aiagents4pharma 1.29.0__py3-none-any.whl → 1.30.0__py3-none-any.whl

aiagents4pharma/talk2scholars/agents/__init__.py

@@ -4,5 +4,6 @@ This file is used to import all the modules in the package.
 
 from . import main_agent
 from . import s2_agent
+from . import paper_download_agent
 from . import zotero_agent
 from . import pdf_agent

aiagents4pharma/talk2scholars/agents/paper_download_agent.py

@@ -0,0 +1,86 @@
+#!/usr/bin/env python3
+"""
+This module defines the paper download agent that connects to the arXiv API to fetch
+paper details and PDFs. It is part of the Talk2Scholars project.
+"""
+
+import logging
+from typing import Any, Dict
+import hydra
+from langchain_core.language_models.chat_models import BaseChatModel
+from langgraph.graph import START, StateGraph
+from langgraph.prebuilt.chat_agent_executor import create_react_agent
+from langgraph.prebuilt.tool_node import ToolNode
+from langgraph.checkpoint.memory import MemorySaver
+from ..state.state_talk2scholars import Talk2Scholars
+from ..tools.paper_download import download_arxiv_paper
+from ..tools.s2.query_results import query_results
+
+# Initialize logger
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+def get_app(uniq_id, llm_model: BaseChatModel):
+    """
+    Initializes and returns the LangGraph application for the Talk2Scholars paper download agent.
+
+    Args:
+        uniq_id (str): A unique identifier for tracking the current session.
+        llm_model (BaseChatModel, optional): The language model to be used by the agent.
+            Defaults to ChatOpenAI(model="gpt-4o-mini", temperature=0.5).
+
+    Returns:
+        StateGraph: A compiled LangGraph application that enables the paper download agent to
+            process user queries and retrieve arXiv papers.
+    """
+
+    # Load Hydra configuration
+    logger.info("Loading Hydra configuration for Talk2Scholars paper download agent")
+    with hydra.initialize(version_base=None, config_path="../configs"):
+        cfg = hydra.compose(
+            config_name="config",
+            overrides=["agents/talk2scholars/paper_download_agent=default"]
+        )
+        cfg = cfg.agents.talk2scholars.paper_download_agent
+
+    # Define tools properly
+    tools = ToolNode(
+    [download_arxiv_paper, query_results]
+    )
+
+    # Define the model
+    logger.info("Using OpenAI model %s", llm_model)
+    model = create_react_agent(
+        llm_model,
+        tools=tools,
+        state_schema=Talk2Scholars,
+        prompt=cfg.prompt,
+        checkpointer=MemorySaver(),
+    )
+
+    def paper_download_agent_node(state: Talk2Scholars) -> Dict[str, Any]:
+        """
+        Processes the current state to fetch the arXiv paper.
+        """
+        logger.info("Creating paper download agent node with thread_id: %s", uniq_id)
+        result = model.invoke(state, {"configurable": {"thread_id": uniq_id}})
+        return result
+
+    # Define new graph
+    workflow = StateGraph(Talk2Scholars)
+
+    # Adding node for paper download agent
+    workflow.add_node("paper_download_agent", paper_download_agent_node)
+
+    # Entering into the agent
+    workflow.add_edge(START, "paper_download_agent")
+
+    # Memory management for states between graph runs
+    checkpointer = MemorySaver()
+
+    # Compile the graph
+    app = workflow.compile(checkpointer=checkpointer)
+
+    # Logging the information and returning the app
+    logger.info("Compiled the graph")
+    return app

aiagents4pharma/talk2scholars/configs/agents/talk2scholars/paper_download_agent/__init__.py

@@ -0,0 +1,3 @@
+"""
+Import all the modules in the package
+"""

aiagents4pharma/talk2scholars/configs/config.yaml

@@ -2,10 +2,12 @@ defaults:
   - _self_
   - agents/talk2scholars/main_agent: default
   - agents/talk2scholars/s2_agent: default
+  - agents/talk2scholars/paper_download_agent: default
   - agents/talk2scholars/zotero_agent: default
   - app/frontend: default
   - agents/talk2scholars/pdf_agent: default
   - tools/search: default
+  - tools/download_arxiv_paper: default
   - tools/single_paper_recommendation: default
   - tools/multi_paper_recommendation: default
   - tools/retrieve_semantic_scholar_paper_id: default

aiagents4pharma/talk2scholars/configs/tools/download_arxiv_paper/__init__.py

@@ -0,0 +1,3 @@
+"""
+Import all the modules in the package
+"""

