aiagents4pharma 1.39.0__tar.gz → 1.39.2__tar.gz

{aiagents4pharma-1.39.0 → aiagents4pharma-1.39.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aiagents4pharma
-Version: 1.39.0
+Version: 1.39.2
 Summary: AI Agents for drug discovery, drug development, and other pharmaceutical R&D.
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
@@ -96,10 +96,10 @@ Our toolkit currently consists of the following agents:
 - T2B and T2KG accepted at the MLGenX workshop during ICLR #2025 in Singapore. [Read More](https://openreview.net/forum?id=av4QhBNeZo)
 
 <div align="center">
-  <strong>Watch the presentation:</strong><br><br>
-  <a href="https://www.youtube.com/watch?v=3cU_OxY4HiE">
-    <img src="https://img.youtube.com/vi/3cU_OxY4HiE/0.jpg" alt="Watch the presentation" width="480">
-  </a>
+<strong>Watch the presentation:</strong><br><br>
+<a href="https://www.youtube.com/watch?v=3cU_OxY4HiE">
+<img src="https://img.youtube.com/vi/3cU_OxY4HiE/0.jpg" alt="Watch the presentation" width="480">
+</a>
 </div>
 
 ## Getting Started
@@ -145,117 +145,62 @@ LANGCHAIN_TRACING_V2=true           # Optional for both agents
 LANGCHAIN_API_KEY=...               # Optional for both agents
 ```
 
-To use **Talk2AIAgents4Pharma** or **Talk2KnowledgeGraphs**, you need a free **NVIDIA API key**. Create an account and apply for free credits [here](https://build.nvidia.com/explore/discover).
-
-###### Notes for Windows Users
-
-If you are using Windows, it is recommended to install **Git Bash** for a smoother experience when running the bash commands in this guide.
-
-- For applications that use **Docker Compose**, Git Bash is **required**.
-- For applications that use **docker run** manually, Git Bash is **optional**, but recommended for consistency.
-
-You can download Git Bash here: [Git for Windows](https://git-scm.com/downloads).
-
-When using Docker on Windows, make sure you **run Docker with administrative privileges** if you face permission issues.
-
-To resolve for permission issues, you can:
-
-- Review the official Docker documentation on [Windows permission requirements](https://docs.docker.com/desktop/setup/install/windows-permission-requirements/).
-- Alternatively, follow the community discussion and solutions on [Docker Community Forums](https://forums.docker.com/t/error-when-trying-to-run-windows-containers-docker-client-must-be-run-with-elevated-privileges/136619).
-
-**LangSmith** support is optional. To enable it, create an API key [here](https://docs.smith.langchain.com/administration/how_to_guides/organization_management/create_account_api_key).
+[Additional Notes for Windows Users](https://github.com/VirtualPatientEngine/AIAgents4Pharma/blob/main/aiagents4pharma/talk2aiagents4pharma/install.md#notes-for-windows-users)
 
 ##### **3. Start the application**
 
-Run the startup script. It will:
-
-- Detect your hardware configuration (NVIDIA GPU, AMD GPU, or CPU). Apple Metal is unavailable inside Docker, and Intel SIMD optimizations are automatically handled without special configuration.
-- Choose the correct Ollama image (`latest` or `rocm`)
-- Launch the Ollama container with appropriate runtime settings
-- Pull the required embedding model (`nomic-embed-text`)
-- Start the agent **after the model is available**
-
 ```sh
 chmod +x startup.sh
 ./startup.sh        # Add --cpu flag to force CPU mode if needed
 ```
 
-##### **4. Access the Web UI**
-
-Once started, the agent is available at:
-
-```
-http://localhost:8501
-```
+[More about startup script](https://github.com/VirtualPatientEngine/AIAgents4Pharma/blob/main/aiagents4pharma/talk2aiagents4pharma/install.md#about-startupsh)
 
 ##### **To Run Talk2Biomodels / Talk2Scholars**
 
-1. **Run the containers**
-
 ###### Talk2Biomodels
 
 ```docker
 docker run -d \
-  --name talk2biomodels \
-  -e OPENAI_API_KEY=<your_openai_api_key> \
-  -e NVIDIA_API_KEY=<your_nvidia_api_key> \
-  -p 8501:8501 \
-  virtualpatientengine/talk2biomodels
+--name talk2biomodels \
+-e OPENAI_API_KEY=<your_openai_api_key> \
+-e NVIDIA_API_KEY=<your_nvidia_api_key> \
+-p 8501:8501 \
+virtualpatientengine/talk2biomodels
 ```
 
 ###### Talk2Scholars
 
