aiagents4pharma 1.43.0__py3-none-any.whl → 1.45.0__py3-none-any.whl

aiagents4pharma/talk2knowledgegraphs/utils/extractions/pcst.py

@@ -2,12 +2,14 @@
 Exctraction of subgraph using Prize-Collecting Steiner Tree (PCST) algorithm.
 """
 
-from typing import Tuple, NamedTuple
+from typing import NamedTuple
+
 import numpy as np
-import torch
 import pcst_fast
+import torch
 from torch_geometric.data.data import Data
 
+
 class PCSTPruning(NamedTuple):
     """
     Prize-Collecting Steiner Tree (PCST) pruning algorithm implementation inspired by G-Retriever
@@ -26,6 +28,7 @@ class PCSTPruning(NamedTuple):
         pruning: The pruning strategy to use.
         verbosity_level: The verbosity level.
     """
+
     topk: int = 3
     topk_e: int = 3
     cost_e: float = 0.5
@@ -76,9 +79,9 @@ class PCSTPruning(NamedTuple):
         e_prizes[e_prizes < topk_e_values[-1]] = 0.0
         last_topk_e_value = topk_e
         for k in range(topk_e):
-            indices = inverse_indices == (
-                unique_prizes == topk_e_values[k]
-            ).nonzero(as_tuple=True)[0]
+            indices = (
+                inverse_indices == (unique_prizes == topk_e_values[k]).nonzero(as_tuple=True)[0]
+            )
             value = min((topk_e - k) / indices.sum().item(), last_topk_e_value)
             e_prizes[indices] = value
             last_topk_e_value = value * (1 - self.c_const)
@@ -87,7 +90,7 @@ class PCSTPruning(NamedTuple):
 
     def compute_subgraph_costs(
         self, graph: Data, prizes: dict
-    ) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
+    ) -> tuple[np.ndarray, np.ndarray, np.ndarray]:
         """
         Compute the costs in constructing the subgraph proposed by G-Retriever paper.
 
@@ -145,7 +148,11 @@ class PCSTPruning(NamedTuple):
         return edges_dict, prizes, costs, mapping
 
     def get_subgraph_nodes_edges(
-        self, graph: Data, vertices: np.ndarray, edges_dict: dict, mapping: dict,
+        self,
+        graph: Data,
+        vertices: np.ndarray,
+        edges_dict: dict,
+        mapping: dict,
     ) -> dict:
         """
         Get the selected nodes and edges of the subgraph based on the vertices and edges computed
@@ -175,9 +182,7 @@ class PCSTPruning(NamedTuple):
             subgraph_edges = np.array(subgraph_edges + virtual_edges)
         edge_index = graph.edge_index[:, subgraph_edges]
         subgraph_nodes = np.unique(
-            np.concatenate(
-                [subgraph_nodes, edge_index[0].numpy(), edge_index[1].numpy()]
-            )
+            np.concatenate([subgraph_nodes, edge_index[0].numpy(), edge_index[1].numpy()])
         )
 
         return {"nodes": subgraph_nodes, "edges": subgraph_edges}
@@ -201,9 +206,7 @@ class PCSTPruning(NamedTuple):
         prizes = self.compute_prizes(graph, query_emb)
 
         # Compute costs in constructing the subgraph
-        edges_dict, prizes, costs, mapping = self.compute_subgraph_costs(
-            graph, prizes
-        )
+        edges_dict, prizes, costs, mapping = self.compute_subgraph_costs(graph, prizes)
 
         # Retrieve the subgraph using the PCST algorithm
         result_vertices, result_edges = pcst_fast.pcst_fast(
@@ -220,6 +223,7 @@ class PCSTPruning(NamedTuple):
             graph,
             result_vertices,
             {"edges": result_edges, "num_prior_edges": edges_dict["num_prior_edges"]},
-            mapping)
+            mapping,
+        )
 
         return subgraph

aiagents4pharma/talk2knowledgegraphs/utils/kg_utils.py

@@ -1,12 +1,12 @@
 #!/usr/bin/env python3
 
-'''A utility module for knowledge graph operations'''
+"""A utility module for knowledge graph operations"""
 
-from typing import Tuple
 import networkx as nx
 import pandas as pd
 
-def kg_to_df_pandas(kg: nx.DiGraph) -> Tuple[pd.DataFrame, pd.DataFrame]:
+
+def kg_to_df_pandas(kg: nx.DiGraph) -> tuple[pd.DataFrame, pd.DataFrame]:
     """
     Convert a directed knowledge graph to a pandas DataFrame.
 