aiagents4pharma/talk2scholars/state/state_talk2scholars.py

@@ -63,3 +63,4 @@ class Talk2Scholars(AgentState):
     pdf_data: Annotated[Dict[str, Any], replace_dict]
     zotero_read: Annotated[Dict[str, Any], replace_dict]
     llm_model: BaseChatModel
+    pdf_data: Annotated[Dict[str, Any], replace_dict]

aiagents4pharma/talk2scholars/tests/test_paper_download_agent.py

@@ -0,0 +1,142 @@
+"""Unit tests for the paper download agent in Talk2Scholars."""
+
+from unittest import mock
+import pytest
+from langchain_core.messages import HumanMessage, AIMessage
+from langchain_core.language_models.chat_models import BaseChatModel
+from ..agents.paper_download_agent import get_app
+from ..state.state_talk2scholars import Talk2Scholars
+
+
+@pytest.fixture(autouse=True)
+def mock_hydra_fixture():
+    """Mocks Hydra configuration for tests."""
+    with mock.patch("hydra.initialize"), mock.patch("hydra.compose") as mock_compose:
+        cfg_mock = mock.MagicMock()
+        cfg_mock.agents.talk2scholars.s2_agent.temperature = 0
+        cfg_mock.agents.talk2scholars.paper_download_agent.prompt = "Test prompt"
+        mock_compose.return_value = cfg_mock
+        yield mock_compose
+
+
+@pytest.fixture
+def mock_tools_fixture():
+    """Mocks paper download tools to prevent real HTTP calls."""
+    with (
+        mock.patch(
+            "aiagents4pharma.talk2scholars.tools.paper_download."
+            "download_arxiv_input.download_arxiv_paper"
+        ) as mock_download_arxiv_paper,
+        mock.patch(
+            "aiagents4pharma.talk2scholars.tools.s2.query_results.query_results"
+        ) as mock_query_results,
+    ):
+        mock_download_arxiv_paper.return_value = {
+            "pdf_data": {"dummy_key": "dummy_value"}
+        }
+        mock_query_results.return_value = {
+        "result": "Mocked Query Result"
+        }
+        yield [mock_download_arxiv_paper, mock_query_results]
+
+@pytest.mark.usefixtures("mock_hydra_fixture")
+def test_paper_download_agent_initialization():
+    """Ensures the paper download agent initializes properly with a prompt."""
+    thread_id = "test_thread_paper_dl"
+    llm_mock = mock.Mock(spec=BaseChatModel)  # Mock LLM
+
+    with mock.patch(
+        "aiagents4pharma.talk2scholars.agents.paper_download_agent.create_react_agent"
+    ) as mock_create_agent:
+        mock_create_agent.return_value = mock.Mock()
+
+        app = get_app(thread_id, llm_mock)
+        assert app is not None, "The agent app should be successfully created."
+        assert mock_create_agent.called
+
+def test_paper_download_agent_invocation():
+    """Verifies agent processes queries and updates state correctly."""
+    _ = mock_tools_fixture  # Prevents unused-argument warning
+    thread_id = "test_thread_paper_dl"
+    mock_state = Talk2Scholars(
+        messages=[HumanMessage(content="Download paper 1234.5678")]
+    )
+    llm_mock = mock.Mock(spec=BaseChatModel)
+
+    with mock.patch(
+        "aiagents4pharma.talk2scholars.agents.paper_download_agent.create_react_agent"
+    ) as mock_create_agent:
+        mock_agent = mock.Mock()
+        mock_create_agent.return_value = mock_agent
+        mock_agent.invoke.return_value = {
+            "messages": [AIMessage(content="Here is the paper")],
+            "pdf_data": {"file_bytes": b"FAKE_PDF_CONTENTS"},
+        }
+
+
+        app = get_app(thread_id, llm_mock)
+        result = app.invoke(
+            mock_state,
+            config={
+                "configurable": {
+                    "thread_id": thread_id,
+                    "checkpoint_ns": "test_ns",
+                    "checkpoint_id": "test_checkpoint",
+                }
+            },
+        )
+
+        assert "messages" in result
+        assert "pdf_data" in result
+
+
+def test_paper_download_agent_tools_assignment(request):  # Keep fixture name
+    """Checks correct tool assignment (download_arxiv_paper, query_results)."""
+    thread_id = "test_thread_paper_dl"
+    mock_tools = request.getfixturevalue("mock_tools_fixture")
+    llm_mock = mock.Mock(spec=BaseChatModel)
+
+    with (
+        mock.patch(
+            "aiagents4pharma.talk2scholars.agents.paper_download_agent.create_react_agent"
+        ) as mock_create_agent,
+        mock.patch(
+            "aiagents4pharma.talk2scholars.agents.paper_download_agent.ToolNode"
+        ) as mock_toolnode,
+    ):
+        mock_agent = mock.Mock()
+        mock_create_agent.return_value = mock_agent
+        mock_tool_instance = mock.Mock()
+        mock_tool_instance.tools = mock_tools
+        mock_toolnode.return_value= mock_tool_instance
+
+        get_app(thread_id, llm_mock)
+        assert mock_toolnode.called
+        assert len(mock_tool_instance.tools) == 2
+
+
+def test_paper_download_agent_hydra_failure():
+    """Confirms the agent gracefully handles exceptions if Hydra fails."""
+    thread_id = "test_thread_paper_dl"
+    llm_mock = mock.Mock(spec=BaseChatModel)
+
+    with mock.patch("hydra.initialize", side_effect=Exception("Mock Hydra failure")):
+        with pytest.raises(Exception) as exc_info:
+            get_app(thread_id, llm_mock)
+        assert "Mock Hydra failure" in str(exc_info.value)
+
+
+def test_paper_download_agent_model_failure():
+    """Ensures agent handles model-related failures gracefully."""
+    thread_id = "test_thread_paper_dl"
+    llm_mock = mock.Mock(spec=BaseChatModel)
+
+    with mock.patch(
+        "aiagents4pharma.talk2scholars.agents.paper_download_agent.create_react_agent",
+        side_effect=Exception("Mock model failure"),
+    ):
+        with pytest.raises(Exception) as exc_info:
+            get_app(thread_id, llm_mock)
+        assert "Mock model failure" in str(exc_info.value), (
+            "Model initialization failure should raise an exception."
+        )