 ```docker
 docker run -d \
-  --name talk2scholars \
-  -e OPENAI_API_KEY=<your_openai_api_key> \
-  -e ZOTERO_API_KEY=<your_zotero_api_key> \
-  -e ZOTERO_USER_ID=<your_zotero_user_id> \
-  -e NVIDIA_API_KEY=<your_nvidia_api_key> \
-  -p 8501:8501 \
-  virtualpatientengine/talk2scholars
+--name talk2scholars \
+-e OPENAI_API_KEY=<your_openai_api_key> \
+-e ZOTERO_API_KEY=<your_zotero_api_key> \
+-e ZOTERO_USER_ID=<your_zotero_user_id> \
+-e NVIDIA_API_KEY=<your_nvidia_api_key> \
+-p 8501:8501 \
+virtualpatientengine/talk2scholars
 ```
 
-2. **Access the Web App**
-   Open your browser and go to:
+##### **4. Access the Web UI**
+
+Once started, the agent is available at:
+
+```
+http://localhost:8501
+```
 
-   ```
-   http://localhost:8501
-   ```
+To use **Talk2AIAgents4Pharma** or **Talk2KnowledgeGraphs**, you need a free **NVIDIA API key**. Create an account and apply for free credits [here](https://build.nvidia.com/explore/discover).
 
 To use **Talk2BioModels** or **Talk2Scholars**, you need a free **NVIDIA API key**. Create an account and apply for free credits [here](https://build.nvidia.com/explore/discover).
 
 Only for **Talk2Scholars**, you also need a **Zotero API key**, which you can generate [here](https://www.zotero.org/user/login#applications). _(For all other agents, the Zotero key is not required.)_
 
-If you are using docker on Windows, please follow these [Windows Setup Notes](#notes-for-windows-users).
+If you are using docker on Windows, please follow these [Windows Setup Notes](https://github.com/VirtualPatientEngine/AIAgents4Pharma/blob/main/aiagents4pharma/talk2aiagents4pharma/install.md#notes-for-windows-users).
 
 **LangSmith** support is optional. To enable it, create an API key [here](https://docs.smith.langchain.com/administration/how_to_guides/organization_management/create_account_api_key).
 
-#### Notes
-
-- Be sure to **replace the placeholder values** with your actual credentials before running any container:
-
-  - `<your_openai_api_key>`
-  - `<your_nvidia_api_key>`
-  - `<your_zotero_api_key>`
-  - `<your_zotero_user_id>`
-
-- All agents default to **port `8501`**. If you plan to run multiple agents simultaneously, make sure to assign **different ports** to avoid conflicts.
-
-  Example (Talk2Scholars on port `8502`):
-
-  ```docker
-  docker run -d \
-    --name talk2scholars \
-    -e OPENAI_API_KEY=<your_openai_api_key> \
-    -e ZOTERO_API_KEY=<your_zotero_api_key> \
-    -e ZOTERO_USER_ID=<your_zotero_user_id> \
-    -e NVIDIA_API_KEY=<your_nvidia_api_key> \
-    -p 8502:8501 \
-    virtualpatientengine/talk2scholars
-  ```
-
-  Then access the app at: [http://localhost:8502](http://localhost:8502)
+[More on running multiple agents simultaneously](https://github.com/VirtualPatientEngine/AIAgents4Pharma/blob/main/aiagents4pharma/talk2aiagents4pharma/install.md#to-run-multiple-agents-simultaneously)
 
 #### Option 2: git (for developers and contributors)
 
@@ -278,14 +223,14 @@ conda create --name AIAgents4Pharma python=3.12 -y && conda activate AIAgents4Ph
 
 3. **Initialize API Keys**
 
