aiagents4pharma 1.44.0__py3-none-any.whl → 1.45.1__py3-none-any.whl

aiagents4pharma/talk2scholars/tools/zotero/utils/read_helper.py

@@ -5,7 +5,7 @@ Utility for zotero read tool.
 """
 
 import logging
-from typing import Any, Dict, List
+from typing import Any
 
 import hydra
 import requests
@@ -51,7 +51,7 @@ class ZoteroSearchData:
         self._filter_and_format_papers(items)
         self._create_content()
 
-    def get_search_results(self) -> Dict[str, Any]:
+    def get_search_results(self) -> dict[str, Any]:
         """Get the search results and content."""
         return {
             "article_data": self.article_data,
@@ -61,9 +61,7 @@ class ZoteroSearchData:
     def _load_config(self) -> Any:
         """Load hydra configuration."""
         with hydra.initialize(version_base=None, config_path="../../../configs"):
-            cfg = hydra.compose(
-                config_name="config", overrides=["tools/zotero_read=default"]
-            )
+            cfg = hydra.compose(config_name="config", overrides=["tools/zotero_read=default"])
             logger.info("Loaded configuration for Zotero search tool")
             return cfg.tools.zotero_read
 
@@ -77,7 +75,7 @@ class ZoteroSearchData:
         )
         return zotero.Zotero(self.cfg.user_id, self.cfg.library_type, self.cfg.api_key)
 
-    def _fetch_items(self) -> List[Dict[str, Any]]:
+    def _fetch_items(self) -> list[dict[str, Any]]:
         """Fetch items from Zotero."""
         try:
             if self.query.strip() == "":
@@ -100,15 +98,13 @@ class ZoteroSearchData:
 
         if not items:
             logger.error("No items returned from Zotero for query: '%s'", self.query)
-            raise RuntimeError(
-                "No items returned from Zotero. Please retry the same query."
-            )
+            raise RuntimeError("No items returned from Zotero. Please retry the same query.")
 
         return items
 
-    def _collect_item_attachments(self) -> Dict[str, str]:
+    def _collect_item_attachments(self) -> dict[str, str]:
         """Collect PDF attachment keys for non-orphan items."""
-        item_attachments: Dict[str, str] = {}
+        item_attachments: dict[str, str] = {}
         for item_key, item_data in self.article_data.items():
             if item_data.get("Type") == "orphan_attachment":
                 continue
@@ -127,7 +123,7 @@ class ZoteroSearchData:
                 logger.error("Failed to get attachments for item %s: %s", item_key, e)
         return item_attachments
 
-    def _process_orphaned_pdfs(self, orphaned_pdfs: Dict[str, str]) -> None:
+    def _process_orphaned_pdfs(self, orphaned_pdfs: dict[str, str]) -> None:
         """Download or record orphaned PDF attachments."""
         if self.download_pdfs:
             logger.info("Downloading %d orphaned PDFs in parallel", len(orphaned_pdfs))
@@ -147,16 +143,14 @@ class ZoteroSearchData:
             logger.info("Skipping orphaned PDF downloads (download_pdfs=False)")
             for attachment_key in orphaned_pdfs:
                 self.article_data[attachment_key]["attachment_key"] = attachment_key
-                self.article_data[attachment_key]["filename"] = (
-                    self.article_data[attachment_key].get("Title", attachment_key)
-                )
+                self.article_data[attachment_key]["filename"] = self.article_data[
+                    attachment_key
+                ].get("Title", attachment_key)
 
-    def _process_item_pdfs(self, item_attachments: Dict[str, str]) -> None:
+    def _process_item_pdfs(self, item_attachments: dict[str, str]) -> None:
         """Download or record regular item PDF attachments."""
         if self.download_pdfs:
-            logger.info(
-                "Downloading %d regular item PDFs in parallel", len(item_attachments)
-            )
+            logger.info("Downloading %d regular item PDFs in parallel", len(item_attachments))
             results = download_pdfs_in_parallel(
                 self.session,
                 self.cfg.user_id,
@@ -175,15 +169,13 @@ class ZoteroSearchData:
             self.article_data[item_key]["attachment_key"] = attachment_key
             logger.info("Downloaded Zotero PDF to: %s", file_path)
 
-    def _filter_and_format_papers(self, items: List[Dict[str, Any]]) -> None:
+    def _filter_and_format_papers(self, items: list[dict[str, Any]]) -> None:
         """Filter and format papers from Zotero items, including standalone PDFs."""
-        filter_item_types = (
-            self.cfg.zotero.filter_item_types if self.only_articles else []
-        )
+        filter_item_types = self.cfg.zotero.filter_item_types if self.only_articles else []
         logger.debug("Filtering item types: %s", filter_item_types)
 
