv_input.fetch_arxiv_metadata"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input.hydra.compose"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input.hydra.initialize"
-    )
-    def test_summary_multiple_papers(
-        self, mock_initialize, mock_compose, _mock_fetch, mock_extract
-    ):
-        """Test summary includes '...and N more papers.' when more than 3 papers."""
-        # Dummy config
-        dummy_cfg = MagicMock()
-        dummy_cfg.tools.download_arxiv_paper.api_url = "http://dummy"
-        dummy_cfg.tools.download_arxiv_paper.request_timeout = 5
-        mock_compose.return_value = dummy_cfg
-        mock_initialize.return_value.__enter__.return_value = None
-
-        # Simulate metadata extraction for multiple papers
-        def dummy_meta(_entry, _ns, aid):
-            """dummy metadata extraction function."""
-            return {
-                "Title": f"T{aid}",
-                "Publication Date": "2020-01-01T00:00:00Z",
-                "URL": f"u{aid}v1",
-            }
-
-        mock_extract.side_effect = dummy_meta
-        # Prepare 5 paper IDs
-        ids = [str(i) for i in range(5)]
-        tool_input = {"arxiv_ids": ids, "tool_call_id": "tid"}
-        result = download_arxiv_paper.run(tool_input)
-        summary = result.update["messages"][0].content
-        # Should report total count of 5 and list only top 3 without ellipsis
-        assert "Number of papers found: 5" in summary
-        assert "Top 3 papers:" in summary
-        # Entries for first three IDs should include URL and no ellipsis
-        assert "1. T0 (2020-01-01T00:00:00Z)" in summary
-        assert "   View PDF: u0v1" in summary
-        assert "3. T2 (2020-01-01T00:00:00Z)" in summary
-        assert "...and" not in summary
-
-
-@pytest.mark.parametrize(
-    "input_text,expected",
-    [
-        ("", ""),
-        ("N/A", ""),
-        ("Just one sentence", "Just one sentence."),
-        ("First. Second", "First. Second."),
-        ("Hello. World.", "Hello. World."),
-    ],
-)
-def test_get_snippet_various(input_text, expected):
-    """Test _get_snippet behavior for various abstracts."""
-    assert _get_snippet(input_text) == expected

aiagents4pharma/talk2scholars/tools/paper_download/download_arxiv_input.py

@@ -1,177 +0,0 @@
-#!/usr/bin/env python3
-"""
-Tool for downloading arXiv paper metadata and retrieving the PDF URL.
-"""
-
-import logging
-import xml.etree.ElementTree as ET
-from typing import Annotated, Any, List
-
-import hydra
-import requests
-from langchain_core.messages import ToolMessage
-from langchain_core.tools import tool
-from langchain_core.tools.base import InjectedToolCallId
-from langgraph.types import Command
-from pydantic import BaseModel, Field
-
-# Configure logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-
-class DownloadArxivPaperInput(BaseModel):
-    """Input schema for the arXiv paper download tool."""
-
-    arxiv_ids: List[str] = Field(
-        description="List of arXiv paper IDs used to retrieve paper details and PDF URLs."
-    )
-    tool_call_id: Annotated[str, InjectedToolCallId]
-
-
-# Helper to load arXiv download configuration
-def _get_arxiv_config() -> Any:
-    """Load arXiv download configuration."""
-    with hydra.initialize(version_base=None, config_path="../../configs"):
-        cfg = hydra.compose(
-            config_name="config", overrides=["tools/download_arxiv_paper=default"]
-        )
-    return cfg.tools.download_arxiv_paper
-
-
-def fetch_arxiv_metadata(
-    api_url: str, arxiv_id: str, request_timeout: int
-) -> ET.Element:
-    """Fetch and parse metadata from the arXiv API."""
-    query_url = f"{api_url}?search_query=id:{arxiv_id}&start=0&max_results=1"
-    response = requests.get(query_url, timeout=request_timeout)
-    response.raise_for_status()
-    return ET.fromstring(response.text)
-
-
-def extract_metadata(entry: ET.Element, ns: dict, arxiv_id: str) -> dict:
-    """Extract metadata from the XML entry."""