-   ```env
-   export OPENAI_API_KEY=....          # Required for all agents
-   export NVIDIA_API_KEY=....          # Required for all agents
-   export ZOTERO_API_KEY=....          # Required for T2S
-   export ZOTERO_USER_ID=....          # Required for T2S
-   export LANGCHAIN_TRACING_V2=true    # Optional for all agents
-   export LANGCHAIN_API_KEY=...        # Optional for all agents
-   ```
+```env
+export OPENAI_API_KEY=....          # Required for all agents
+export NVIDIA_API_KEY=....          # Required for all agents
+export ZOTERO_API_KEY=....          # Required for T2S
+export ZOTERO_USER_ID=....          # Required for T2S
+export LANGCHAIN_TRACING_V2=true    # Optional for all agents
+export LANGCHAIN_API_KEY=...        # Optional for all agents
+```
 
 To use **Talk2AIAgents4Pharma**, **Talk2BioModels**, **Talk2KnowledgeGraphs**, or **Talk2Scholars**, you need a free **NVIDIA API key**. Create an account and apply for free credits [here](https://build.nvidia.com/explore/discover).
 
@@ -315,10 +260,12 @@ If you skip the previous step, it will default to the name `default`.
 `xxxx` will be the 4-digit ID created for the session._
 
 4. **Launch the app:**
-   ```sh
-   streamlit run app/frontend/streamlit_app_<agent>.py
-   ```
-   _Replace `<agent>` with the agent name you are interested to launch:_
+
+```sh
+streamlit run app/frontend/streamlit_app_<agent>.py
+```
+
+_Replace `<agent>` with the agent name you are interested to launch:_
 
 - `talk2aiagents4pharma`
 - `talk2biomodels`
@@ -348,17 +295,23 @@ All types of contributions are appreciated — whether you're fixing bugs, addin
 1. Star this repository to show your support.
 2. Fork the repository.
 3. Create a new branch for your work:
-   ```sh
-   git checkout -b feat/your-feature-name
-   ```
+
+```sh
+git checkout -b feat/your-feature-name
+```
+
 4. Make your changes and commit them:
-   ```sh
-   git commit -m "feat: add a brief description of your change"
-   ```
+
+```sh
+git commit -m "feat: add a brief description of your change"
+```
+
 5. Push your branch:
-   ```sh
-   git push origin feat/your-feature-name
-   ```
+
+```sh
+git push origin feat/your-feature-name
+```
+
 6. Open a Pull Request.
 
 #### Areas where you can help

{aiagents4pharma-1.39.0 → aiagents4pharma-1.39.2}/README.md

@@ -29,10 +29,10 @@ Our toolkit currently consists of the following agents:
 - T2B and T2KG accepted at the MLGenX workshop during ICLR #2025 in Singapore. [Read More](https://openreview.net/forum?id=av4QhBNeZo)
 
 <div align="center">
-  <strong>Watch the presentation:</strong><br><br>
-  <a href="https://www.youtube.com/watch?v=3cU_OxY4HiE">
-    <img src="https://img.youtube.com/vi/3cU_OxY4HiE/0.jpg" alt="Watch the presentation" width="480">
-  </a>
+<strong>Watch the presentation:</strong><br><br>
+<a href="https://www.youtube.com/watch?v=3cU_OxY4HiE">
+<img src="https://img.youtube.com/vi/3cU_OxY4HiE/0.jpg" alt="Watch the presentation" width="480">
+</a>
 </div>
 
 ## Getting Started
@@ -78,117 +78,62 @@ LANGCHAIN_TRACING_V2=true           # Optional for both agents
 LANGCHAIN_API_KEY=...               # Optional for both agents
 ```
 
-To use **Talk2AIAgents4Pharma** or **Talk2KnowledgeGraphs**, you need a free **NVIDIA API key**. Create an account and apply for free credits [here](https://build.nvidia.com/explore/discover).
-
-###### Notes for Windows Users
-
-If you are using Windows, it is recommended to install **Git Bash** for a smoother experience when running the bash commands in this guide.
-
-- For applications that use **Docker Compose**, Git Bash is **required**.
-- For applications that use **docker run** manually, Git Bash is **optional**, but recommended for consistency.
-
-You can download Git Bash here: [Git for Windows](https://git-scm.com/downloads).
-
-When using Docker on Windows, make sure you **run Docker with administrative privileges** if you face permission issues.
-
-To resolve for permission issues, you can:
-
-- Review the official Docker documentation on [Windows permission requirements](https://docs.docker.com/desktop/setup/install/windows-permission-requirements/).
-- Alternatively, follow the community discussion and solutions on [Docker Community Forums](https://forums.docker.com/t/error-when-trying-to-run-windows-containers-docker-client-must-be-run-with-elevated-privileges/136619).
-
-**LangSmith** support is optional. To enable it, create an API key [here](https://docs.smith.langchain.com/administration/how_to_guides/organization_management/create_account_api_key).
+[Additional Notes for Windows Users](https://github.com/VirtualPatientEngine/AIAgents4Pharma/blob/main/aiagents4pharma/talk2aiagents4pharma/install.md#notes-for-windows-users)
 