         # Maps to track attachments for batch processing
-        orphaned_pdfs: Dict[str, str] = {}  # attachment_key -> item key (same for orphans)
+        orphaned_pdfs: dict[str, str] = {}  # attachment_key -> item key (same for orphans)
 
         # First pass: process all items without downloading PDFs
         for item in items:
@@ -214,17 +206,14 @@ class ZoteroSearchData:
                     "Authors": [
                         f"{creator.get('firstName', '')} {creator.get('lastName', '')}".strip()
                         for creator in data.get("creators", [])
-                        if isinstance(creator, dict)
-                        and creator.get("creatorType") == "author"
+                        if isinstance(creator, dict) and creator.get("creatorType") == "author"
                     ],
                     "source": "zotero",
                 }
                 # We'll collect attachment info in second pass
 
             # CASE 2: Standalone orphaned PDF attachment
-            elif data.get("contentType") == "application/pdf" and not data.get(
-                "parentItem"
-            ):
+            elif data.get("contentType") == "application/pdf" and not data.get("parentItem"):
                 attachment_key = key
                 filename = data.get("filename", "unknown.pdf")
 
@@ -260,25 +249,18 @@ class ZoteroSearchData:
 
         # Ensure we have some results
         if not self.article_data:
-            logger.error(
-                "No matching papers returned from Zotero for query: '%s'", self.query
-            )
+            logger.error("No matching papers returned from Zotero for query: '%s'", self.query)
             raise RuntimeError(
                 "No matching papers returned from Zotero. Please retry the same query."
             )
 
-        logger.info(
-            "Filtered %d items (including orphaned attachments)", len(self.article_data)
-        )
+        logger.info("Filtered %d items (including orphaned attachments)", len(self.article_data))
 
     def _create_content(self) -> None:
         """Create the content message for the response."""
         top_papers = list(self.article_data.values())[:2]
         top_papers_info = "\n".join(
-            [
-                f"{i+1}. {paper['Title']} ({paper['Type']})"
-                for i, paper in enumerate(top_papers)
-            ]
+            [f"{i + 1}. {paper['Title']} ({paper['Type']})" for i, paper in enumerate(top_papers)]
         )
 
         self.content = "Retrieval was successful. Papers are attached as an artifact."

aiagents4pharma/talk2scholars/tools/zotero/utils/review_helper.py

@@ -5,7 +5,6 @@ Utility for reviewing papers and saving them to Zotero.
 """
 
 import logging
-from typing import List
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -40,12 +39,9 @@ class ReviewData:
 
     def get_custom_path_approval_message(self, custom_path: str) -> str:
         """Get the formatted approval message for a custom collection path."""
-        return (
-            f"Human approved saving papers to custom Zotero "
-            f"collection '{custom_path}'."
-        )
+        return f"Human approved saving papers to custom Zotero collection '{custom_path}'."
 
-    def _create_papers_summary(self) -> List[str]:
+    def _create_papers_summary(self) -> list[str]:
         """Create a summary of papers for review."""
         summary = []
         for paper_id, paper in list(self.fetched_papers.items())[:5]:

aiagents4pharma/talk2scholars/tools/zotero/utils/write_helper.py

@@ -5,15 +5,16 @@ Utility for zotero write tool.
 """
 
 import logging
-from typing import Any, Dict
+from typing import Any
+
 import hydra
 from pyzotero import zotero
+
 from .zotero_path import (
-    find_or_create_collection,
     fetch_papers_for_save,
+    find_or_create_collection,
 )
 
-
 # Configure logging
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
@@ -41,9 +42,7 @@ class ZoteroWriteData:
     def _load_config(self) -> Any:
         """Load hydra configuration."""
         with hydra.initialize(version_base=None, config_path="../../../configs"):
-            cfg = hydra.compose(
-                config_name="config", overrides=["tools/zotero_write=default"]
-            )
+            cfg = hydra.compose(config_name="config", overrides=["tools/zotero_write=default"])
             logger.info("Loaded configuration for Zotero write tool")
             return cfg.tools.zotero_write
 
@@ -107,9 +106,7 @@ class ZoteroWriteData:
                     if " " in name
                     else {"creatorType": "author", "lastName": name}
                 )
-                for name in [
-                    author.split(" (ID: ")[0] for author in paper.get("Authors", [])
-                ]
+                for name in [author.split(" (ID: ")[0] for author in paper.get("Authors", [])]
             ]
 
             self.zotero_items.append(
@@ -152,13 +149,13 @@ class ZoteroWriteData:
         top_papers = list(self.fetched_papers.values())[:2]
         top_papers_info = "\n".join(
             [
-                f"{i+1}. {paper.get('Title', 'N/A')} ({paper.get('URL', 'N/A')})"
+                f"{i + 1}. {paper.get('Title', 'N/A')} ({paper.get('URL', 'N/A')})"
                 for i, paper in enumerate(top_papers)
             ]
         )
         self.content += "Here are a few of these articles:\n" + top_papers_info
 
