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

aiagents4pharma/talk2scholars/tools/s2/__init__.py

@@ -2,12 +2,14 @@
 This file is used to import all the modules in the package.
 """
 
-from . import display_dataframe
-from . import multi_paper_rec
-from . import search
-from . import single_paper_rec
-from . import query_dataframe
-from . import retrieve_semantic_scholar_paper_id
+from . import (
+    display_dataframe,
+    multi_paper_rec,
+    query_dataframe,
+    retrieve_semantic_scholar_paper_id,
+    search,
+    single_paper_rec,
+)
 
 __all__ = [
     "display_dataframe",

aiagents4pharma/talk2scholars/tools/s2/display_dataframe.py

@@ -12,17 +12,15 @@ only displays the existing list. If no papers are available, it raises NoPapersF
 to signal that a search or recommendation must be executed first.
 """
 
-
 import logging
-
 from typing import Annotated
-from pydantic import BaseModel, Field
+
 from langchain_core.messages import ToolMessage
 from langchain_core.tools import tool
 from langchain_core.tools.base import InjectedToolCallId
 from langgraph.prebuilt import InjectedState
 from langgraph.types import Command
-
+from pydantic import BaseModel, Field
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -97,9 +95,7 @@ def display_dataframe(
         artifact = state.get(context_val)
     if not artifact:
         logger.info("No papers found in state, raising NoPapersFoundError")
-        raise NoPapersFoundError(
-            "No papers found. A search/rec needs to be performed first."
-        )
+        raise NoPapersFoundError("No papers found. A search/rec needs to be performed first.")
     content = f"{len(artifact)} papers found. Papers are attached as an artifact."
     return Command(
         update={

aiagents4pharma/talk2scholars/tools/s2/multi_paper_rec.py

@@ -9,14 +9,15 @@ of recommended papers.
 """
 
 import logging
-from typing import Annotated, Any, List, Optional
+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.multi_helper import MultiPaperRecData
 
+from .utils.multi_helper import MultiPaperRecData
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -34,7 +35,7 @@ class MultiPaperRecInput(BaseModel):
         tool_call_id: Internal tool call identifier injected by the system.
     """
 
-    paper_ids: List[str] = Field(
+    paper_ids: list[str] = Field(
         description="List of 40-character Semantic Scholar Paper IDs"
         "(at least two) to base recommendations on"
     )
@@ -44,7 +45,7 @@ class MultiPaperRecInput(BaseModel):
         ge=1,
         le=500,
     )
-    year: Optional[str] = Field(
+    year: str | None = Field(
         default=None,
         description="Publication year filter; supports formats:"
         "'YYYY', 'YYYY-', '-YYYY', 'YYYY:YYYY'",
@@ -59,10 +60,10 @@ class MultiPaperRecInput(BaseModel):
     parse_docstring=True,
 )
 def get_multi_paper_recommendations(
-    paper_ids: List[str],
+    paper_ids: list[str],
     tool_call_id: Annotated[str, InjectedToolCallId],
     limit: int = 10,
-    year: Optional[str] = None,
+    year: str | None = None,
 ) -> Command[Any]:
     """
     Recommend related research papers using the Semantic Scholar API.

aiagents4pharma/talk2scholars/tools/s2/query_dataframe.py

@@ -26,9 +26,8 @@ Notes
   first identifier is returned; otherwise a list is returned from all rows that have values.
 """
 
-
 import logging
-from typing import Annotated, Optional, Any
+from typing import Annotated, Any
 
 import pandas as pd
 from langchain_core.messages import ToolMessage
@@ -99,7 +98,7 @@ class QueryDataFrameInput(BaseModel):
             "extract when extract_ids=True."
         ),
     )
-    row_number: Optional[int] = Field(
+    row_number: int | None = Field(
         default=None,
         description=(
             "1-based index of the ID to extract from the list; if provided, returns only"
@@ -180,9 +179,7 @@ def query_dataframe(
     context_val = state.get("last_displayed_papers")
     if not context_val:
         logger.info("No papers displayed so far, raising NoPapersFoundError")
-        raise NoPapersFoundError(
-            "No papers found. A search needs to be performed first."
-        )
+        raise NoPapersFoundError("No papers found. A search needs to be performed first.")
 