 ##### **3. Start the application**
 
-Run the startup script. It will:
-
-- Detect your hardware configuration (NVIDIA GPU, AMD GPU, or CPU). Apple Metal is unavailable inside Docker, and Intel SIMD optimizations are automatically handled without special configuration.
-- Choose the correct Ollama image (`latest` or `rocm`)
-- Launch the Ollama container with appropriate runtime settings
-- Pull the required embedding model (`nomic-embed-text`)
-- Start the agent **after the model is available**
-
 ```sh
 chmod +x startup.sh
 ./startup.sh        # Add --cpu flag to force CPU mode if needed
 ```
 
-##### **4. Access the Web UI**
-
-Once started, the agent is available at:
-
-```
-http://localhost:8501
-```
+[More about startup script](https://github.com/VirtualPatientEngine/AIAgents4Pharma/blob/main/aiagents4pharma/talk2aiagents4pharma/install.md#about-startupsh)
 
 ##### **To Run Talk2Biomodels / Talk2Scholars**
 
-1. **Run the containers**
-
 ###### Talk2Biomodels
 
 ```docker
 docker run -d \
-  --name talk2biomodels \
-  -e OPENAI_API_KEY=<your_openai_api_key> \
-  -e NVIDIA_API_KEY=<your_nvidia_api_key> \
-  -p 8501:8501 \
-  virtualpatientengine/talk2biomodels
+--name talk2biomodels \
+-e OPENAI_API_KEY=<your_openai_api_key> \
+-e NVIDIA_API_KEY=<your_nvidia_api_key> \
+-p 8501:8501 \
+virtualpatientengine/talk2biomodels
 ```
 
 ###### Talk2Scholars
 
 ```docker
 docker run -d \
-  --name talk2scholars \
-  -e OPENAI_API_KEY=<your_openai_api_key> \
-  -e ZOTERO_API_KEY=<your_zotero_api_key> \
-  -e ZOTERO_USER_ID=<your_zotero_user_id> \
-  -e NVIDIA_API_KEY=<your_nvidia_api_key> \
-  -p 8501:8501 \
-  virtualpatientengine/talk2scholars
+--name talk2scholars \
+-e OPENAI_API_KEY=<your_openai_api_key> \
+-e ZOTERO_API_KEY=<your_zotero_api_key> \
+-e ZOTERO_USER_ID=<your_zotero_user_id> \
+-e NVIDIA_API_KEY=<your_nvidia_api_key> \
+-p 8501:8501 \
+virtualpatientengine/talk2scholars
 ```
 
-2. **Access the Web App**
-   Open your browser and go to:
+##### **4. Access the Web UI**
+
+Once started, the agent is available at:
+
+```
+http://localhost:8501
+```
 
-   ```
-   http://localhost:8501
-   ```
+To use **Talk2AIAgents4Pharma** or **Talk2KnowledgeGraphs**, you need a free **NVIDIA API key**. Create an account and apply for free credits [here](https://build.nvidia.com/explore/discover).
 
 To use **Talk2BioModels** or **Talk2Scholars**, you need a free **NVIDIA API key**. Create an account and apply for free credits [here](https://build.nvidia.com/explore/discover).
 
 Only for **Talk2Scholars**, you also need a **Zotero API key**, which you can generate [here](https://www.zotero.org/user/login#applications). _(For all other agents, the Zotero key is not required.)_
 
-If you are using docker on Windows, please follow these [Windows Setup Notes](#notes-for-windows-users).
+If you are using docker on Windows, please follow these [Windows Setup Notes](https://github.com/VirtualPatientEngine/AIAgents4Pharma/blob/main/aiagents4pharma/talk2aiagents4pharma/install.md#notes-for-windows-users).
 
 **LangSmith** support is optional. To enable it, create an API key [here](https://docs.smith.langchain.com/administration/how_to_guides/organization_management/create_account_api_key).
 