-    title_elem = entry.find("atom:title", ns)
-    title = (title_elem.text or "").strip() if title_elem is not None else "N/A"
-
-    authors = []
-    for author_elem in entry.findall("atom:author", ns):
-        name_elem = author_elem.find("atom:name", ns)
-        if name_elem is not None and name_elem.text:
-            authors.append(name_elem.text.strip())
-
-    summary_elem = entry.find("atom:summary", ns)
-    abstract = (summary_elem.text or "").strip() if summary_elem is not None else "N/A"
-
-    published_elem = entry.find("atom:published", ns)
-    pub_date = (
-        (published_elem.text or "").strip() if published_elem is not None else "N/A"
-    )
-
-    pdf_url = next(
-        (
-            link.attrib.get("href")
-            for link in entry.findall("atom:link", ns)
-            if link.attrib.get("title") == "pdf"
-        ),
-        None,
-    )
-    if not pdf_url:
-        raise RuntimeError(f"Could not find PDF URL for arXiv ID {arxiv_id}")
-
-    return {
-        "Title": title,
-        "Authors": authors,
-        "Abstract": abstract,
-        "Publication Date": pub_date,
-        "URL": pdf_url,
-        "pdf_url": pdf_url,
-        "filename": f"{arxiv_id}.pdf",
-        "source": "arxiv",
-        "arxiv_id": arxiv_id,
-    }
-
-
-def _get_snippet(abstract: str) -> str:
-    """Extract the first one or two sentences from an abstract."""
-    if not abstract or abstract == "N/A":
-        return ""
-    sentences = abstract.split(". ")
-    snippet_sentences = sentences[:2]
-    snippet = ". ".join(snippet_sentences)
-    if not snippet.endswith("."):
-        snippet += "."
-    return snippet
-
-
-def _build_summary(article_data: dict[str, Any]) -> str:
-    """Build a summary string for up to three papers with snippets."""
-    top = list(article_data.values())[:3]
-    lines: list[str] = []
-    for idx, paper in enumerate(top):
-        title = paper.get("Title", "N/A")
-        pub_date = paper.get("Publication Date", "N/A")
-        url = paper.get("URL", "")
-        snippet = _get_snippet(paper.get("Abstract", ""))
-        line = f"{idx+1}. {title} ({pub_date})"
-        if url:
-            line += f"\n   View PDF: {url}"
-        if snippet:
-            line += f"\n   Abstract snippet: {snippet}"
-        lines.append(line)
-    summary = "\n".join(lines)
-    return (
-        "Download was successful. Papers metadata are attached as an artifact. "
-        "Here is a summary of the results:\n"
-        f"Number of papers found: {len(article_data)}\n"
-        "Top 3 papers:\n" + summary
-    )
-
-
-@tool(
-    args_schema=DownloadArxivPaperInput,
-    parse_docstring=True,
-)
-def download_arxiv_paper(
-    arxiv_ids: List[str],
-    tool_call_id: Annotated[str, InjectedToolCallId],
-) -> Command[Any]:
-    """
-    Get metadata and PDF URLs for one or more arXiv papers using their unique arXiv IDs.
-    """
-    logger.info("Fetching metadata from arXiv for paper IDs: %s", arxiv_ids)
-
-    # Load configuration
-    cfg = _get_arxiv_config()
-    api_url = cfg.api_url
-    request_timeout = cfg.request_timeout
-
-    # Aggregate results
-    article_data: dict[str, Any] = {}
-    for aid in arxiv_ids:
-        logger.info("Processing arXiv ID: %s", aid)
-        # Fetch and parse metadata
-        entry = fetch_arxiv_metadata(api_url, aid, request_timeout).find(
-            "atom:entry", {"atom": "http://www.w3.org/2005/Atom"}
-        )
-        if entry is None:
-            logger.warning("No entry found for arXiv ID %s", aid)
-            continue
-        article_data[aid] = extract_metadata(
-            entry, {"atom": "http://www.w3.org/2005/Atom"}, aid
-        )
-
-    # Build and return summary
-    content = _build_summary(article_data)
-    return Command(
-        update={
-            "article_data": article_data,
-            "messages": [
-                ToolMessage(
-                    content=content,
-                    tool_call_id=tool_call_id,
-                    artifact=article_data,
-                )
-            ],
-        }
-    )

aiagents4pharma/talk2scholars/tools/paper_download/download_biorxiv_input.py

@@ -1,114 +0,0 @@
-#!/usr/bin/env python3
-"""
-Tool for downloading bioRxiv paper metadata and retrieving the PDF URL.