     # Resolve the paper dictionary
     if isinstance(context_val, dict):
@@ -205,14 +202,10 @@ def query_dataframe(
         if not id_column:
             raise ValueError("Must specify 'id_column' when extract_ids=True.")
         if row_number is not None:
-            question_to_agent = (
-                f"df['{id_column}'].dropna().str[0].tolist()[{row_number-1}]"
-            )
+            question_to_agent = f"df['{id_column}'].dropna().str[0].tolist()[{row_number - 1}]"
         else:
             question_to_agent = f"df['{id_column}'].dropna().str[0].tolist()"
-        logger.info(
-            "extract_ids enabled: asking agent to run expression: %s", question_to_agent
-        )
+        logger.info("extract_ids enabled: asking agent to run expression: %s", question_to_agent)
 
     df_agent = create_pandas_dataframe_agent(
         llm_model,

aiagents4pharma/talk2scholars/tools/s2/retrieve_semantic_scholar_paper_id.py

@@ -10,6 +10,7 @@ Configuration is loaded via Hydra and the top ranked result is returned.
 
 import logging
 from typing import Annotated, Any
+
 import hydra
 import requests
 from langchain_core.messages import ToolMessage
@@ -18,7 +19,6 @@ 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__)
@@ -36,9 +36,7 @@ class RetrieveSemanticScholarPaperIdInput(BaseModel):
         Runtime-injected identifier for tracing the tool invocation.
     """
 
-    paper_title: str = Field(
-        ..., description="The paper title to search for on Semantic Scholar."
-    )
+    paper_title: str = Field(..., description="The paper title to search for on Semantic Scholar.")
     tool_call_id: Annotated[str, InjectedToolCallId]
 
 

aiagents4pharma/talk2scholars/tools/s2/search.py

@@ -8,12 +8,14 @@ optionally filtered by publication year.
 """
 
 import logging
-from typing import Annotated, Any, Optional
+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.search_helper import SearchData
 
 # Configure logging
@@ -32,16 +34,14 @@ class SearchInput(BaseModel):
         tool_call_id: Internal tool call identifier injected by the system.
     """
 
-    query: str = Field(
-        description="Full or partial paper title or keywords to search for"
-    )
+    query: str = Field(description="Full or partial paper title or keywords to search for")
     limit: int = Field(
         default=10,
         description="Maximum number of search results to return (1-100)",
         ge=1,
         le=100,
     )
-    year: Optional[str] = Field(
+    year: str | None = Field(
         default=None,
         description="Publication year filter; supports formats:"
         "'YYYY', 'YYYY-', '-YYYY', 'YYYY:YYYY'",
@@ -58,7 +58,7 @@ def search_tool(
     query: str,
     tool_call_id: Annotated[str, InjectedToolCallId],
     limit: int = 10,
-    year: Optional[str] = None,
+    year: str | None = None,
 ) -> Command[Any]:
     """
     Return academic papers from Semantic Scholar matching a title or keyword query.

aiagents4pharma/talk2scholars/tools/s2/single_paper_rec.py

@@ -8,12 +8,14 @@ Given a Semantic Scholar paper ID, this tool retrieves related works
 """
 
 import logging
-from typing import Annotated, Any, Optional
+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.single_helper import SinglePaperRecData
 
 # Configure logging
@@ -40,7 +42,7 @@ class SinglePaperRecInput(BaseModel):
         ge=1,
         le=500,
     )
-    year: Optional[str] = Field(
+    year: str | None = Field(
         default=None,
         description="Publication year filter; supports formats::"
         "'YYYY', 'YYYY-', '-YYYY', 'YYYY:YYYY'",
@@ -57,7 +59,7 @@ def get_single_paper_recommendations(
     paper_id: str,
     tool_call_id: Annotated[str, InjectedToolCallId],
     limit: int = 10,
-    year: Optional[str] = None,
+    year: str | None = None,
 ) -> Command[Any]:
     """
     Recommend related research papers using the Semantic Scholar API for a single paper ID.

aiagents4pharma/talk2scholars/tools/s2/utils/__init__.py

@@ -1,7 +1,5 @@
 """This module contains utility functions for the Semantic Scholar search tool."""
 