@@ -19,20 +19,17 @@ def kg_to_df_pandas(kg: nx.DiGraph) -> Tuple[pd.DataFrame, pd.DataFrame]:
     """
 
     # Create a pandas DataFrame of the nodes
-    df_nodes = pd.DataFrame.from_dict(kg.nodes, orient='index')
+    df_nodes = pd.DataFrame.from_dict(kg.nodes, orient="index")
 
     # Create a pandas DataFrame of the edges
-    df_edges = nx.to_pandas_edgelist(kg,
-                                    source='node_source',
-                                    target='node_target')
+    df_edges = nx.to_pandas_edgelist(kg, source="node_source", target="node_target")
 
     return df_nodes, df_edges
 
-def df_pandas_to_kg(df: pd.DataFrame,
-                    df_nodes_attrs: pd.DataFrame,
-                    node_source: str,
-                    node_target: str
-                    ) -> nx.DiGraph:
+
+def df_pandas_to_kg(
+    df: pd.DataFrame, df_nodes_attrs: pd.DataFrame, node_source: str, node_target: str
+) -> nx.DiGraph:
     """
     Convert a pandas DataFrame to a directed knowledge graph.
 
@@ -47,22 +44,24 @@ def df_pandas_to_kg(df: pd.DataFrame,
     """
 
     # Assert if the columns node_source and node_target are in the df
-    assert node_source in df.columns, f'{node_source} not in df'
-    assert node_target in df.columns, f'{node_target} not in df'
+    assert node_source in df.columns, f"{node_source} not in df"
+    assert node_target in df.columns, f"{node_target} not in df"
 
     # Assert that the nodes in the index of the df_nodes_attrs
     # are present in the source and target columns of the df
-    assert set(df_nodes_attrs.index).issubset(set(df[node_source]).\
-                                        union(set(df[node_target]))), \
-                                        'Nodes in index of df_nodes not found in df_edges'
+    assert set(df_nodes_attrs.index).issubset(set(df[node_source]).union(set(df[node_target]))), (
+        "Nodes in index of df_nodes not found in df_edges"
+    )
 
     # Create a knowledge graph from the dataframes
     # Add edges and nodes to the knowledge graph
-    kg = nx.from_pandas_edgelist(df,
-                                source=node_source,
-                                target=node_target,
-                                create_using=nx.DiGraph,
-                                edge_attr=True)
-    kg.add_nodes_from(df_nodes_attrs.to_dict('index').items())
+    kg = nx.from_pandas_edgelist(
+        df,
+        source=node_source,
+        target=node_target,
+        create_using=nx.DiGraph,
+        edge_attr=True,
+    )
+    kg.add_nodes_from(df_nodes_attrs.to_dict("index").items())
 
     return kg

aiagents4pharma/talk2knowledgegraphs/utils/pubchem_utils.py

@@ -5,13 +5,15 @@ Enrichment class for enriching PubChem IDs with their STRINGS representation.
 """
 
 import logging
-import requests
+
 import hydra
+import requests
 
 # Initialize logger
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
+
 def cas_rn2pubchem_cid(casrn):
     """
     Convert CAS RN to PubChem CID.
@@ -24,8 +26,7 @@ def cas_rn2pubchem_cid(casrn):
     """
     # Load Hydra configuration for PubChem ID conversion
     with hydra.initialize(version_base=None, config_path="../configs"):
-        cfg = hydra.compose(config_name='config',
-                            overrides=['utils/pubchem_utils=default'])
+        cfg = hydra.compose(config_name="config", overrides=["utils/pubchem_utils=default"])
         cfg = cfg.utils.pubchem_utils
     # Prepare the URL
     pubchem_url_for_drug = f"{cfg.pubchem_casrn2cid_url}{casrn}/record/JSON"
@@ -43,6 +44,7 @@ def cas_rn2pubchem_cid(casrn):
             break
     return cid
 
+
 def external_id2pubchem_cid(db, db_id):
     """
     Convert external DB ID to PubChem CID.
@@ -59,8 +61,7 @@ def external_id2pubchem_cid(db, db_id):
     """
     # Load Hydra configuration for PubChem ID conversion
     with hydra.initialize(version_base=None, config_path="../configs"):
-        cfg = hydra.compose(config_name='config',
-                            overrides=['utils/pubchem_utils=default'])
+        cfg = hydra.compose(config_name="config", overrides=["utils/pubchem_utils=default"])
         cfg = cfg.utils.pubchem_utils
     # Prepare the URL
     pubchem_url_for_drug = f"{cfg.pubchem_cid_base_url}/{db}/{db_id}/JSON"
@@ -76,6 +77,7 @@ def external_id2pubchem_cid(db, db_id):
                 break
     return cid
 
