PyPI - aiagents4pharma - Versions diffs - 1.42.0__py3-none-any.whl → 1.43.0__py3-none-any.whl - Mend

aiagents4pharma 1.42.0py3-none-any.whl → 1.43.0py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (42) hide show

aiagents4pharma/talk2scholars/tools/s2/query_dataframe.py CHANGED Viewed

@@ -1,13 +1,31 @@
 #!/usr/bin/env python3
-"""
-Tool for querying the metadata table of the last displayed papers.
-This tool loads the most recently displayed papers into a pandas DataFrame and uses an
-LLM-driven pandas agent to answer metadata-level questions (e.g., filter by author, list titles).
-It is intended for metadata exploration only, and does not perform content-based retrieval
-or summarization. For PDF-level question answering, use the 'question_and_answer_agent'.
 """
+Query the metadata table of the most recently displayed papers.
+This tool loads `state['last_displayed_papers']` into a pandas DataFrame and uses an
+LLM-driven DataFrame agent to execute metadata-level queries. It supports both
+natural-language prompts (e.g., “list titles by author X”) and direct Python expressions
+over the DataFrame.
+Capabilities
+- Filter, sort, and aggregate rows using metadata columns (e.g., Title, Authors, Venue, Year).
+- Extract paper identifiers from a designated column (default: 'paper_ids'),
+  optionally for a single row.
+- Return the DataFrame agent’s textual result as a ToolMessage.
+Requirements
+- `state['llm_model']`: model used to instantiate the DataFrame agent.
+- `state['last_displayed_papers']`: dictionary mapping row keys → metadata records.
+Notes
+- Operates strictly on the metadata table; it does not parse or read PDF content.
+- When `extract_ids=True`, the tool constructs a Python expression for the agent to evaluate
+  and return identifiers from `id_column`. If `row_number` is provided (1-based), only that row’s
+  first identifier is returned; otherwise a list is returned from all rows that have values.
+"""
 import logging
 from typing import Annotated, Optional, Any
@@ -32,23 +50,32 @@ class NoPapersFoundError(Exception):
 class QueryDataFrameInput(BaseModel):
     """
-    Pydantic schema for querying the metadata of displayed papers.
+    Input schema for querying the last displayed papers metadata DataFrame.
     Fields:
-      question: A free-text prompt or Python expression to query the papers DataFrame.
-      tool_call_id: LangGraph-injected identifier for tracking the tool invocation.
-      state: Agent state dictionary. Must include:
-        - 'last_displayed_papers': dictionary of paper metadata (rows = papers).
-        - 'llm_model': model used to instantiate the DataFrame agent.
-    Notes:
-      - This tool is only for metadata queries. It does not perform full-text PDF analysis.
-      - You can access standard metadata columns such as 'Title', 'Authors',
-        'Venue', 'Year', and the unified 'paper_ids' (list of <source>:<ID>).
-      - To extract raw paper IDs for downloading, set extract_ids=True and specify:
-          - id_column: 'paper_ids' (default)
-          - row_number: 1-based index of the paper to return (optional—for a single ID)
-        Example: {{"question":"","extract_ids":True,"row_number":4}}
+      question (str):
+        The query to execute. Accepts natural language (e.g., "List titles from 2024")
+        or a Python expression over the DataFrame (e.g., "df['Title'].tolist()").
+      extract_ids (bool, default=False):
+        When True, the tool prepares a Python expression for the DataFrame agent to extract
+        identifiers from `id_column`. Use to obtain IDs from the metadata table.
+      id_column (str, default="paper_ids"):
+        Name of the column that contains per-row lists of identifiers (e.g., ["arxiv:2301.12345"]).
+        Used only when `extract_ids=True`.
+      row_number (int | None, default=None):
+        1-based row index. When provided with `extract_ids=True`, returns only that row’s first
+        identifier. When omitted, returns a list of first identifiers from each applicable row.
+      tool_call_id (InjectedToolCallId):
+        Internal identifier for tracing the tool invocation.
+      state (dict):
+        Agent state containing:
+          - 'last_displayed_papers': dict with the current results table (rows → metadata)
+          - 'llm_model': model object or reference for the DataFrame agent
     """
     question: str = Field(
@@ -95,30 +122,55 @@ def query_dataframe(
     **kwargs: Any,
 ) -> Command:
     """
-    Perform a tabular query on the most recently displayed papers.
-    This function loads the last displayed papers into a pandas DataFrame and uses a
-    pandas DataFrame agent to answer metadata-level questions (e.g., "Which papers have
-    'Transformer' in the title?", "List authors of paper X"). It does not perform PDF
-    content analysis or summarization; for content-level question answering, use the
-    'question_and_answer_agent'.
-    Args:
-        question (str): The metadata query to ask over the papers table.
-        extract_ids (bool): If true, modify the query to instruct the DataFrame agent
-        to extract values from the specified ID column via Python code.
-        id_column (str): Name of the metadata column to extract values from when extract_ids=True.
-        row_number (int, optional): 1-based index of the ID to extract from the list; if provided,
-        returns only that single ID.
-        state (dict): The agent's state containing 'last_displayed_papers' key
-        referencing the metadata table in state.
-        tool_call_id (str): LangGraph-injected identifier for this tool call.
-    Returns:
-        Command: A structured response containing a ToolMessage with the query result.
-    Raises:
-        NoPapersFoundError: If no papers have been displayed yet.
+    Execute a metadata query against the DataFrame built from `last_displayed_papers`.
+    Behavior
+    - Builds a pandas DataFrame from `state['last_displayed_papers']`.
+    - Instantiates a pandas DataFrame agent with `state['llm_model']`.
+    - Runs either:
+        • the provided natural-language prompt, or
+        • a constructed Python expression when `extract_ids=True`
+          (optionally scoped to `row_number`, 1-based).
+    - Returns the DataFrame agent’s output text in a ToolMessage.
+    Parameters
+      question (str):
+        Natural-language query or Python expression to run on the DataFrame.
+      state (dict):
+        Must provide 'llm_model' and 'last_displayed_papers'.
+      tool_call_id (str):
+        Internal identifier for the tool call.
+      **kwargs:
+        extract_ids (bool): Enable ID extraction from `id_column`.
+        id_column (str): Column containing lists of identifiers (default: "paper_ids").
+        row_number (int | None): 1-based index for a single-row extraction.
+    Returns
+      Command:
+        update = {
+          "messages": [
+            ToolMessage(
+              content=<text result from the DataFrame agent>,
+              tool_call_id=<tool_call_id>
+            )
+          ]
+        }
+    Errors
+    - Raises `ValueError` if 'llm_model' is missing in `state`.
+    - Raises `NoPapersFoundError` if `state['last_displayed_papers']` is missing or empty.
+    - Raises `ValueError` if a required argument for the chosen mode is invalid
+      (e.g., no `id_column` when `extract_ids=True`).
+    Examples
+    - Natural language:
+        question="List titles where Year >= 2023"
+    - Python list of titles:
+        question="df.query('Year >= 2023')['Title'].tolist()"
+    - Extract first ID from row 1:
+        extract_ids=True, row_number=1
+    - Extract first IDs from all rows:
+        extract_ids=True
     """
     logger.info("Querying last displayed papers with question: %s", question)
     llm_model = state.get("llm_model")