aiagents4pharma/talk2scholars/tests/test_paper_download_tools.py

@@ -0,0 +1,154 @@
+"""
+Unit tests for arXiv paper downloading functionality, including:
+- AbstractPaperDownloader (base class)
+- ArxivPaperDownloader (arXiv-specific implementation)
+- download_arxiv_paper tool function.
+"""
+
+from unittest.mock import patch, MagicMock
+import pytest
+import requests
+from requests.exceptions import HTTPError
+from langgraph.types import Command
+from langchain_core.messages import ToolMessage
+
+# Import the classes and function under test
+from aiagents4pharma.talk2scholars.tools.paper_download.abstract_downloader import (
+    AbstractPaperDownloader,
+)
+from aiagents4pharma.talk2scholars.tools.paper_download.arxiv_downloader import (
+    ArxivPaperDownloader,
+)
+from aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input import (
+    download_arxiv_paper,
+)
+
+@pytest.mark.parametrize("class_obj", [AbstractPaperDownloader])
+
+def test_abstract_downloader_cannot_be_instantiated(class_obj):
+    """
+    Validates that AbstractPaperDownloader is indeed abstract and raises TypeError
+    if anyone attempts to instantiate it directly.
+    """
+    with pytest.raises(TypeError):
+        class_obj()
+
+
+@pytest.fixture(name="arxiv_downloader_fixture")
+@pytest.mark.usefixtures("mock_hydra_config_setup")
+def fixture_arxiv_downloader():
+    """
+    Provides an ArxivPaperDownloader instance with a mocked Hydra config.
+    """
+    return ArxivPaperDownloader()
+
+
+def test_fetch_metadata_success(arxiv_downloader_fixture,):
+    """
+    Ensures fetch_metadata retrieves XML data correctly, given a successful HTTP response.
+    """
+    mock_response = MagicMock()
+    mock_response.text = "<xml>Mock ArXiv Metadata</xml>"
+    mock_response.raise_for_status = MagicMock()
+
+    with patch.object(requests, "get", return_value=mock_response) as mock_get:
+        paper_id = "1234.5678"
+        result = arxiv_downloader_fixture.fetch_metadata(paper_id)
+        mock_get.assert_called_once_with(
+            "http://export.arxiv.org/api/query?search_query=id:1234.5678&start=0&max_results=1",
+            timeout=10,
+        )
+        assert result["xml"] == "<xml>Mock ArXiv Metadata</xml>"
+
+
+def test_fetch_metadata_http_error(arxiv_downloader_fixture):
+    """
+    Validates that fetch_metadata raises HTTPError when the response indicates a failure.
+    """
+    mock_response = MagicMock()
+    mock_response.raise_for_status.side_effect = HTTPError("Mocked HTTP failure")
+
+    with patch.object(requests, "get", return_value=mock_response):
+        with pytest.raises(HTTPError):
+            arxiv_downloader_fixture.fetch_metadata("invalid_id")
+
+
+def test_download_pdf_success(arxiv_downloader_fixture):
+    """
+    Tests that download_pdf fetches the PDF link from metadata and successfully
+    retrieves the binary content.
+    """
+    mock_metadata = {
+        "xml": """
+        <feed xmlns="http://www.w3.org/2005/Atom">
+            <entry>
+                <link title="pdf" href="http://test.arxiv.org/pdf/1234.5678v1.pdf"/>
+            </entry>
+        </feed>
+        """
+    }
+
+    mock_pdf_response = MagicMock()
+    mock_pdf_response.raise_for_status = MagicMock()