+
 def pubchem_cid_description(cid):
     """
     Get the description of a PubChem CID.
@@ -88,8 +90,7 @@ def pubchem_cid_description(cid):
     """
     # Load Hydra configuration for PubChem CID description
     with hydra.initialize(version_base=None, config_path="../configs"):
-        cfg = hydra.compose(config_name='config',
-                            overrides=['utils/pubchem_utils=default'])
+        cfg = hydra.compose(config_name="config", overrides=["utils/pubchem_utils=default"])
         cfg = cfg.utils.pubchem_utils
     # Prepare the URL
     pubchem_url_for_descpription = f"{cfg.pubchem_cid_description_url}/{cid}/description/JSON"
@@ -97,7 +98,7 @@ def pubchem_cid_description(cid):
     response = requests.get(pubchem_url_for_descpription, timeout=60)
     data = response.json()
     # Extract the PubChem CID description
-    description = ''
-    for information in data["InformationList"]['Information']:
-        description += information.get("Description", '')
+    description = ""
+    for information in data["InformationList"]["Information"]:
+        description += information.get("Description", "")
     return description

aiagents4pharma/talk2scholars/.dockerignore

@@ -0,0 +1,13 @@
+_pycache_/
+*.pyc
+*.log
+*.csv
+*.pt
+*.pkl
+models/
+data/
+env/
+.venv/
+.git/
+.env
+.cufile.log

aiagents4pharma/talk2scholars/Dockerfile

@@ -0,0 +1,104 @@
+# syntax=docker/dockerfile:1
+
+# Dockerfile for the talk2scholars application
+# Multi-stage build for optimized image size with UV package manager
+
+ARG BASE_IMAGE=ubuntu:24.04
+ARG PYTHON_VERSION=3.12
+
+FROM ${BASE_IMAGE} AS dev-base
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+  build-essential \
+  ca-certificates \
+  cmake \
+  curl \
+  g++ \
+  libopenblas-dev \
+  libomp-dev \
+  ninja-build \
+  wget \
+  && rm -rf /var/lib/apt/lists/*
+
+FROM dev-base AS python-install
+ARG PYTHON_VERSION=3.12
+
+# Install Python (available in Ubuntu 24.04 default repos)
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+  python${PYTHON_VERSION} \
+  python${PYTHON_VERSION}-dev \
+  python${PYTHON_VERSION}-venv \
+  python3-pip \
+  && rm -rf /var/lib/apt/lists/* \
+  && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1 \
+  && update-alternatives --install /usr/bin/python python /usr/bin/python${PYTHON_VERSION} 1
+
+FROM python-install AS uv-install
+WORKDIR /app
+
+# Install UV package manager and dependencies
+COPY pyproject.toml uv.lock* ./
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh && \
+  export PATH="/root/.local/bin:$PATH" && \
+  export UV_PROJECT_ENVIRONMENT="/opt/venv" && \
+  uv sync --frozen --extra dev --no-install-project --python python${PYTHON_VERSION} && \
+  . /opt/venv/bin/activate && \
+  # RAPIDS packages (commented out - will be added in future if needed)
+  # uv pip install \
+  # --extra-index-url=https://pypi.nvidia.com \
+  # --index-strategy unsafe-best-match \
+  # cudf-cu12 dask-cudf-cu12 && \
+  uv cache clean
+
+FROM ${BASE_IMAGE} AS runtime
+ARG PYTHON_VERSION=3.12
+LABEL maintainer="talk2scholars"
+LABEL version="1.0.0"
+LABEL description="AI Agents for Pharma - Scholars Application"
+
+# Install runtime dependencies
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+  ca-certificates \
+  curl \
+  libmagic1 \
+  libopenblas0 \
+  libomp5 \
+  python${PYTHON_VERSION} \
+  && rm -rf /var/lib/apt/lists/* \
+  && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1 \
+  && update-alternatives --install /usr/bin/python python /usr/bin/python${PYTHON_VERSION} 1
+
+# Copy UV virtual environment from build stage
+COPY --from=uv-install /opt/venv /opt/venv
+
+# Set environment variables
+ENV PATH="/opt/venv/bin:$PATH"
+ENV PYTHONPATH="/app"
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV STREAMLIT_SERVER_HEADLESS=true
+ENV STREAMLIT_SERVER_ENABLE_CORS=false
+
+# Set working directory and create necessary directories
+WORKDIR /app
+
+# Copy application code
+COPY aiagents4pharma/talk2scholars /app/aiagents4pharma/talk2scholars
+COPY docs /app/docs
+COPY app /app/app
+
+# Copy and set up the entrypoint script (commented out - will be added in future if needed)
+# COPY aiagents4pharma/talk2knowledgegraphs/entrypoint.sh /usr/local/bin/entrypoint.sh
+# RUN chmod +x /usr/local/bin/entrypoint.sh
+
+# Health check for production monitoring
+HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
+  CMD curl -f http://localhost:8501/health || exit 1
+
+# Expose the default Streamlit port
+EXPOSE 8501
+
+# Set the entrypoint (commented out - will be added in future if needed)
+# ENTRYPOINT ["/usr/local/bin/entrypoint.sh"]
+
+# Default command (can be overridden)
+CMD ["streamlit", "run", "/app/app/frontend/streamlit_app_talk2scholars.py", "--server.port=8501", "--server.address=0.0.0.0"]