aiagents4pharma/talk2scholars/tools/s2/retrieve_semantic_scholar_paper_id.py CHANGED Viewed

@@ -1,12 +1,11 @@
 #!/usr/bin/env python3
 """
-Tool for retrieving a Semantic Scholar paper ID given a paper title.
+Resolve a paper title to a Semantic Scholar paperId.
-This tool queries the Semantic Scholar API for the best match of the provided paper title
-and returns the unique Semantic Scholar paperId. Use when you have a known title and need its
-Semantic Scholar identifier for further metadata retrieval or pipeline integration. Do not
-use this tool for broad literature search; use the `search` tool instead.
+This module provides a tool that queries the Semantic Scholar API for the best match to a
+given paper title (full or partial) and returns the corresponding `paperId` string.
+Configuration is loaded via Hydra and the top ranked result is returned.
 """
 import logging
@@ -27,11 +26,14 @@ logger = logging.getLogger(__name__)
 class RetrieveSemanticScholarPaperIdInput(BaseModel):
     """
-    Pydantic schema for retrieving a Semantic Scholar paper ID.
-    Fields:
-      paper_title: The title (full or partial) of the paper to look up on Semantic Scholar.
-      tool_call_id: LangGraph-injected identifier for tracking the tool invocation.
+    Input schema for title→paperId resolution.
+    Fields
+    -------
+    paper_title : str
+        Paper title to search. Accepts full titles or informative partial titles.
+    tool_call_id : InjectedToolCallId
+        Runtime-injected identifier for tracing the tool invocation.
     """
     paper_title: str = Field(
@@ -50,27 +52,43 @@ def retrieve_semantic_scholar_paper_id(
     tool_call_id: str,
 ) -> Command[Any]:
     """
-    Retrieve a Semantic Scholar paper ID using a paper title.
-    This tool searches Semantic Scholar for the best match to the provided paper title
-    and returns the corresponding unique paper ID. It is intended to support downstream
-    tasks such as recommendations, metadata lookups, or citation graph queries.
-    Use this tool when you know the full or partial title of a paper and need its
-    Semantic Scholar ID.
-    For broad literature searches or topic-based queries, use a general `search` tool instead.
-    Args:
-        paper_title (str): The full or partial title of the paper to look up.
-        tool_call_id (str): LangGraph-injected identifier for this tool call.
+    Look up a Semantic Scholar paperId from a paper title.
+    Behavior
+    --------
+    - Loads Hydra config from `tools.retrieve_semantic_scholar_paper_id`.
+    - Sends a search request with `query=<paper_title>`, `limit=1`, and requested fields.
+    - Parses the top hit and returns its `paperId` as the ToolMessage content (plain string).
+    Parameters
+    ----------
+    paper_title : str
+        Title or informative partial title to resolve.
+    tool_call_id : str
+        Runtime-injected identifier for the tool call.
+    Returns
+    -------
+    Command
+        update = {
+          "messages": [
+            ToolMessage(
+              content="<paperId>",  # Semantic Scholar paperId string
+              tool_call_id=<tool_call_id>
+            )
+          ]
+        }
-    Returns:
-        Command: A structured response containing a ToolMessage whose content is
-            the Semantic Scholar paper ID string (e.g., 'abc123xyz').
+    Exceptions
+    ----------
+    ValueError
+        Raised when no match is found for the provided title.
+    requests.RequestException
+        Raised on network/HTTP errors (timeout, connection issues, etc.).
-    Raises:
-        ValueError: If no matching paper is found for the given title.
-        requests.RequestException: If the API request fails.
+    Examples
+    --------
+    >>> retrieve_semantic_scholar_paper_id("Attention Is All You Need", "tc_123")
     """
     # Load hydra configuration
     with hydra.initialize(version_base=None, config_path="../../configs"):