-from . import search_helper
-from . import single_helper
-from . import multi_helper
+from . import multi_helper, search_helper, single_helper
 
 __all__ = ["search_helper", "single_helper", "multi_helper"]

aiagents4pharma/talk2scholars/tools/s2/utils/multi_helper.py

@@ -6,11 +6,11 @@ Utility for fetching recommendations based on multiple papers.
 
 import json
 import logging
-from typing import Any, List, Optional, Dict
+from typing import Any
+
 import hydra
 import requests
 
-
 # Configure logging
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
@@ -21,9 +21,9 @@ class MultiPaperRecData:
 
     def __init__(
         self,
-        paper_ids: List[str],
+        paper_ids: list[str],
         limit: int,
-        year: Optional[str],
+        year: str | None,
         tool_call_id: str,
     ):
         self.paper_ids = paper_ids
@@ -51,7 +51,7 @@ class MultiPaperRecData:
             logger.info("Loaded configuration for multi-paper recommendation tool")
             return cfg.tools.multi_paper_recommendation
 
-    def _create_params(self) -> Dict[str, Any]:
+    def _create_params(self) -> dict[str, Any]:
         """Create parameters for the API request."""
         params = {
             "limit": min(self.limit, 500),
@@ -94,9 +94,7 @@ class MultiPaperRecData:
                     ) from e
 
         if self.response is None:
-            raise RuntimeError(
-                "Failed to obtain a response from the Semantic Scholar API."
-            )
+            raise RuntimeError("Failed to obtain a response from the Semantic Scholar API.")
 
         logger.info(
             "API Response Status for multi-paper recommendations: %s",
@@ -117,9 +115,7 @@ class MultiPaperRecData:
 
         self.recommendations = self.data.get("recommendedPapers", [])
         if not self.recommendations:
-            logger.error(
-                "No recommendations returned from API for paper IDs: %s", self.paper_ids
-            )
+            logger.error("No recommendations returned from API for paper IDs: %s", self.paper_ids)
             raise RuntimeError(
                 "No recommendations were found for your query. Consider refining your search "
                 "by using more specific keywords or different terms."
@@ -128,12 +124,12 @@ class MultiPaperRecData:
     def _filter_papers(self) -> None:
         """Filter and format papers."""
         # Build filtered recommendations with unified paper_ids
-        filtered: Dict[str, Any] = {}
+        filtered: dict[str, Any] = {}
         for paper in self.recommendations:
             if not paper.get("title") or not paper.get("authors"):
                 continue
             ext = paper.get("externalIds", {}) or {}
-            ids: List[str] = []
+            ids: list[str] = []
             arxiv = ext.get("ArXiv")
             if arxiv:
                 ids.append(f"arxiv:{arxiv}")
@@ -191,7 +187,7 @@ class MultiPaperRecData:
             title = paper.get("Title", "N/A")
             year = paper.get("Year", "N/A")
             snippet = self._get_snippet(paper.get("Abstract", ""))
-            entry = f"{i+1}. {title} ({year})"
+            entry = f"{i + 1}. {title} ({year})"
             if snippet:
                 entry += f"\n   Abstract snippet: {snippet}"
             entries.append(entry)
@@ -202,14 +198,12 @@ class MultiPaperRecData:
             "Papers are attached as an artifact."
         )
         self.content += " Here is a summary of the recommendations:\n"
-        self.content += (
-            f"Number of recommended papers found: {self.get_paper_count()}\n"
-        )
+        self.content += f"Number of recommended papers found: {self.get_paper_count()}\n"
         self.content += f"Query Paper IDs: {', '.join(self.paper_ids)}\n"
         self.content += f"Year: {self.year}\n" if self.year else ""
         self.content += "Here are a few of these papers:\n" + top_papers_info
 