aiagents4pharma/talk2scholars/README.md

@@ -0,0 +1 @@
+Please check out the README file in the root folder for more information.

aiagents4pharma/talk2scholars/agents/__init__.py

@@ -2,11 +2,7 @@
 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
+from . import main_agent, paper_download_agent, pdf_agent, s2_agent, zotero_agent
 
 __all__ = [
     "main_agent",

aiagents4pharma/talk2scholars/agents/main_agent.py

@@ -12,15 +12,17 @@ Functions:
 """
 
 import logging
+
 import hydra
-from langgraph_supervisor import create_supervisor
-from langchain_openai import ChatOpenAI
 from langchain_core.language_models.chat_models import BaseChatModel
+from langchain_openai import ChatOpenAI
 from langgraph.checkpoint.memory import MemorySaver
+from langgraph_supervisor import create_supervisor
+
+from ..agents.paper_download_agent import get_app as get_app_paper_download
+from ..agents.pdf_agent import get_app as get_app_pdf
 from ..agents.s2_agent import get_app as get_app_s2
 from ..agents.zotero_agent import get_app as get_app_zotero
-from ..agents.pdf_agent import get_app as get_app_pdf
-from ..agents.paper_download_agent import get_app as get_app_paper_download
 from ..state.state_talk2scholars import Talk2Scholars
 
 # Initialize logger

aiagents4pharma/talk2scholars/agents/paper_download_agent.py

@@ -5,17 +5,18 @@ paper details and PDFs. It is part of the Talk2Scholars project.
 """
 
 import logging
-from typing import Any, Dict
+from typing import Any
+
 import hydra
 from langchain_core.language_models.chat_models import BaseChatModel
+from langgraph.checkpoint.memory import MemorySaver
 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.paper_downloader import download_papers
 
-
 # Initialize logger
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
@@ -67,7 +68,7 @@ def get_app(uniq_id, llm_model: BaseChatModel):
         checkpointer=MemorySaver(),
     )
 
-    def paper_download_agent_node(state: Talk2Scholars) -> Dict[str, Any]:
+    def paper_download_agent_node(state: Talk2Scholars) -> dict[str, Any]:
         """
         Processes the current state to fetch the research paper from arXiv, BioRxiv, or MedRxiv.
         """

aiagents4pharma/talk2scholars/agents/pdf_agent.py

@@ -12,11 +12,13 @@ Usage:
 """
 
 import logging
+
 import hydra
 from langchain_core.language_models.chat_models import BaseChatModel
-from langgraph.graph import START, StateGraph
-from langgraph.prebuilt import create_react_agent, ToolNode
 from langgraph.checkpoint.memory import MemorySaver
+from langgraph.graph import START, StateGraph
+from langgraph.prebuilt import ToolNode, create_react_agent
+
 from ..state.state_talk2scholars import Talk2Scholars
 from ..tools.pdf.question_and_answer import question_and_answer
 

aiagents4pharma/talk2scholars/agents/s2_agent.py

@@ -5,7 +5,7 @@ Agent for interacting with Semantic Scholar
 """
 
 import logging
-from typing import Any, Dict
+from typing import Any
 
 import hydra
 from langchain_core.language_models.chat_models import BaseChatModel
@@ -54,7 +54,7 @@ def get_app(uniq_id, llm_model: BaseChatModel):
         >>> result = app.invoke(initial_state)
     """
 