{aiagents4pharma-1.42.0.dist-info → aiagents4pharma-1.43.0.dist-info}/METADATA RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aiagents4pharma
-Version: 1.42.0
+Version: 1.43.0
 Summary: AI Agents for drug discovery, drug development, and other pharmaceutical R&D.
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
@@ -72,6 +72,7 @@ Dynamic: license-file
 <!--  Project Info -->
 ![RELEASE](https://img.shields.io/github/v/release/VirtualPatientEngine/AIAgents4Pharma?label=RELEASE)
+![Docker Compose Release Version](https://img.shields.io/github/v/release/VirtualPatientEngine/AIAgents4Pharma?label=Docker%20Compose%20Version)
 ![Python Version from PEP 621 TOML](https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2FVirtualPatientEngine%2FAIAgents4Pharma%2Frefs%2Fheads%2Fmain%2Fpyproject.toml)
 <!--  Deployment Workflows -->
@@ -79,6 +80,7 @@ Dynamic: license-file
 [![Pages Deployment](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/pages/pages-build-deployment/badge.svg)](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/pages/pages-build-deployment)
 [![MkDocs Deploy](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/mkdocs-deploy.yml/badge.svg)](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/mkdocs-deploy.yml)
 [![Docker Build & Push](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/docker_build.yml/badge.svg)](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/docker_build.yml)
+[![Docker Compose Release](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/docker_compose_release.yml/badge.svg)](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/docker_compose_release.yml)
 <!--  Tests -->

{aiagents4pharma-1.42.0.dist-info → aiagents4pharma-1.43.0.dist-info}/RECORD RENAMED Viewed