-"""
-
-import logging
-from typing import Annotated, Any
-
-import hydra
-import requests
-from langchain_core.messages import ToolMessage
-from langchain_core.tools import tool
-from langchain_core.tools.base import InjectedToolCallId
-from langgraph.types import Command
-from pydantic import BaseModel, Field
-
-# Configure logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-
-class DownloadBiorxivPaperInput(BaseModel):
-    """Input schema for the bioRxiv paper download tool."""
-
-    doi: str = Field(
-        description="""The bioRxiv DOI, from search_helper or multi_helper or single_helper,
-    used to retrieve the paper details and PDF URL."""
-    )
-    tool_call_id: Annotated[str, InjectedToolCallId]
-
-
-def fetch_biorxiv_metadata(doi: str, api_url: str, request_timeout: int) -> dict:
-    """
-    Fetch metadata for a bioRxiv paper using its DOI and extract relevant fields.
-
-    Parameters:
-        doi (str): The DOI of the bioRxiv paper.
-
-    Returns:
-        dict: A dictionary containing the title, authors, abstract, publication date, and URLs.
-    """
-    # Strip any version suffix (e.g., v1) since bioRxiv's API is version-sensitive
-    clean_doi = doi.split("v")[0]
-
-    api_url = f"{api_url}{clean_doi}"
-    logger.info("Fetching metadata from api url: %s", api_url)
-    response = requests.get(api_url, timeout=request_timeout)
-    response.raise_for_status()
-
-    data = response.json()
-    if not data.get("collection"):
-        raise ValueError(f"No metadata found for DOI: {doi}")
-
-    data = response.json()
-
-    return data["collection"][0]
-
-
-def extract_metadata(paper: dict, doi: str) -> dict:
-    """
-    Extract relevant metadata fields from a bioRxiv paper entry.
-    """
-    title = paper.get("title", "")
-    authors = paper.get("authors", "")
-    abstract = paper.get("abstract", "")
-    pub_date = paper.get("date", "")
-    doi_suffix = paper.get("doi", "").split("10.1101/")[-1]
-    pdf_url = f"https://www.biorxiv.org/content/10.1101/{doi_suffix}.full.pdf"
-    logger.info("PDF URL: %s", pdf_url)
-    return {
-        "Title": title,
-        "Authors": authors,
-        "Abstract": abstract,
-        "Publication Date": pub_date,
-        "URL": pdf_url,
-        "pdf_url": pdf_url,
-        "filename": f"{doi_suffix}.pdf",
-        "source": "biorxiv",
-        "biorxiv_id": doi,
-    }
-
-
-@tool(args_schema=DownloadBiorxivPaperInput, parse_docstring=True)
-def download_biorxiv_paper(
-    doi: str,
-    tool_call_id: Annotated[str, InjectedToolCallId],
-) -> Command[Any]:
-    """
-    Get metadata and PDF URL for a bioRxiv paper using its DOI.
-    """
-    logger.info("Fetching metadata from bioRxiv for DOI: %s", doi)
-
-    # Load configuration
-    with hydra.initialize(version_base=None, config_path="../../configs"):
-        cfg = hydra.compose(
-            config_name="config", overrides=["tools/download_biorxiv_paper=default"]
-        )
-        api_url = cfg.tools.download_biorxiv_paper.api_url
-        request_timeout = cfg.tools.download_biorxiv_paper.request_timeout
-        logger.info("API URL: %s", api_url)
-        logger.info("Request Timeout: %s", request_timeout)
-
-    # Fetch metadata
-    raw_data = fetch_biorxiv_metadata(doi, api_url, request_timeout)
-    metadata = extract_metadata(raw_data, doi)
-    article_data = {doi: metadata}
-    content = f"Successfully retrieved metadata and PDF URL for bioRxiv DOI {doi}"
-
-    return Command(
-        update={
-            "article_data": article_data,
-            "messages": [ToolMessage(content=content, tool_call_id=tool_call_id)],
-        }
-    )