+    mock_pdf_response.iter_content = lambda chunk_size: [b"FAKE_PDF_CONTENT"]
+
+    with patch.object(arxiv_downloader_fixture, "fetch_metadata", return_value=mock_metadata):
+        with patch.object(requests, "get", return_value=mock_pdf_response) as mock_get:
+            result = arxiv_downloader_fixture.download_pdf("1234.5678")
+            assert result["pdf_object"] == b"FAKE_PDF_CONTENT"
+            assert result["pdf_url"] == "http://test.arxiv.org/pdf/1234.5678v1.pdf"
+            assert result["arxiv_id"] == "1234.5678"
+            mock_get.assert_called_once_with(
+                "http://test.arxiv.org/pdf/1234.5678v1.pdf",
+                stream=True,
+                timeout=10,
+            )
+
+
+def test_download_pdf_no_pdf_link(arxiv_downloader_fixture):
+    """
+    Ensures a RuntimeError is raised if no <link> with title="pdf" is found in the XML.
+    """
+    mock_metadata = {"xml": "<feed></feed>"}
+
+    with patch.object(arxiv_downloader_fixture, "fetch_metadata", return_value=mock_metadata):
+        with pytest.raises(RuntimeError, match="Failed to download PDF"):
+            arxiv_downloader_fixture.download_pdf("1234.5678")
+
+
+def test_download_arxiv_paper_tool_success(arxiv_downloader_fixture):
+    """
+    Validates download_arxiv_paper orchestrates the ArxivPaperDownloader correctly,
+    returning a Command with PDF data and success messages.
+    """
+    mock_metadata = {"xml": "<mockxml></mockxml>"}
+    mock_pdf_response = {
+        "pdf_object": b"FAKE_PDF_CONTENT",
+        "pdf_url": "http://test.arxiv.org/mock.pdf",
+        "arxiv_id": "9999.8888",
+    }
+
+    with patch(
+        "aiagents4pharma.talk2scholars.tools.paper_download.download_arxiv_input."
+        "ArxivPaperDownloader",
+        return_value=arxiv_downloader_fixture,
+    ):
+        with patch.object(arxiv_downloader_fixture, "fetch_metadata", return_value=mock_metadata):
+            with patch.object(
+                arxiv_downloader_fixture,
+                "download_pdf",
+                return_value=mock_pdf_response,
+            ):
+                command_result = download_arxiv_paper.invoke(
+                    {"arxiv_id": "9999.8888", "tool_call_id": "test_tool_call"}
+                )
+
+                assert isinstance(command_result, Command)
+                assert "pdf_data" in command_result.update
+                assert command_result.update["pdf_data"] == mock_pdf_response
+
+                messages = command_result.update.get("messages", [])
+                assert len(messages) == 1
+                assert isinstance(messages[0], ToolMessage)
+                assert "Successfully downloaded PDF" in messages[0].content
+                assert "9999.8888" in messages[0].content

aiagents4pharma/talk2scholars/tools/paper_download/__init__.py

@@ -0,0 +1,17 @@
+#!/usr/bin/env python3
+"""
+This package provides modules for fetching and downloading academic papers from arXiv.
+"""
+
+# Import modules
+from . import abstract_downloader
+from . import arxiv_downloader
+from . import download_arxiv_input
+from .download_arxiv_input import download_arxiv_paper
+
+__all__ = [
+    "abstract_downloader",
+    "arxiv_downloader",
+    "download_arxiv_input",
+    "download_arxiv_paper",
+]