@@ -157,36 +157,32 @@ aiagents4pharma/talk2knowledgegraphs/utils/extractions/pcst.py,sha256=m5p0yoJb7I
 aiagents4pharma/talk2scholars/__init__.py,sha256=NOZxTklAH1j1ggu97Ib8Xn9LCKudEWt-8dx8w7yxVD8,180
 aiagents4pharma/talk2scholars/agents/__init__.py,sha256=c_0Pk85bt-RfK5RMyALM3MXo3qXVMoYS7BOqM9wuFME,317
 aiagents4pharma/talk2scholars/agents/main_agent.py,sha256=oQqa1z4nvfUvPWCX-SUHGs9jOCJKtzjw86jXJZ68gCk,3382
-aiagents4pharma/talk2scholars/agents/paper_download_agent.py,sha256=J_kEl8joQfM80211xlNLZA9RkN52fY58dbCisuiEft8,3687
+aiagents4pharma/talk2scholars/agents/paper_download_agent.py,sha256=gIaaUcT4JPuQSJ5C-PPtY92oskWKh69zl99WzqPO9AA,3501
 aiagents4pharma/talk2scholars/agents/pdf_agent.py,sha256=GEXzJMQxIeZ7zLP-AlnTMU-n_KXZ7g22Qd9L3USIc_4,3626
 aiagents4pharma/talk2scholars/agents/s2_agent.py,sha256=oui0CMSyXmBGBJ7LnYq8Ce0V8Qc3BS6GgH5Qx5wI6oM,4565
 aiagents4pharma/talk2scholars/agents/zotero_agent.py,sha256=NAmEURIhH-sjXGO-dqAigUA10m-Re9Qe1hY8db4CIP0,4370
 aiagents4pharma/talk2scholars/configs/__init__.py,sha256=Y9-4PxsNCMoxyyQgDSbPByJnO9wnyem5SYL3eOZt1HY,189
-aiagents4pharma/talk2scholars/configs/config.yaml,sha256=F7BCgmcnhfkyKT6qFL11E_iwTYPmF8W_0b1n4KAaSho,680
+aiagents4pharma/talk2scholars/configs/config.yaml,sha256=GyL69HPuoccv93Gcw7S44xiWG-iPxfKU-p27VWC12iY,590
 aiagents4pharma/talk2scholars/configs/agents/__init__.py,sha256=plv5Iw34gvbGZbRyJapvoOiiFXekRQIwjV_yy5AR_SI,104
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/__init__.py,sha256=D94LW4cXLmJe4dNl5qoR9QN0JnBqGLbQDgDLqhCNUE0,213
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/main_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
-aiagents4pharma/talk2scholars/configs/agents/talk2scholars/main_agent/default.yaml,sha256=hew5vyrhLeJktoN6DTPRRpnINrXqKZ4trLJQDOuDGOA,4712
+aiagents4pharma/talk2scholars/configs/agents/talk2scholars/main_agent/default.yaml,sha256=vSxteufVdgZeXBnU_LhduoBNBVz17s3mpqrjFw-QPUI,3677
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/paper_download_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
-aiagents4pharma/talk2scholars/configs/agents/talk2scholars/paper_download_agent/default.yaml,sha256=D-IanUKvd2yhrFJjQCMnIG8UNQ3fbkW_bOdhHWRKmq8,357
+aiagents4pharma/talk2scholars/configs/agents/talk2scholars/paper_download_agent/default.yaml,sha256=S1cmJaX6Xp4i_ixExZfP0qgD-tXQVFbpWpXvrh7ZVeQ,1173
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/pdf_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
-aiagents4pharma/talk2scholars/configs/agents/talk2scholars/pdf_agent/default.yaml,sha256=p3hFJi-1xbHCNagTG13WHvsrPt11XQg1nHS7VJx2XOY,166
+aiagents4pharma/talk2scholars/configs/agents/talk2scholars/pdf_agent/default.yaml,sha256=MYC9REeARVfTOCWyV_4cInvWHDksKMz193Q1LirKtZw,832
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/s2_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
-aiagents4pharma/talk2scholars/configs/agents/talk2scholars/s2_agent/default.yaml,sha256=CHMsW3cpGtfYWpSIY5XgNEYPvbI31OjOYfl_VbbKIyY,707
+aiagents4pharma/talk2scholars/configs/agents/talk2scholars/s2_agent/default.yaml,sha256=X88qKa0DgqCIvpnJgO_qEqAhhT9ymDr1B8HkJLTkB0U,2718
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/zotero_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
-aiagents4pharma/talk2scholars/configs/agents/talk2scholars/zotero_agent/default.yaml,sha256=FUbJIiH_FHeL0n1M-HSsLX_R2gMBRxBnPcejhd0HrYc,399