-    def s2_agent_node(state: Talk2Scholars) -> Dict[str, Any]:
+    def s2_agent_node(state: Talk2Scholars) -> dict[str, Any]:
         """
         Processes the user query and retrieves relevant research papers.
 

aiagents4pharma/talk2scholars/agents/zotero_agent.py

@@ -5,22 +5,23 @@ Agent for interacting with Zotero with human-in-the-loop features
 """
 
 import logging
-from typing import Any, Dict
-import hydra
+from typing import Any
 
+import hydra
 from langchain_core.language_models.chat_models import BaseChatModel
-from langgraph.graph import START, StateGraph
-from langgraph.prebuilt import create_react_agent, ToolNode
 from langgraph.checkpoint.memory import MemorySaver
+from langgraph.graph import START, StateGraph
+from langgraph.prebuilt import ToolNode, create_react_agent
+
 from ..state.state_talk2scholars import Talk2Scholars
-from ..tools.zotero.zotero_read import zotero_read
-from ..tools.zotero.zotero_review import zotero_review
-from ..tools.zotero.zotero_write import zotero_write
 from ..tools.s2.display_dataframe import display_dataframe
 from ..tools.s2.query_dataframe import query_dataframe
 from ..tools.s2.retrieve_semantic_scholar_paper_id import (
     retrieve_semantic_scholar_paper_id,
 )
+from ..tools.zotero.zotero_read import zotero_read
+from ..tools.zotero.zotero_review import zotero_review
+from ..tools.zotero.zotero_write import zotero_write
 
 # Initialize logger
 logging.basicConfig(level=logging.INFO)
@@ -49,7 +50,7 @@ def get_app(uniq_id, llm_model: BaseChatModel):
         >>> result = app.invoke(initial_state)
     """
 
-    def zotero_agent_node(state: Talk2Scholars) -> Dict[str, Any]:
+    def zotero_agent_node(state: Talk2Scholars) -> dict[str, Any]:
         """
         Processes the user query and retrieves relevant research papers from Zotero.
 
@@ -68,9 +69,7 @@ def get_app(uniq_id, llm_model: BaseChatModel):
             >>> result = zotero_agent_node(current_state)
             >>> papers = result.get("papers", [])
         """
-        logger.log(
-            logging.INFO, "Creating Agent_Zotero node with thread_id %s", uniq_id
-        )
+        logger.log(logging.INFO, "Creating Agent_Zotero node with thread_id %s", uniq_id)
         result = model.invoke(state, {"configurable": {"thread_id": uniq_id}})
 
         return result

aiagents4pharma/talk2scholars/configs/__init__.py

@@ -2,8 +2,6 @@
 This package contains configuration settings and prompts used by various AI agents
 """
 
-from . import agents
-from . import tools
-from . import app
+from . import agents, app, tools
 
 __all__ = ["agents", "tools", "app"]

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

@@ -2,9 +2,6 @@
 Import all the modules in the package
 """
 
-from . import s2_agent
-from . import main_agent
-from . import pdf_agent
-from . import zotero_agent
+from . import main_agent, pdf_agent, s2_agent, zotero_agent
 
 __all__ = ["s2_agent", "main_agent", "pdf_agent", "zotero_agent"]

aiagents4pharma/talk2scholars/configs/agents/talk2scholars/main_agent/default.yaml

@@ -26,7 +26,7 @@ system_prompt: |
 
   **IMPORTANT – Q&A Disambiguation (Pause Before Acting):**
   - When the user asks a question like “Tell me more about X”, “What does the first article say?”, or similar:
-    1) **Pause and ask**:  
+    1) **Pause and ask**:
        “Do you want me to answer using the **PDF content** (full text), or using the **last displayed table** (metadata only)?”
        - Accept synonyms: *PDF, full text, paper text* → **PDF content**.
        - Accept synonyms: *last displayed table, table above, results table, search results* → **metadata/table**.

aiagents4pharma/talk2scholars/configs/agents/talk2scholars/pdf_agent/default.yaml

@@ -2,7 +2,7 @@ _target_: agents.pdf_agent.get_app
 pdf_agent: |
   You are the **PDF Agent**.
 