-#### Notes
-
-- Be sure to **replace the placeholder values** with your actual credentials before running any container:
-
-  - `<your_openai_api_key>`
-  - `<your_nvidia_api_key>`
-  - `<your_zotero_api_key>`
-  - `<your_zotero_user_id>`
-
-- All agents default to **port `8501`**. If you plan to run multiple agents simultaneously, make sure to assign **different ports** to avoid conflicts.
-
-  Example (Talk2Scholars on port `8502`):
-
-  ```docker
-  docker run -d \
-    --name talk2scholars \
-    -e OPENAI_API_KEY=<your_openai_api_key> \
-    -e ZOTERO_API_KEY=<your_zotero_api_key> \
-    -e ZOTERO_USER_ID=<your_zotero_user_id> \
-    -e NVIDIA_API_KEY=<your_nvidia_api_key> \
-    -p 8502:8501 \
-    virtualpatientengine/talk2scholars
-  ```
-
-  Then access the app at: [http://localhost:8502](http://localhost:8502)
+[More on running multiple agents simultaneously](https://github.com/VirtualPatientEngine/AIAgents4Pharma/blob/main/aiagents4pharma/talk2aiagents4pharma/install.md#to-run-multiple-agents-simultaneously)
 
 #### Option 2: git (for developers and contributors)
 
@@ -211,14 +156,14 @@ conda create --name AIAgents4Pharma python=3.12 -y && conda activate AIAgents4Ph
 
 3. **Initialize API Keys**
 
-   ```env
-   export OPENAI_API_KEY=....          # Required for all agents
-   export NVIDIA_API_KEY=....          # Required for all agents
-   export ZOTERO_API_KEY=....          # Required for T2S
-   export ZOTERO_USER_ID=....          # Required for T2S
-   export LANGCHAIN_TRACING_V2=true    # Optional for all agents
-   export LANGCHAIN_API_KEY=...        # Optional for all agents
-   ```
+```env
+export OPENAI_API_KEY=....          # Required for all agents
+export NVIDIA_API_KEY=....          # Required for all agents
+export ZOTERO_API_KEY=....          # Required for T2S
+export ZOTERO_USER_ID=....          # Required for T2S
+export LANGCHAIN_TRACING_V2=true    # Optional for all agents
+export LANGCHAIN_API_KEY=...        # Optional for all agents
+```
 
 To use **Talk2AIAgents4Pharma**, **Talk2BioModels**, **Talk2KnowledgeGraphs**, or **Talk2Scholars**, you need a free **NVIDIA API key**. Create an account and apply for free credits [here](https://build.nvidia.com/explore/discover).
 
@@ -248,10 +193,12 @@ If you skip the previous step, it will default to the name `default`.
 `xxxx` will be the 4-digit ID created for the session._
 
 4. **Launch the app:**
-   ```sh
-   streamlit run app/frontend/streamlit_app_<agent>.py
-   ```
-   _Replace `<agent>` with the agent name you are interested to launch:_
+
+```sh
+streamlit run app/frontend/streamlit_app_<agent>.py
+```
+
+_Replace `<agent>` with the agent name you are interested to launch:_
 
 - `talk2aiagents4pharma`
 - `talk2biomodels`
@@ -281,17 +228,23 @@ All types of contributions are appreciated — whether you're fixing bugs, addin
 1. Star this repository to show your support.
 2. Fork the repository.
 3. Create a new branch for your work:
-   ```sh
-   git checkout -b feat/your-feature-name
-   ```
+
+```sh
+git checkout -b feat/your-feature-name
+```
+
 4. Make your changes and commit them:
-   ```sh
-   git commit -m "feat: add a brief description of your change"
-   ```
+
+```sh
+git commit -m "feat: add a brief description of your change"
+```
+
 5. Push your branch:
-   ```sh
-   git push origin feat/your-feature-name
-   ```
+
+```sh
+git push origin feat/your-feature-name
+```
+
 6. Open a Pull Request.
 