+aiagents4pharma/talk2scholars/configs/agents/talk2scholars/zotero_agent/default.yaml,sha256=d_38r0JtOPW0wM3J7LTB17aW3eBRyA6nFhB8MJd6lOw,1016
 aiagents4pharma/talk2scholars/configs/app/__init__.py,sha256=tXpOW3R4eAfNoqvoaHfabSG-DcMHmUGSTg_4zH_vlgw,94
 aiagents4pharma/talk2scholars/configs/app/frontend/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/app/frontend/default.yaml,sha256=A6nYjrgzEyRv5JYsGN7oqNX4-tufMBZ6mg-A7bMX6V4,906
 aiagents4pharma/talk2scholars/configs/tools/__init__.py,sha256=6pHPF0ZGY78SD6KPMukd_xrfO1ocVXcyrsrB-kz-OnI,402
-aiagents4pharma/talk2scholars/configs/tools/download_arxiv_paper/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
-aiagents4pharma/talk2scholars/configs/tools/download_arxiv_paper/default.yaml,sha256=VT3f-E6QGtqUjLEX0eaw9b_7f1Fp83cnnMOpqOufK4I,120
-aiagents4pharma/talk2scholars/configs/tools/download_biorxiv_paper/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
-aiagents4pharma/talk2scholars/configs/tools/download_biorxiv_paper/default.yaml,sha256=d5_dl1_FYWseBGTVGkvC41jfJMsMUaDMOmC_av3aL4Q,72
-aiagents4pharma/talk2scholars/configs/tools/download_medrxiv_paper/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
-aiagents4pharma/talk2scholars/configs/tools/download_medrxiv_paper/default.yaml,sha256=NaWmyVZ71rIF3ZRUm912wQgRL0cgDTWA-hVKeu60rtg,70
 aiagents4pharma/talk2scholars/configs/tools/multi_paper_recommendation/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/tools/multi_paper_recommendation/default.yaml,sha256=comNgL9hRpH--IWuEsrN6hV5WdrJmh-ZsRh7hbryVhg,631
+aiagents4pharma/talk2scholars/configs/tools/paper_download/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
+aiagents4pharma/talk2scholars/configs/tools/paper_download/default.yaml,sha256=KaHKlCf-Y1Ob1wnEKhfhKEaLye_L9Qs_BT3PhLlDM6Y,3571
 aiagents4pharma/talk2scholars/configs/tools/question_and_answer/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/tools/question_and_answer/default.yaml,sha256=Pa3JVyA9tabXZ4Bk3n5dAml7P-nXUcT7HgkA8Kr_sXk,2238
 aiagents4pharma/talk2scholars/configs/tools/retrieve_semantic_scholar_paper_id/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
@@ -202,12 +198,14 @@ aiagents4pharma/talk2scholars/configs/tools/zotero_write/default.yaml,sha256=gB7
 aiagents4pharma/talk2scholars/state/__init__.py,sha256=ReScKLpEvedq4P6ww52NRQS0Xr6SSQV7hqoQ83Mt75U,138
 aiagents4pharma/talk2scholars/state/state_talk2scholars.py,sha256=Z2zV-SXB2SMnn8PnjWjmK-OD5KjUwMTChBpXBAcl2hg,3885
 aiagents4pharma/talk2scholars/tests/__init__.py,sha256=U3PsTiUZaUBD1IZanFGkDIOdFieDVJtGKQ5-woYUo8c,45
+aiagents4pharma/talk2scholars/tests/test_arxiv_downloader.py,sha256=JvqMLUeNVnmkhGo9fjDr73r76kwWFiuBbJHMAdo7Jko,18772
+aiagents4pharma/talk2scholars/tests/test_base_paper_downloader.py,sha256=Rtp05inMVbDg4Yt7HlmXFt3_9xOXUighQsxishmABSk,25107
+aiagents4pharma/talk2scholars/tests/test_biorxiv_downloader.py,sha256=qvNDcJTpqV7L5bZ3r40wtBehNcrDNtlOJLkzhSNh6q0,27690
 aiagents4pharma/talk2scholars/tests/test_main_agent.py,sha256=4Z3xLq8MGlayGhQE5qKOirYotwJrlf7fk8rqAaORorg,7617
+aiagents4pharma/talk2scholars/tests/test_medrxiv_downloader.py,sha256=aoLB64tw7HXMv0xIIOUZ5CFt9fd8n61kQMmKpznh2M0,20848
 aiagents4pharma/talk2scholars/tests/test_nvidia_nim_reranker.py,sha256=ftfn4VenufZ-zt2nSOyOoCjfSbwFOW9CS1DLzPtBEaM,4410
-aiagents4pharma/talk2scholars/tests/test_paper_download_agent.py,sha256=gKSQp-sw62FplNnGYW0wv2ZIUEefh3o0tFWbRzy9yLs,5068