-    def process_recommendations(self) -> Dict[str, Any]:
+    def process_recommendations(self) -> dict[str, Any]:
         """Process the recommendations request and return results."""
         self._fetch_recommendations()
         self._filter_papers()

aiagents4pharma/talk2scholars/tools/s2/utils/search_helper.py

@@ -5,7 +5,8 @@ Utility for fetching recommendations based on a single paper.
 """
 
 import logging
-from typing import Any, Optional, Dict
+from typing import Any
+
 import hydra
 import requests
 
@@ -21,7 +22,7 @@ class SearchData:
         self,
         query: str,
         limit: int,
-        year: Optional[str],
+        year: str | None,
         tool_call_id: str,
     ):
         self.query = query
@@ -40,13 +41,11 @@ class SearchData:
     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/search=default"]
-            )
+            cfg = hydra.compose(config_name="config", overrides=["tools/search=default"])
             logger.info("Loaded configuration for search tool")
             return cfg.tools.search
 
-    def _create_params(self) -> Dict[str, Any]:
+    def _create_params(self) -> dict[str, Any]:
         """Create parameters for the API request."""
         params = {
             "query": self.query,
@@ -64,9 +63,7 @@ class SearchData:
         # Wrap API call in try/except to catch connectivity issues
         for attempt in range(10):
             try:
-                self.response = requests.get(
-                    self.endpoint, params=self.params, timeout=10
-                )
+                self.response = requests.get(self.endpoint, params=self.params, timeout=10)
                 self.response.raise_for_status()  # Raises HTTPError for bad responses
                 break  # Exit loop if request is successful
             except requests.exceptions.RequestException as e:
@@ -82,9 +79,7 @@ class SearchData:
                     ) from e
 
         if self.response is None:
-            raise RuntimeError(
-                "Failed to obtain a response from the Semantic Scholar API."
-            )
+            raise RuntimeError("Failed to obtain a response from the Semantic Scholar API.")
 
         self.data = self.response.json()
 
@@ -99,9 +94,7 @@ class SearchData:
 
         self.papers = self.data.get("data", [])
         if not self.papers:
-            logger.error(
-                "No papers returned from Semantic Scholar API for query: %s", self.query
-            )
+            logger.error("No papers returned from Semantic Scholar API for query: %s", self.query)
             raise RuntimeError(
                 "No papers were found for your query. Consider refining your search "
                 "by using more specific keywords or different terms."
@@ -110,7 +103,7 @@ class SearchData:
     def _filter_papers(self) -> None:
         """Filter and format papers."""
         # Build filtered papers mapping with unified paper_ids list
-        filtered: Dict[str, Any] = {}
+        filtered: dict[str, Any] = {}
         for paper in self.papers:
             if not paper.get("title") or not paper.get("authors"):
                 continue
@@ -175,7 +168,7 @@ class SearchData:
             title = paper.get("Title", "N/A")
             year = paper.get("Year", "N/A")
             snippet = self._get_snippet(paper.get("Abstract", ""))
-            entry = f"{i+1}. {title} ({year})"
+            entry = f"{i + 1}. {title} ({year})"
             if snippet:
                 entry += f"\n   Abstract snippet: {snippet}"
             entries.append(entry)
@@ -192,7 +185,7 @@ class SearchData:
         self.content += f"Year: {self.year}\n" if self.year else ""
         self.content += "Top 3 papers:\n" + top_papers_info
 
-    def process_search(self) -> Dict[str, Any]:
+    def process_search(self) -> dict[str, Any]:
         """Process the search request and return results."""
         self._fetch_papers()
         self._filter_papers()

aiagents4pharma/talk2scholars/tools/s2/utils/single_helper.py

@@ -5,7 +5,8 @@ Utility for fetching recommendations based on a single paper.
 """
 
 import logging
-from typing import Any, Optional, Dict, List
+from typing import Any
+
 import hydra
 import requests
 