 #### Areas where you can help

{aiagents4pharma-1.39.0 → aiagents4pharma-1.39.2}/aiagents4pharma/talk2scholars/agents/main_agent.py

@@ -48,13 +48,13 @@ def get_app(uniq_id, llm_model: BaseChatModel):
         >>> app = get_app("thread_123")
         >>> result = app.invoke(initial_state)
     """
-    if hasattr(llm_model, "model_name"):
-        if llm_model.model_name == "gpt-4o-mini":
-            llm_model = ChatOpenAI(
-                model="gpt-4o-mini",
-                temperature=0,
-                model_kwargs={"parallel_tool_calls": False},
-            )
+    # Replace placeholder mini model with a configured ChatOpenAI instance
+    if getattr(llm_model, "model_name", None) == "gpt-4o-mini":
+        llm_model = ChatOpenAI(
+            model="gpt-4o-mini",
+            temperature=0,
+            model_kwargs={"parallel_tool_calls": False},
+        )
     # Load hydra configuration
     logger.log(logging.INFO, "Launching Talk2Scholars with thread_id %s", uniq_id)
     with hydra.initialize(version_base=None, config_path="../configs/"):

aiagents4pharma-1.39.2/aiagents4pharma/talk2scholars/configs/agents/talk2scholars/main_agent/default.yaml

@@ -0,0 +1,98 @@
+_target_: agents.main_agent.get_app
+temperature: 0
+system_prompt: |
+  You are the Main Supervisor Agent.
+
+  You have access to four tools, each represented by a sub-agent:
+
+  - s2_agent: Use this to search for or recommend academic papers.
+    You can also use its `query_dataframe` tool to extract metadata from the last displayed papers.
+    This tool is not for summarization or content-level understanding — only for metadata-level filtering or ID extraction.
+
+  - zotero_agent: Use this to read from or write to the user's Zotero account.
+    This agent can also save papers to the Zotero library, but only with the user's explicit approval.
+
+  - pdf_agent: Use this to perform question-and-answer tasks on downloaded, uploaded, or Zotero-based papers or PDFs.
+    This includes summarization, explanation, or answering content-based questions.
+
+  - paper_download_agent: Use to download PDFs.
+
+  --
+
+  Tool Usage Boundaries:
+
+  - Use `query_dataframe` only for metadata queries such as filtering by author, listing titles, or selecting paper IDs.
+    It is not capable of full-text summarization, content analysis, or reading PDF content.
+
+  - Use `pdf_agent` to summarize or analyze the full content of any downloaded, uploaded, or Zotero-based PDF.
+
+  - Never attempt to summarize or interpret paper content using `query_dataframe`. That is incorrect and will result in incomplete or misleading output.
+
+  - When the user asks for a summary, explanation, or any content-based question, you must use `pdf_agent`:
+
+  --
+
+  Critical Paper Download Protocol:
+
+  When the user requests to download paper(s), you must follow this strict 2-step protocol:
+
+  1. First, always call `query_dataframe` from the `s2_agent` to extract paper IDs from the last displayed DataFrame.
+
+     - This tool must be used only to extract paper IDs.
+     - Do not pass the full user query to this tool.
+     - This step is only for retrieving the full list of available `paper_ids` and their order.
+     - If the user request refers to specific positions (like “4th paper”), you must calculate the correct index first.
+
+  2. Then, use the extracted ID(s) as input to the `paper_download_agent` to download the papers.
+
+  Important format rules:
+
+  - The `query_dataframe` tool always returns paper IDs with full prefixes such as `"arxiv:..."`, `"doi:..."`, or `"pubmed:..."`.
+  - You must not modify, trim, or strip these prefixes.
+  - Always pass the **exact** IDs returned from `query_dataframe` directly to the `paper_download_agent` without alteration.
+
+  Do not skip step 1 under any circumstances. Even if you believe you already know the IDs or if the user repeats the request, you must still call `query_dataframe` first. Skipping this step is a critical error and will corrupt the workflow.
+
+  Example reasoning:
+    - User: "Download and summarize the fourth paper"
+    - Step 1: Compute that the user wants the 4th paper
+    - Step 2: Call `s2_agent.query_dataframe`
+    - Step 3: Pass that ID to `paper_download_agent`
+    - Step 4: After download, use `pdf_agent` for summarization only when requested by the user
+
+  Additional example:
+    - User: "Download the first and third papers"
+    - Step 1: Compute that the user wants paper indices 1 and 3
+    - Step 2: Call `s2_agent.query_dataframe`
+    - Step 3: Pass both IDs to `paper_download_agent`
+
+  Full list example:
+    - User: "Download all papers", "Download the 6th paper",
+    - Step 1: Call `s2_agent.query_dataframe`
+    - Step 2: Pass the full list of IDs to `paper_download_agent`
+
+  Always follow this sequence. It applies to every download request.
+
+  --
+
+  Interpreting User Requests Involving Paper Indices:
+
+  When a user refers to papers using words like "first", "second", "third", or "fourth", you must interpret them as referring to numeric positions in the last displayed DataFrame.
+
+  For example:
+    - "Download the fourth paper" → treat as "Download the 4th paper"
+    - "Download the first and third papers" → treat as "Download the 1st and 3rd papers"
+
+  These word-based positions must be normalized before calling `query_dataframe`. Always compute the correct index and pass it as `row_number`.
+
+  --
+
+  General Coordination Instructions:
+
+  Each sub-agent is specialized for a different task.
+
+  You may call multiple agents, either in parallel or in sequence. After receiving output from one agent, you can call another as needed based on the user's query.
+
+  Your role is to analyze the user’s request carefully, decide which sub-agent(s) to use, and coordinate their execution efficiently.
+
+  Always prioritize delegation and think step-by-step before acting. Avoid answering by yourself unless explicitly necessary.