-aiagents4pharma/talk2scholars/tests/test_paper_download_biorxiv.py,sha256=gosuW4VBXyorQXbf0TpgAIT2hQjEeuvTTnT1jnoBYqM,6405
-aiagents4pharma/talk2scholars/tests/test_paper_download_medrxiv.py,sha256=iNq9vEIVapmnUZTRJXCv_UoaWThGapW7Vt_2BmZG9NE,6414
-aiagents4pharma/talk2scholars/tests/test_paper_download_tools.py,sha256=lGXbHl3lEXDjMHAX9uCgrREBOUuOHWv9TsYEshiG_tc,10421
+aiagents4pharma/talk2scholars/tests/test_paper_download_agent.py,sha256=1QeIf9SrBM712DOPC5qotL-vDo7Ax-9l9LDDEtTJNdI,5344
+aiagents4pharma/talk2scholars/tests/test_paper_downloader.py,sha256=8r_OZOJkHZ8mhrSNuSZ3aLyIA6Ngb-S23S30XmYRZ-c,22822
 aiagents4pharma/talk2scholars/tests/test_pdf_agent.py,sha256=9Kr0FcyFWmUDTasYh6ZdS-OWQqy37mH9K3p5Y0dqQHw,4283
 aiagents4pharma/talk2scholars/tests/test_pdf_answer_formatter.py,sha256=a1a_z1M9sOQ_SFo-gHM3xA_f5MoJJmEoW8Tc3AX9vL0,2239
 aiagents4pharma/talk2scholars/tests/test_pdf_batch_processor.py,sha256=e8KQJ80nbOmCH4mgDnIXXjlrRk0zf0g-5Odt2jsCU0s,3251
@@ -221,6 +219,7 @@ aiagents4pharma/talk2scholars/tests/test_pdf_retrieve_chunks.py,sha256=2cjbCrf86
 aiagents4pharma/talk2scholars/tests/test_pdf_singleton_manager.py,sha256=gOk8L9wNRPUnAiB89n1a4pQQPI7UtonRi7-IcCip94k,5628
 aiagents4pharma/talk2scholars/tests/test_pdf_vector_normalization.py,sha256=pu9I3tromjToIN5r4S8sWanaLBVhhk71UPP5zTTGwZY,3928
 aiagents4pharma/talk2scholars/tests/test_pdf_vector_store.py,sha256=-7CUiPLT4mOBVkNV2qlF7t4yU_mRArM0uAcUAKgEY4k,15644
+aiagents4pharma/talk2scholars/tests/test_pubmed_downloader.py,sha256=FpuyL2NhlnX6tkI8UwU7rxYJe94TdHlwJWZan5rbXcg,44972
 aiagents4pharma/talk2scholars/tests/test_question_and_answer_tool.py,sha256=UKSD7wLJ1cZunw8a1BHM7E-NUML6blxpqoDroCYuvQs,4245
 aiagents4pharma/talk2scholars/tests/test_read_helper_utils.py,sha256=yTT1aLpTydDSdGcRZur5cMktwYZbFK5NEUgOBvltcWg,3819
 aiagents4pharma/talk2scholars/tests/test_s2_agent.py,sha256=TsdNlZ6vHz18bbX6Vto28nbBLRDI94wSFt5-1acDK64,7768
@@ -240,10 +239,14 @@ aiagents4pharma/talk2scholars/tests/test_zotero_pdf_downloader_utils.py,sha256=N
 aiagents4pharma/talk2scholars/tests/test_zotero_read.py,sha256=qkudWMjxjjTYKJ1zvpWs0EJXCIvFx-iNKyKs_Tv1CSI,29061
 aiagents4pharma/talk2scholars/tests/test_zotero_write.py,sha256=qWlO0XoZJ6vxUxgisjYv9Np87CoTEDxiQBEOhdj9foo,6111
 aiagents4pharma/talk2scholars/tools/__init__.py,sha256=c8pYHDqR9P0Frz2jWjbvyizfSTBMlMFzGsiQzx2KC9c,189
-aiagents4pharma/talk2scholars/tools/paper_download/__init__.py,sha256=Lu5FmBxDH8mIIYE41G8_BKYXUf-vHIYVwujidbeydl4,295
-aiagents4pharma/talk2scholars/tools/paper_download/download_arxiv_input.py,sha256=e3S8JusJVVSEC_tFh8H5CS9ZqD20jX8hkFO9EYESBXo,5653
-aiagents4pharma/talk2scholars/tools/paper_download/download_biorxiv_input.py,sha256=Iipvv0P-KLbW8ELMDBLr-FxgoGBjRjPToVw7pBVJS-Y,3676
-aiagents4pharma/talk2scholars/tools/paper_download/download_medrxiv_input.py,sha256=2ONhx7rygCACf_SYc1cxDAmQP4ZzkB39OoLZYsbFMyI,3752
+aiagents4pharma/talk2scholars/tools/paper_download/__init__.py,sha256=PzJTrcXBHB3e2rgOvJ3Q8JJjvZAXyUCtGcGdANk1svE,227
+aiagents4pharma/talk2scholars/tools/paper_download/paper_downloader.py,sha256=YJuuRhkxFZIHyQTE3Hh4rkJF1hYCFNgORd_9dyp9-5E,16908
+aiagents4pharma/talk2scholars/tools/paper_download/utils/__init__.py,sha256=mbtb0IK6fW6ASQyqMhkaCHFBXQUguR7G6hZHrTJwZXc,467
+aiagents4pharma/talk2scholars/tools/paper_download/utils/arxiv_downloader.py,sha256=xWb4YPbDPZbgBDS1INDCSrOVeNiDRNC2KYhiOQjJV3o,7029