@@ -21,7 +22,7 @@ class SinglePaperRecData:
         self,
         paper_id: str,
         limit: int,
-        year: Optional[str],
+        year: str | None,
         tool_call_id: str,
     ):
         self.paper_id = paper_id
@@ -47,7 +48,7 @@ class SinglePaperRecData:
             logger.info("Loaded configuration for single paper recommendation tool")
             return cfg.tools.single_paper_recommendation
 
-    def _create_params(self) -> Dict[str, Any]:
+    def _create_params(self) -> dict[str, Any]:
         """Create parameters for the API request."""
         params = {
             "limit": min(self.limit, 500),  # Max 500 per API docs
@@ -86,9 +87,7 @@ class SinglePaperRecData:
                     ) from e
 
         if self.response is None:
-            raise RuntimeError(
-                "Failed to obtain a response from the Semantic Scholar API."
-            )
+            raise RuntimeError("Failed to obtain a response from the Semantic Scholar API.")
 
         logger.info(
             "API Response Status for recommendations of paper %s: %s",
@@ -110,9 +109,7 @@ class SinglePaperRecData:
 
         self.recommendations = self.data.get("recommendedPapers", [])
         if not self.recommendations:
-            logger.error(
-                "No recommendations returned from API for paper: %s", self.paper_id
-            )
+            logger.error("No recommendations returned from API for paper: %s", self.paper_id)
             raise RuntimeError(
                 "No recommendations were found for your query. Consider refining your search "
                 "by using more specific keywords or different terms."
@@ -121,12 +118,12 @@ class SinglePaperRecData:
     def _filter_papers(self) -> None:
         """Filter and format papers."""
         # Build filtered recommendations with unified paper_ids
-        filtered: Dict[str, Any] = {}
+        filtered: dict[str, Any] = {}
         for paper in self.recommendations:
             if not paper.get("title") or not paper.get("authors"):
                 continue
             ext = paper.get("externalIds", {}) or {}
-            ids: List[str] = []
+            ids: list[str] = []
             arxiv = ext.get("ArXiv")
             if arxiv:
                 ids.append(f"arxiv:{arxiv}")
@@ -184,7 +181,7 @@ class SinglePaperRecData:
             title = paper.get("Title", "N/A")
             year = paper.get("Year", "N/A")
             snippet = self._get_snippet(paper.get("Abstract", ""))
-            entry = f"{i+1}. {title} ({year})"
+            entry = f"{i + 1}. {title} ({year})"
             if snippet:
                 entry += f"\n   Abstract snippet: {snippet}"
             entries.append(entry)
@@ -195,13 +192,11 @@ class SinglePaperRecData:
             "Papers are attached as an artifact. "
             "Here is a summary of the recommendations:\n"
         )
-        self.content += (
-            f"Number of recommended papers found: {self.get_paper_count()}\n"
-        )
+        self.content += f"Number of recommended papers found: {self.get_paper_count()}\n"
         self.content += f"Query Paper ID: {self.paper_id}\n"
         self.content += "Here are a few of these papers:\n" + top_papers_info
 
-    def process_recommendations(self) -> Dict[str, Any]:
+    def process_recommendations(self) -> dict[str, Any]:
         """Process the recommendations request and return results."""
         self._fetch_recommendations()
         self._filter_papers()

aiagents4pharma/talk2scholars/tools/zotero/__init__.py

@@ -2,9 +2,6 @@
 Import statements
 """
 
-from . import zotero_read
-from . import zotero_write
-from . import utils
-from . import zotero_review
+from . import utils, zotero_read, zotero_review, zotero_write
 
 __all__ = ["zotero_read", "zotero_write", "utils", "zotero_review"]

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

@@ -2,9 +2,6 @@
 Import statements
 """
 
-from . import zotero_path
-from . import read_helper
-from . import write_helper
-from . import review_helper
+from . import read_helper, review_helper, write_helper, zotero_path
 
 __all__ = ["zotero_path", "read_helper", "write_helper", "review_helper"]