aiagents4pharma/talk2scholars/tools/paper_download/abstract_downloader.py

@@ -0,0 +1,43 @@
+"""
+Abstract Base Class for Paper Downloaders.
+
+This module defines the `AbstractPaperDownloader` class, which serves as a
+base class for downloading scholarly papers from different sources
+(e.g., arXiv, PubMed, IEEE Xplore). Any specific downloader should
+inherit from this class and implement its methods.
+"""
+
+from abc import ABC, abstractmethod
+from typing import Any, Dict
+class AbstractPaperDownloader(ABC):
+    """
+    Abstract base class for scholarly paper downloaders.
+
+    This is designed to be extended for different paper sources
+    like arXiv, PubMed, IEEE Xplore, etc. Each implementation
+    must define methods for fetching metadata and downloading PDFs.
+    """
+
+    @abstractmethod
+    def fetch_metadata(self, paper_id: str) -> Dict[str, Any]:
+        """
+        Fetch metadata for a given paper ID.
+
+        Args:
+            paper_id (str): The unique identifier for the paper.
+
+        Returns:
+            Dict[str, Any]: The metadata dictionary (format depends on the data source).
+        """
+
+    @abstractmethod
+    def download_pdf(self, paper_id: str) -> bytes:
+        """
+        Download the PDF for a given paper ID.
+
+        Args:
+            paper_id (str): The unique identifier for the paper.
+
+        Returns:
+            bytes: The binary content of the downloaded PDF.
+        """

aiagents4pharma/talk2scholars/tools/paper_download/arxiv_downloader.py

@@ -0,0 +1,108 @@
+"""
+Arxiv Paper Downloader
+
+This module provides an implementation of `AbstractPaperDownloader` for arXiv.
+It connects to the arXiv API, retrieves metadata for a research paper, and
+downloads the corresponding PDF.
+
+By using an abstract base class, this implementation is extendable to other
+APIs like PubMed, IEEE Xplore, etc.
+"""
+import xml.etree.ElementTree as ET
+from typing import Any, Dict
+import logging
+import hydra
+import requests
+from .abstract_downloader import AbstractPaperDownloader
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+class ArxivPaperDownloader(AbstractPaperDownloader):
+    """
+    Downloader class for arXiv.
+
+    This class interfaces with the arXiv API to fetch metadata
+    and retrieve PDFs of academic papers based on their arXiv IDs.
+    """
+
+    def __init__(self):
+        """
+        Initializes the arXiv paper downloader.
+
+        Uses Hydra for configuration management to retrieve API details.
+        """
+        with hydra.initialize(version_base=None, config_path="../../configs"):
+            cfg = hydra.compose(
+                config_name="config",
+                overrides=["tools/download_arxiv_paper=default"]
+            )
+            self.api_url = cfg.tools.download_arxiv_paper.api_url
+            self.request_timeout = cfg.tools.download_arxiv_paper.request_timeout
+            self.chunk_size = cfg.tools.download_arxiv_paper.chunk_size
+            self.pdf_base_url = cfg.tools.download_arxiv_paper.pdf_base_url
+    def fetch_metadata(self, paper_id: str) -> Dict[str, Any]:
+        """
+        Fetch metadata from arXiv for a given paper ID.
+
+        Args:
+            paper_id (str): The arXiv ID of the paper.
+
+        Returns:
+            Dict[str, Any]: A dictionary containing metadata, including the XML response.
+        """
+        logger.info("Fetching metadata from arXiv for paper ID: %s", paper_id)
+        api_url = f"{self.api_url}?search_query=id:{paper_id}&start=0&max_results=1"
+        response = requests.get(api_url, timeout=self.request_timeout)
+        response.raise_for_status()
+        return {"xml": response.text}
+
+    def download_pdf(self, paper_id: str) -> Dict[str, Any]:
+        """
+        Download the PDF of a paper from arXiv.
+
+        This function first retrieves the paper's metadata to locate the PDF link
+        before downloading the file.
+
+        Args:
+            paper_id (str): The arXiv ID of the paper.
+
+        Returns:
+            Dict[str, Any]: A dictionary containing:
+                - `pdf_object`: The binary content of the downloaded PDF.
+                - `pdf_url`: The URL from which the PDF was fetched.
+                - `arxiv_id`: The arXiv ID of the downloaded paper.
+        """
+        metadata = self.fetch_metadata(paper_id)
+
+        # Parse the XML response to locate the PDF link.
+        root = ET.fromstring(metadata["xml"])
+        ns = {"atom": "http://www.w3.org/2005/Atom"}
+        pdf_url = next(
+            (
+                link.attrib.get("href")
+                for entry in root.findall("atom:entry", ns)
+                for link in entry.findall("atom:link", ns)
+                if link.attrib.get("title") == "pdf"
+            ),
+            None,
+        )
+
+        if not pdf_url:
+            raise RuntimeError(f"Failed to download PDF for arXiv ID {paper_id}.")
+
+        logger.info("Downloading PDF from: %s", pdf_url)
+        pdf_response = requests.get(pdf_url, stream=True, timeout=self.request_timeout)
+        pdf_response.raise_for_status()
+
+        # Combine the PDF data from chunks.
+        pdf_object = b"".join(
+            chunk for chunk in pdf_response.iter_content(chunk_size=self.chunk_size) if chunk
+            )
+
+        return {
+            "pdf_object": pdf_object,
+            "pdf_url": pdf_url,
+            "arxiv_id": paper_id,
+        }