+aiagents4pharma/talk2scholars/tools/paper_download/utils/base_paper_downloader.py,sha256=pIt-BFgt7mh4XPXzcfRy5LY8xzmhADF6j8-TOyiaa1Q,11350
+aiagents4pharma/talk2scholars/tools/paper_download/utils/biorxiv_downloader.py,sha256=sz4lc1jQEKzYk9kX2QJotgjbNWXpLfmi8jfY-zVW8Wg,11652
+aiagents4pharma/talk2scholars/tools/paper_download/utils/medrxiv_downloader.py,sha256=9jKbh6lW9IBI9RJhHzqV1ktz3LfvoD3B5ayeXk15Eg4,6638
+aiagents4pharma/talk2scholars/tools/paper_download/utils/pubmed_downloader.py,sha256=Md9bWaiy7_88NIue_3NkPrmXyNZQS8zLcK4xaFQmIjU,12177
 aiagents4pharma/talk2scholars/tools/pdf/__init__.py,sha256=DPpOfON3AySko5EBBAe_3udOoSaAdQWNyGeNvJyV5R8,138
 aiagents4pharma/talk2scholars/tools/pdf/question_and_answer.py,sha256=_HLO04bzTSlnEEWwkJ3rC9Gjz8MPeHVglqovoTDOSp4,5844
 aiagents4pharma/talk2scholars/tools/pdf/utils/__init__.py,sha256=AlvoJY0hI4MCS4zHO3EtFkFJpKqjO7ZxWkoE3QvHi88,820
@@ -265,8 +268,8 @@ aiagents4pharma/talk2scholars/tools/pdf/utils/vector_store.py,sha256=X9OGwV3RHZI
 aiagents4pharma/talk2scholars/tools/s2/__init__.py,sha256=w_eiw0pG8HNp79F9O_icXs_Yl_4odsmagYNKDTjIsvk,428
 aiagents4pharma/talk2scholars/tools/s2/display_dataframe.py,sha256=qnY7AQDnAs0SrmV7AZ9pWm10HEmPlO7EBfzYvpb3jvs,3965
 aiagents4pharma/talk2scholars/tools/s2/multi_paper_rec.py,sha256=TEt4jOX1u8v3w_u10sGx-Ghwhe4yjuaYmUjD62nJQJM,3886
-aiagents4pharma/talk2scholars/tools/s2/query_dataframe.py,sha256=EJ-EV-pk2kLS12Q5HatBdGue3t-MB8mx5PrSxtLN7Co,7042
-aiagents4pharma/talk2scholars/tools/s2/retrieve_semantic_scholar_paper_id.py,sha256=0yILvpqraXldd61nLHSCfITvKyLIxts6HBC5GaGVfBQ,3995
+aiagents4pharma/talk2scholars/tools/s2/query_dataframe.py,sha256=bZiSe7-hf0IHIoZhITtgOSDauyd9NAtim5ukWi1vyuA,8599
+aiagents4pharma/talk2scholars/tools/s2/retrieve_semantic_scholar_paper_id.py,sha256=zwm4LGfFWxJLIPRc2TO5zQ48kCKe7EmkwY1SyTVCTAg,4014
 aiagents4pharma/talk2scholars/tools/s2/search.py,sha256=SUAN32x1d9dNikFKitcXZZ0BhFfsGMdLDk0z0DpJXuA,3334
 aiagents4pharma/talk2scholars/tools/s2/single_paper_rec.py,sha256=JTggOB4sqhTF1kP81Gl_54RjpbHIfqtJEoUTxlZ82N8,3630
 aiagents4pharma/talk2scholars/tools/s2/utils/__init__.py,sha256=wBTPVgiXbmIJUMouOQRwojgk5PJXeEinDJzHzEToZbU,229
@@ -283,8 +286,8 @@ aiagents4pharma/talk2scholars/tools/zotero/utils/review_helper.py,sha256=IPD1V9y
 aiagents4pharma/talk2scholars/tools/zotero/utils/write_helper.py,sha256=ALwLecy1QVebbsmXJiDj1GhGmyhq2R2tZlAyEl1vfhw,7410
 aiagents4pharma/talk2scholars/tools/zotero/utils/zotero_path.py,sha256=oIrfbOySgts50ksHKyjcWjRkPRIS88g3Lc0v9mBkU8w,6375
 aiagents4pharma/talk2scholars/tools/zotero/utils/zotero_pdf_downloader.py,sha256=ERBha8afU6Q1EaRBe9qB8tchOzZ4_KfFgDW6EElOJoU,4816
-aiagents4pharma-1.42.0.dist-info/licenses/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
-aiagents4pharma-1.42.0.dist-info/METADATA,sha256=qbfg8yUF-3Tn5k82Ry5wCuLNzv6PWVpeL46inguNRuI,12894
-aiagents4pharma-1.42.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-aiagents4pharma-1.42.0.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
-aiagents4pharma-1.42.0.dist-info/RECORD,,
+aiagents4pharma-1.43.0.dist-info/licenses/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
+aiagents4pharma-1.43.0.dist-info/METADATA,sha256=9gum-z3uXsxDqDhQjnjD8tHEoNpfSFgxeusKXRC3WJ0,13281
+aiagents4pharma-1.43.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+aiagents4pharma-1.43.0.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
+aiagents4pharma-1.43.0.dist-info/RECORD,,