-    def process_write(self) -> Dict[str, Any]:
+    def process_write(self) -> dict[str, Any]:
         """Process the write operation and return results."""
         self._validate_papers()
         matched_collection_key = self._find_collection()

aiagents4pharma/talk2scholars/tools/zotero/utils/zotero_path.py

@@ -29,9 +29,7 @@ def get_item_collections(zot):
 
     # Create mappings: collection key → name and collection key → parent key
     collection_map = {col["key"]: col["data"]["name"] for col in collections}
-    parent_map = {
-        col["key"]: col["data"].get("parentCollection") for col in collections
-    }
+    parent_map = {col["key"]: col["data"].get("parentCollection") for col in collections}
 
     # Build full paths for collections
     def build_collection_path(col_key):
@@ -49,9 +47,7 @@ def get_item_collections(zot):
 
     for collection in collections:
         collection_key = collection["key"]
-        collection_items = zot.collection_items(
-            collection_key
-        )  # Fetch items in the collection
+        collection_items = zot.collection_items(collection_key)  # Fetch items in the collection
 
         for item in collection_items:
             item_key = item["data"]["key"]
@@ -67,9 +63,7 @@ def get_item_collections(zot):
 
 def find_or_create_collection(zot, path, create_missing=False):
     """find collection or create if missing"""
-    logger.info(
-        "Finding collection for path: %s (create_missing=%s)", path, create_missing
-    )
+    logger.info("Finding collection for path: %s (create_missing=%s)", path, create_missing)
     # Normalize path: remove leading/trailing slashes and convert to lowercase
     normalized = path.strip("/").lower()
     path_parts = normalized.split("/") if normalized else []
@@ -136,9 +130,7 @@ def get_all_collection_paths(zot):
 
     # Create mappings: collection key → name and collection key → parent key
     collection_map = {col["key"]: col["data"]["name"] for col in collections}
-    parent_map = {
-        col["key"]: col["data"].get("parentCollection") for col in collections
-    }
+    parent_map = {col["key"]: col["data"].get("parentCollection") for col in collections}
 
     # Build full paths for collections
     def build_collection_path(col_key):

aiagents4pharma/talk2scholars/tools/zotero/utils/zotero_pdf_downloader.py

@@ -3,10 +3,10 @@
 Utility functions for downloading PDFs from Zotero.
 """
 
+import concurrent.futures
 import logging
 import tempfile
-from typing import Optional, Tuple, Dict
-import concurrent.futures
+
 import requests
 
 logger = logging.getLogger(__name__)
@@ -18,7 +18,7 @@ def download_zotero_pdf(
     api_key: str,
     attachment_key: str,
     **kwargs,
-) -> Optional[Tuple[str, str]]:
+) -> tuple[str, str] | None:
     """
     Download a PDF from Zotero by attachment key.
 
@@ -40,18 +40,12 @@ def download_zotero_pdf(
     # Log configured parameters for verification
     logger.info("download_zotero_pdf params -> timeout=%s, chunk_size=%s", timeout, chunk_size)
     # Log download start
-    logger.info(
-        "Downloading Zotero PDF for attachment %s from Zotero API", attachment_key
-    )
-    zotero_pdf_url = (
-        f"https://api.zotero.org/users/{user_id}/items/" f"{attachment_key}/file"
-    )
+    logger.info("Downloading Zotero PDF for attachment %s from Zotero API", attachment_key)
+    zotero_pdf_url = f"https://api.zotero.org/users/{user_id}/items/{attachment_key}/file"
     headers = {"Zotero-API-Key": api_key}
 
     try:
-        response = session.get(
-            zotero_pdf_url, headers=headers, stream=True, timeout=timeout
-        )
+        response = session.get(zotero_pdf_url, headers=headers, stream=True, timeout=timeout)
         response.raise_for_status()
 
         # Download to a temporary file first
@@ -65,9 +59,7 @@ def download_zotero_pdf(
         # Determine filename from Content-Disposition header or default
         if "filename=" in response.headers.get("Content-Disposition", ""):
             filename = (
-                response.headers.get("Content-Disposition", "")
-                .split("filename=")[-1]
-                .strip('"')
+                response.headers.get("Content-Disposition", "").split("filename=")[-1].strip('"')
             )
         else:
             filename = "downloaded.pdf"
@@ -75,9 +67,7 @@ def download_zotero_pdf(
         return temp_file_path, filename
 
     except (requests.exceptions.RequestException, OSError) as e:
-        logger.error(
-            "Failed to download Zotero PDF for attachment %s: %s", attachment_key, e
-        )
+        logger.error("Failed to download Zotero PDF for attachment %s: %s", attachment_key, e)
         return None
 
 
@@ -85,9 +75,9 @@ def download_pdfs_in_parallel(
     session: requests.Session,
     user_id: str,
     api_key: str,
-    attachment_item_map: Dict[str, str],
+    attachment_item_map: dict[str, str],
     **kwargs,
-) -> Dict[str, Tuple[str, str, str]]:
+) -> dict[str, tuple[str, str, str]]:
     """
     Download multiple PDFs in parallel using ThreadPoolExecutor.
 