aiagents4pharma/talk2scholars/tools/paper_download/download_arxiv_input.py

@@ -0,0 +1,60 @@
+# File: aiagents4pharma/talk2scholars/tools/paper_download/download_arxiv_input.py
+"""
+This module defines the `download_arxiv_paper` tool, which leverages the
+`ArxivPaperDownloader` class to fetch and download academic papers from arXiv
+based on their unique arXiv ID.
+"""
+from typing import Annotated, Any
+from pydantic import BaseModel, Field
+from langchain_core.tools import tool
+from langchain_core.messages import ToolMessage
+from langchain_core.tools.base import InjectedToolCallId
+from langgraph.types import Command
+
+# Local import from the same package:
+from .arxiv_downloader import ArxivPaperDownloader
+
+class DownloadArxivPaperInput(BaseModel):
+    """
+    Input schema for the arXiv paper download tool.
+    (Optional: if you decide to keep Pydantic validation in the future)
+    """
+    arxiv_id: str = Field(
+        description="The arXiv paper ID used to retrieve the paper details and PDF."
+        )
+    tool_call_id: Annotated[str, InjectedToolCallId]
+
+@tool(args_schema=DownloadArxivPaperInput, parse_docstring=True)
+def download_arxiv_paper(
+    arxiv_id: str,
+    tool_call_id: Annotated[str, InjectedToolCallId],
+) -> Command[Any]:
+    """
+    Download an arXiv paper's PDF using its unique arXiv ID.
+
+    This function:
+      1. Creates an `ArxivPaperDownloader` instance.
+      2. Fetches metadata from arXiv using the provided `arxiv_id`.
+      3. Downloads the PDF from the returned link.
+      4. Returns a `Command` object containing the PDF data and a success message.
+
+    Args:
+        arxiv_id (str): The unique arXiv paper ID.
+        tool_call_id (InjectedToolCallId): A unique identifier for tracking this tool call.
+
+    Returns:
+        Command[Any]: Contains metadata and messages about the success of the operation.
+    """
+    downloader = ArxivPaperDownloader()
+
+    # If the downloader fails or the arxiv_id is invalid, this might raise an error
+    pdf_data = downloader.download_pdf(arxiv_id)
+
+    content = f"Successfully downloaded PDF for arXiv ID {arxiv_id}"
+
+    return Command(
+        update={
+            "pdf_data": pdf_data,
+            "messages": [ToolMessage(content=content, tool_call_id=tool_call_id)],
+        }
+    )

{aiagents4pharma-1.29.0.dist-info → aiagents4pharma-1.30.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: aiagents4pharma
-Version: 1.29.0
+Version: 1.30.0
 Summary: AI Agents for drug discovery, drug development, and other pharmaceutical R&D.
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License