aiagents4pharma/talk2scholars/configs/tools/download_arxiv_paper/default.yaml DELETED Viewed

@@ -1,4 +0,0 @@
-api_url: "http://export.arxiv.org/api/query"
-request_timeout: 10
-chunk_size: 1024
-pdf_base_url: "https://arxiv.org/pdf"

aiagents4pharma/talk2scholars/configs/tools/download_biorxiv_paper/__init__.py DELETED Viewed

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

aiagents4pharma/talk2scholars/configs/tools/download_biorxiv_paper/default.yaml DELETED Viewed

	@@ -1,2 +0,0 @@
1	- api_url: "https://api.biorxiv.org/details/biorxiv/"
2	- request_timeout: 20

aiagents4pharma/talk2scholars/configs/tools/download_medrxiv_paper/__init__.py DELETED Viewed

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

aiagents4pharma/talk2scholars/configs/tools/download_medrxiv_paper/default.yaml DELETED Viewed

	@@ -1,2 +0,0 @@
1	- api_url: "https://api.biorxiv.org/details/medrxiv"
2	- request_timeout: 20

aiagents4pharma/talk2scholars/tests/test_paper_download_biorxiv.py DELETED Viewed

@@ -1,151 +0,0 @@
-"""
-Unit tests for bioRxiv paper downloading functionality, including:
-- download_bioRxiv_paper tool function.
-"""
-import unittest
-from unittest.mock import MagicMock, patch
-from langchain_core.messages import ToolMessage
-from aiagents4pharma.talk2scholars.tools.paper_download.download_biorxiv_input import (
-    download_biorxiv_paper,
-)
-class TestDownloadBiorxivPaper(unittest.TestCase):
-    """Tests for the download_bioRxiv_paper tool."""
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_biorxiv_input.hydra.initialize"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_biorxiv_input.hydra.compose"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_biorxiv_input.requests.get"
-    )
-    def test_download_biorxiv_paper_success(self, mock_get, mock_compose, mock_initialize):
-        """Test successful metadata and PDF URL retrieval."""
-        dummy_cfg = MagicMock()
-        dummy_cfg.tools.download_biorxiv_paper.api_url = "http://dummy.biorxiv.org/api"
-        dummy_cfg.tools.download_biorxiv_paper.request_timeout = 10
-        mock_compose.return_value = dummy_cfg
-        mock_initialize.return_value.__enter__.return_value = None
-        doi = "10.1101/2025.05.13.653102"
-        dummy_response = MagicMock()
-        dummy_response.status_code = 200
-        dummy_response.raise_for_status = MagicMock()
-        dummy_response.json.return_value = {
-            "collection": [
-                {
-                    "title": "Sample BioRxiv Paper",
-                    "authors": "Author One; Author Two",
-                    "abstract": "This is a bioRxiv abstract.",
-                    "date": "2025-04-25",
-                    "doi": doi,
-                    "link": f"https://www.biorxiv.org/content/{doi}.full.pdf"
-                }
-            ]
-        }
-        mock_get.return_value = dummy_response
-        tool_input = {"doi": doi, "tool_call_id": "test_tool_id"}
-        result = download_biorxiv_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 BioRxiv Paper")
-        self.assertEqual(metadata["Authors"], "Author One; Author Two")
-        self.assertEqual(metadata["Abstract"], "This is a bioRxiv abstract.")
-        self.assertEqual(metadata["Publication Date"], "2025-04-25")
-        self.assertEqual(metadata["URL"], f"https://www.biorxiv.org/content/{doi}.full.pdf")
-        self.assertEqual(metadata["pdf_url"], f"https://www.biorxiv.org/content/{doi}.full.pdf")
-        self.assertEqual(metadata["filename"], f"{doi.rsplit('/', maxsplit=1)[-1]}.pdf")
-        self.assertEqual(metadata["source"], "biorxiv")
-        self.assertEqual(metadata["biorxiv_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_biorxiv_input.hydra.initialize"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_biorxiv_input.hydra.compose"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_biorxiv_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_biorxiv_paper.api_url = "http://dummy.biorxiv.org/api"
-        dummy_cfg.tools.download_biorxiv_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 = "10.1101/2025.05.13.653102"
-        tool_input = {"doi": doi, "tool_call_id": "test_tool_id"}
-        with self.assertRaises(ValueError) as context:
-            download_biorxiv_paper.run(tool_input)
-        self.assertEqual(str(context.exception), f"No metadata found for DOI: {doi}")
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_biorxiv_input.hydra.initialize"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_biorxiv_input.hydra.compose"
-    )
-    @patch(
-        "aiagents4pharma.talk2scholars.tools.paper_download.download_biorxiv_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_biorxiv_paper.api_url = "http://dummy.biorxiv.org/api"
-        dummy_cfg.tools.download_biorxiv_paper.request_timeout = 10
-        mock_compose.return_value = dummy_cfg
-        mock_initialize.return_value.__enter__.return_value = None
-        doi = "10.1101/2025.05.13.653102"
-        dummy_response = MagicMock()
-        dummy_response.status_code = 200
-        dummy_response.raise_for_status = MagicMock()
-        dummy_response.json.return_value = {
-            "collection": [
-                {
-                    "title": "Sample Biorxiv Paper",
-                    "authors": "Author One; Author Two",
-                    "abstract": "This is a BioRxiv 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_biorxiv_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.biorxiv.org/content/10.1101/{expected_suffix}.full.pdf"
-        self.assertEqual(metadata["pdf_url"], expected_url)

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

aiagents4pharma 1.42.0py3-none-any.whl → 1.43.0py3-none-any.whl