-  **Primary Role:**  
+  **Primary Role:**
   Perform question-and-answer tasks on the **full text** of papers, articles, or PDFs that are already available
   (downloaded locally, uploaded by the user, or stored in the user's Zotero library).
 

aiagents4pharma/talk2scholars/configs/agents/talk2scholars/s2_agent/default.yaml

@@ -2,12 +2,12 @@ _target_: agents.s2_agent.get_app
 s2_agent: |
   You are the **S2 Agent**.
 
-  **Primary Role:**  
-  - Search for academic papers.  
-  - Provide recommendations **only when explicitly requested** by the user.  
+  **Primary Role:**
+  - Search for academic papers.
+  - Provide recommendations **only when explicitly requested** by the user.
   - Display results using the `display_dataframe` tool.
 
-  **Additional Capability – Metadata Queries:**  
+  **Additional Capability – Metadata Queries:**
   - You can query the last displayed results table using the `query_dataframe` tool to filter, sort, or extract metadata (including paper IDs).
   - Use this tool only for **metadata-level** questions (not full PDF content).
 
@@ -22,10 +22,10 @@ s2_agent: |
        END
        ---
     3) Do **not** call any other S2 tools (e.g., `retrieve_semantic_scholar_paper_id`, `get_single_paper_recommendations`, `get_multi_paper_recommendations`) in this mode.
-    4) If no last displayed table exists, reply:  
-       `IDS: NONE`  
-       `SOURCE: none (no results table available)`  
-       `END`  
+    4) If no last displayed table exists, reply:
+       `IDS: NONE`
+       `SOURCE: none (no results table available)`
+       `END`
        and stop.
 
   **Tool-Selection Policy (default mode):**

aiagents4pharma/talk2scholars/configs/agents/talk2scholars/zotero_agent/default.yaml

@@ -2,18 +2,18 @@ _target_: agents.zotero_agent.get_app
 zotero_agent: |
   You are the **Zotero Agent**.
 
-  **Primary Role:**  
-  - Read from the user's Zotero library (list items, retrieve metadata, check existing entries).  
-  - Write to the user's Zotero library (save new papers, update existing records) — only with explicit user approval.  
+  **Primary Role:**
+  - Read from the user's Zotero library (list items, retrieve metadata, check existing entries).
+  - Write to the user's Zotero library (save new papers, update existing records) — only with explicit user approval.
   - Display Zotero query results using "display_dataframe" tool.
 
-  **Rules & Boundaries:**  
+  **Rules & Boundaries:**
   - Never save papers to Zotero without **explicit human approval**. If approval is denied, do not retry unless the user changes their decision.
   - Do not search for papers on the web — that is the `s2_agent`’s role.
   - Do not perform PDF content analysis — that is the `pdf_agent`’s role.
   - Do not download PDFs directly — that is the `paper_download_agent`’s role.
 
-  **Examples:**  
-  - “Show me all papers I saved last month.”  
-  - “Check if I already have this paper in Zotero.”  
+  **Examples:**
+  - “Show me all papers I saved last month.”
+  - “Check if I already have this paper in Zotero.”
   - “Save this paper to Zotero” → Ask for explicit approval before saving.

aiagents4pharma/talk2scholars/configs/tools/__init__.py

@@ -2,12 +2,14 @@
 Import all the modules in the package
 """
 
-from . import search
-from . import single_paper_recommendation
-from . import multi_paper_recommendation
-from . import question_and_answer
-from . import zotero_read
-from . import zotero_write
+from . import (
+    multi_paper_recommendation,
+    question_and_answer,
+    search,
+    single_paper_recommendation,
+    zotero_read,
+    zotero_write,
+)
 
 __all__ = [
     "search",

aiagents4pharma/talk2scholars/docker-compose/cpu/.env.example

@@ -0,0 +1,21 @@
+# .env.example (DO NOT put actual API keys here, read the README.md)
+
+# OPENAI API KEY
+OPENAI_API_KEY=your_openai_api_key_here
+
+# LangSmith API KEY
+LANGCHAIN_TRACING_V2=true
+LANGCHAIN_API_KEY=your_langchain_api_key_heres
+
+# NVIDIA API KEY
+NVIDIA_API_KEY=your_nvidia_api_key_here
+
+# ZOTERO API KEY
+ZOTERO_API_KEY=your_zotero_api_key_here
+ZOTERO_USER_ID=your_zotero_user_id_here
+
+# Set environment variables for data loader
+MILVUS_HOST=milvus-standalone
+MILVUS_PORT=19530
+MILVUS_DB_NAME=pdf_rag_db
+MILVUS_COLLECTION_NAME=pdf_rag_documents