{aiagents4pharma-1.29.0.dist-info → aiagents4pharma-1.30.0.dist-info}/RECORD

@@ -135,17 +135,19 @@ aiagents4pharma/talk2knowledgegraphs/utils/enrichments/pubchem_strings.py,sha256
 aiagents4pharma/talk2knowledgegraphs/utils/extractions/__init__.py,sha256=7gwwtfzKhB8GuOBD47XRi0NprwEXkOzwNl5eeu-hDTI,86
 aiagents4pharma/talk2knowledgegraphs/utils/extractions/pcst.py,sha256=m5p0yoJb7I19ua5yeQfXPf7c4r6S1XPwttsrM7Qoy94,9336
 aiagents4pharma/talk2scholars/__init__.py,sha256=gphERyVKZHvOnMQsml7TIHlaIshHJ75R1J3FKExkfuY,120
-aiagents4pharma/talk2scholars/agents/__init__.py,sha256=ZwFiHOlDGJk1601J5xEZDy0btPzqiOk2UCocKxohde8,168
+aiagents4pharma/talk2scholars/agents/__init__.py,sha256=inLJpRDlT80RNSi3OFNi2lpbbTisQgzNkMYTvnhFjVY,203
 aiagents4pharma/talk2scholars/agents/main_agent.py,sha256=TABzGSOg7I0_fJ0qybBVqZDdrU8YCjyG_m-kasO4WgE,2854
+aiagents4pharma/talk2scholars/agents/paper_download_agent.py,sha256=3GxxNhA_VGf3QOozIjr5cEY2te5n6rQSdZpdFajZttA,3006
 aiagents4pharma/talk2scholars/agents/pdf_agent.py,sha256=c9-_z5qp5Zkgh6piEIlgI4uo4OMXD3janZNmfYwnFCg,3729
 aiagents4pharma/talk2scholars/agents/s2_agent.py,sha256=ua1bjKE2HBKZuLnDn8me5fuV1lSvdZbwAlo3Yp27TT4,4659
 aiagents4pharma/talk2scholars/agents/zotero_agent.py,sha256=5jfIJiLsRdlCJjkF7BQMkP5PsEY_Gr7SfztWKozbUGo,4223
 aiagents4pharma/talk2scholars/configs/__init__.py,sha256=tf2gz8n7M4ko6xLdX_C925ELVIxoP6SgkPcbeh59ad4,151
-aiagents4pharma/talk2scholars/configs/config.yaml,sha256=dQIMg3jLGYAudkc1Zz85qqvFf-HdVXPfewUfAfPNNzU,501
+aiagents4pharma/talk2scholars/configs/config.yaml,sha256=-8X0_gTmjEuXAeIrnppw3Npy8HICelHZOvTKEScI-rs,596
 aiagents4pharma/talk2scholars/configs/agents/__init__.py,sha256=yyh7PB2oY_JulnpSQCWS4wwCH_uzIdt47O2Ay48x_oU,75
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/__init__.py,sha256=64GEWAoKOd_YHLi27eSOcOC5eSLK0IG_FNra3ZBt02Y,146
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/main_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/main_agent/default.yaml,sha256=rZfZ_dJArjlznHzusjxCnOjhptLTyejFiB0euV5R13c,662
+aiagents4pharma/talk2scholars/configs/agents/talk2scholars/paper_download_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/pdf_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/s2_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/s2_agent/default.yaml,sha256=sn6vX6r-P0CR7UWS63ZqCmMKKn4As8pZoITRWx8sdoo,1151
@@ -155,6 +157,7 @@ aiagents4pharma/talk2scholars/configs/app/__init__.py,sha256=JoSZV6N669kGMv5zLDs
 aiagents4pharma/talk2scholars/configs/app/frontend/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/app/frontend/default.yaml,sha256=wsELBdRLv6UqZ9QZfwpS7K4xfMj5s-a99-aXqIs6WEI,868
 aiagents4pharma/talk2scholars/configs/tools/__init__.py,sha256=GwpgnRrfjyZDVsangewSVTG3H3GBYM6s_YaQd9-zI10,238
+aiagents4pharma/talk2scholars/configs/tools/download_arxiv_paper/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/tools/multi_paper_recommendation/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/tools/multi_paper_recommendation/default.yaml,sha256=QV7HrG7NdjBEjTMszh27MbGBYMbf_78V3sCGftdTtvo,442
 aiagents4pharma/talk2scholars/configs/tools/question_and_answer/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
@@ -168,10 +171,12 @@ aiagents4pharma/talk2scholars/configs/tools/zotero_read/__init__.py,sha256=fqQQ-
 aiagents4pharma/talk2scholars/configs/tools/zotero_read/default.yaml,sha256=6ZvZdCsnudPeVjnatv78Z0QfMwsHZuliE2RCIRCW05Y,1221
 aiagents4pharma/talk2scholars/configs/tools/zotero_write/__inti__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/state/__init__.py,sha256=S6SxlszIMZSIMJehjevPF9sKyR-PAwWb5TEdo6xWXE8,103