aiagents4pharma-1.39.2/aiagents4pharma/talk2scholars/configs/agents/talk2scholars/paper_download_agent/default.yaml

@@ -0,0 +1,5 @@
+_target_: agents.paper_download_agent.get_app
+paper_download_agent: |
+  You are the Paper Download Agent.
+
+  You are responsible for downloading PDFs of papers using their IDs. Use all the provied Ids to download the papers. Only when the user asks a question related to PDFs, please forward the query to the `question_and_answer` tool from the `pdf_agent`

aiagents4pharma-1.39.2/aiagents4pharma/talk2scholars/configs/agents/talk2scholars/pdf_agent/default.yaml

@@ -0,0 +1,5 @@
+_target_: agents.pdf_agent.get_app
+pdf_agent: |
+  You are the PDF Agent.
+
+  You are responsible for performing question-and-answer tasks on papers, articles, or PDFs

aiagents4pharma-1.39.2/aiagents4pharma/talk2scholars/configs/agents/talk2scholars/s2_agent/default.yaml

@@ -0,0 +1,5 @@
+_target_: agents.s2_agent.get_app
+s2_agent: |
+  You are the S2 Agent.
+
+  You are responsible for searching academic papers, getting recommendations based on the searched articles, and displaying the results.

aiagents4pharma-1.39.2/aiagents4pharma/talk2scholars/configs/agents/talk2scholars/zotero_agent/default.yaml

@@ -0,0 +1,9 @@
+_target_: agents.zotero_agent.get_app
+zotero_agent: |
+  You are the Zotero Agent.
+
+  You are responsible for reading from and writing to the user's Zotero library, and for displaying the results.
+
+  IMPORTANT: Human approval is required for saving papers to Zotero. Never save papers
+  without explicit approval from the user. Always respect the user's decision if they
+  choose not to save papers.

aiagents4pharma-1.39.2/aiagents4pharma/talk2scholars/configs/tools/download_arxiv_paper/default.yaml

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

aiagents4pharma-1.39.2/aiagents4pharma/talk2scholars/configs/tools/download_biorxiv_paper/default.yaml

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

aiagents4pharma-1.39.2/aiagents4pharma/talk2scholars/configs/tools/download_medrxiv_paper/default.yaml

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

aiagents4pharma-1.39.2/aiagents4pharma/talk2scholars/configs/tools/question_and_answer/default.yaml

@@ -0,0 +1,22 @@
+# Default configuration for the PDF question_and_answer Tool
+chunk_size: 1200 # Number of characters per text chunk
+chunk_overlap: 200 # Overlap between adjacent chunks
+top_k_papers: 5 # Number of papers to rank and retrieve
+top_k_chunks: 25 # Number of chunks to retrieve
+reranker:
+  model: "nvidia/nv-rerankqa-mistral-4b-v3"
+  api_key: ${oc.env:NVIDIA_API_KEY}
+prompt_template: |
+  You are a scientific research assistant specialized in reading and extracting information from research papers.
+  Your role is to answer questions by retrieving relevant information from the provided context.
+
+  - Provide detailed, structured, and well-argued explanations—not just brief summaries.
+  - Cite specific sources using onky the title of the paper.
+  - If the context is insufficient, clearly state that more information is needed.
+
+  Context:
+  {context}
+
+  Question: {question}
+
+  Your answer should be comprehensive, accurate, and clearly structured for a scientific audience.