@@ -108,20 +98,16 @@ def download_pdfs_in_parallel(
     chunk_size = kwargs.get("chunk_size")
     # Log configured parameters for verification
     logger.info(
-        "download_pdfs_in_parallel params -> max_workers=%s, chunk_size=%s", 
+        "download_pdfs_in_parallel params -> max_workers=%s, chunk_size=%s",
         max_workers,
         chunk_size,
     )
-    results: Dict[str, Tuple[str, str, str]] = {}
+    results: dict[str, tuple[str, str, str]] = {}
     if not attachment_item_map:
         return results
 
     with concurrent.futures.ThreadPoolExecutor(
-        max_workers=(
-            max_workers
-            if max_workers is not None
-            else min(10, len(attachment_item_map))
-        )
+        max_workers=(max_workers if max_workers is not None else min(10, len(attachment_item_map)))
     ) as executor:
         future_to_keys = {
             executor.submit(

aiagents4pharma/talk2scholars/tools/zotero/zotero_read.py

@@ -10,13 +10,14 @@ for each found item and makes the results available as an artifact.
 
 import logging
 from typing import Annotated, Any
+
 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
-from .utils.read_helper import ZoteroSearchData
 
+from .utils.read_helper import ZoteroSearchData
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -34,16 +35,12 @@ class ZoteroSearchInput(BaseModel):
         tool_call_id (str): Internal identifier for this tool invocation.
     """
 
-    query: str = Field(
-        description="Search query string to find papers in Zotero library."
-    )
+    query: str = Field(description="Search query string to find papers in Zotero library.")
     only_articles: bool = Field(
         default=True,
         description="Whether to only search for journal articles/conference papers.",
     )
-    limit: int = Field(
-        default=2, description="Maximum number of results to return", ge=1, le=100
-    )
+    limit: int = Field(default=2, description="Maximum number of results to return", ge=1, le=100)
     download_pdfs: bool = Field(
         default=False,
         description="Whether to download PDF attachments immediately (default True).",

aiagents4pharma/talk2scholars/tools/zotero/zotero_review.py

@@ -5,15 +5,17 @@ This tool implements human-in-the-loop review for Zotero write operations.
 """
 
 import logging
-from typing import Annotated, Any, Optional, Literal
+from typing import Annotated, Any, Literal
+
+from langchain_core.messages import HumanMessage, ToolMessage
 from langchain_core.tools import tool
-from langchain_core.messages import ToolMessage, HumanMessage
 from langchain_core.tools.base import InjectedToolCallId
 from langgraph.prebuilt import InjectedState
 from langgraph.types import Command, interrupt
 from pydantic import BaseModel, Field
-from .utils.zotero_path import fetch_papers_for_save
+
 from .utils.review_helper import ReviewData
+from .utils.zotero_path import fetch_papers_for_save
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -28,7 +30,7 @@ class ZoteroReviewDecision(BaseModel):
     """
 
     decision: Literal["approve", "reject", "custom"]
-    custom_path: Optional[str] = None
+    custom_path: str | None = None
 
 
 class ZoteroReviewInput(BaseModel):
@@ -83,9 +85,7 @@ def zotero_review(
             raise ValueError("LLM model is not available in the state.")
         structured_llm = llm_model.with_structured_output(ZoteroReviewDecision)
         # Convert the raw human response to a message for structured parsing
-        decision_response = structured_llm.invoke(
-            [HumanMessage(content=str(human_review))]
-        )
+        decision_response = structured_llm.invoke([HumanMessage(content=str(human_review))])
 
         # Process the structured response
         if decision_response.decision == "approve":
@@ -105,9 +105,7 @@ def zotero_review(
                 }
             )
         if decision_response.decision == "custom" and decision_response.custom_path:
-            logger.info(
-                "User approved with custom path: %s", decision_response.custom_path
-            )
+            logger.info("User approved with custom path: %s", decision_response.custom_path)
             return Command(
                 update={
                     "messages": [

aiagents4pharma/talk2scholars/tools/zotero/zotero_write.py

@@ -6,14 +6,15 @@ This tool is used to save fetched papers to Zotero library after human approval.
 
 import logging
 from typing import Annotated, Any
+
 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 langgraph.prebuilt import InjectedState
+from langgraph.types import Command
 from pydantic import BaseModel, Field
-from .utils.write_helper import ZoteroWriteData
 
+from .utils.write_helper import ZoteroWriteData
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)