-aiagents4pharma/talk2scholars/state/state_talk2scholars.py,sha256=E0epqlBurzNcMzN4WV6nh--YkVAesbxQTuBBlJhESVA,2436
+aiagents4pharma/talk2scholars/state/state_talk2scholars.py,sha256=0dFSdsGiiilNIuuHQFEjpjQmcZXlK0JQwMV_GCiAsuU,2490
 aiagents4pharma/talk2scholars/tests/__init__.py,sha256=U3PsTiUZaUBD1IZanFGkDIOdFieDVJtGKQ5-woYUo8c,45
 aiagents4pharma/talk2scholars/tests/test_llm_main_integration.py,sha256=SAMG-Kb2S9sei8Us5vUWCUJikTKXPZVKQ6aJJPEhJsc,1880
 aiagents4pharma/talk2scholars/tests/test_main_agent.py,sha256=5QnOPKNrQCd5GdYU-vVF3bUrmitOsUcazZA7BsXeomo,5947
+aiagents4pharma/talk2scholars/tests/test_paper_download_agent.py,sha256=CP4fKFU_JYP_AXvTptnwpjaVar1d5lVKV5vxYgH_1j4,5309
+aiagents4pharma/talk2scholars/tests/test_paper_download_tools.py,sha256=_bGuoo4b6zD_vwLa7jGziWDT5qRtavsf02Jiaa7JIRU,5817
 aiagents4pharma/talk2scholars/tests/test_pdf_agent.py,sha256=TN4Sq5-SCxv-9VfFyq7sOlBlxbekmnWuB7-qh4MrhkA,4656
 aiagents4pharma/talk2scholars/tests/test_question_and_answer_tool.py,sha256=TpCDiGfsC2y6bOkm0ZTXjT1Vp8D-Po25wiEH5aDT_DA,6491
 aiagents4pharma/talk2scholars/tests/test_routing_logic.py,sha256=AZrvaEBDk51KL6edrZY3GpQ_N6VbrlADqXFeg_jxDoQ,2284
@@ -188,6 +193,10 @@ aiagents4pharma/talk2scholars/tests/test_zotero_path.py,sha256=XeXYqTlSkJgZ02tCz
 aiagents4pharma/talk2scholars/tests/test_zotero_read.py,sha256=vLAPAFeL8MjDju_HlsLnio-9HxzN1RqOApr9jyemYBk,14951
 aiagents4pharma/talk2scholars/tests/test_zotero_write.py,sha256=76V7ezb6Xw-BEEwdJQvJs78JPGRYpAsijHIi3bTGsW8,23206
 aiagents4pharma/talk2scholars/tools/__init__.py,sha256=UtGutYNNaRcr2nOmT_XqbTiaJpgVYKo3KVGVPFVrX2Y,107
+aiagents4pharma/talk2scholars/tools/paper_download/__init__.py,sha256=0XmPLEqCply536Y1uWksmHYjlgNWcmcMpZx63XvGEFI,413
+aiagents4pharma/talk2scholars/tools/paper_download/abstract_downloader.py,sha256=UgJOu9o9RAjlzMahUgPWV6iCGC6n7atDOa0VEp8bGx0,1325
+aiagents4pharma/talk2scholars/tools/paper_download/arxiv_downloader.py,sha256=kP5tyLc92zlkF5EPA7zVYSjpVk724pCsjHFgOntb_Tw,3869
+aiagents4pharma/talk2scholars/tools/paper_download/download_arxiv_input.py,sha256=EJBr9RSSog8tFa7BIFIDZ-Qn7qjqJIAuRb_hF4wZ49Q,2181
 aiagents4pharma/talk2scholars/tools/pdf/__init__.py,sha256=WOm-o-fFzyjFZBaHg658Gjzdiu1Kt-h9xvzvw0hR7aE,103
 aiagents4pharma/talk2scholars/tools/pdf/question_and_answer.py,sha256=22JvT7F0rY11TF40pBfe9Cn2Y-6Tx73NfWDt4NJv700,6639
 aiagents4pharma/talk2scholars/tools/s2/__init__.py,sha256=wytqCmGm8Fbl8y5qLdIkxhhG8VHLYMifCGjbH_LK2Fc,258
@@ -202,8 +211,8 @@ aiagents4pharma/talk2scholars/tools/zotero/zotero_read.py,sha256=eRqdQCyWws8q6iC
 aiagents4pharma/talk2scholars/tools/zotero/zotero_write.py,sha256=dqYc5HWMK3vz77psHYUosMLE63NYg9Nk6xbWy8TOrU4,9246
 aiagents4pharma/talk2scholars/tools/zotero/utils/__init__.py,sha256=Ll8YQZj9sYJpXmoGxj_0ZcuEHDj06_CUqdDlTlevGL4,53
 aiagents4pharma/talk2scholars/tools/zotero/utils/zotero_path.py,sha256=nHmYe3kcrygNOslHki4YeMztfnmRDPul4gZvXl_XsV0,1954
-aiagents4pharma-1.29.0.dist-info/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
-aiagents4pharma-1.29.0.dist-info/METADATA,sha256=qYpzGvw6Raduy-RwlrnMNTElHqb4HP9n3LslreZaNl0,13245
-aiagents4pharma-1.29.0.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
-aiagents4pharma-1.29.0.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
-aiagents4pharma-1.29.0.dist-info/RECORD,,
+aiagents4pharma-1.30.0.dist-info/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
+aiagents4pharma-1.30.0.dist-info/METADATA,sha256=411N0HHxJVGSKxY07zzYQ4Z60aIJRN7fd4cMaSa7uVc,13245
+aiagents4pharma-1.30.0.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
+aiagents4pharma-1.30.0.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
+aiagents4pharma-1.30.0.dist-info/RECORD,,