aiagents4pharma 1.39.0__py3-none-any.whl → 1.39.1__py3-none-any.whl

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

@@ -109,8 +109,28 @@ class SearchData:
 
     def _filter_papers(self) -> None:
         """Filter and format papers."""
-        self.filtered_papers = {
-            paper["paperId"]: {
+        # Build filtered papers mapping with unified paper_ids list
+        filtered: Dict[str, Any] = {}
+        for paper in self.papers:
+            if not paper.get("title") or not paper.get("authors"):
+                continue
+            ext = paper.get("externalIds", {}) or {}
+            # Prioritized list of IDs: arXiv, PubMed, PubMedCentral, DOI
+            ids: list[str] = []
+            arxiv = ext.get("ArXiv")
+            if arxiv:
+                ids.append(f"arxiv:{arxiv}")
+            pubmed = ext.get("PubMed")
+            if pubmed:
+                ids.append(f"pubmed:{pubmed}")
+            pmc = ext.get("PubMedCentral")
+            if pmc:
+                ids.append(f"pmc:{pmc}")
+            doi_id = ext.get("DOI")
+            if doi_id:
+                ids.append(f"doi:{doi_id}")
+            # Compose metadata dict
+            metadata = {
                 "semantic_scholar_paper_id": paper["paperId"],
                 "Title": paper.get("title", "N/A"),
                 "Abstract": paper.get("abstract", "N/A"),
@@ -124,27 +144,42 @@ class SearchData:
                     for author in paper.get("authors", [])
                 ],
                 "URL": paper.get("url", "N/A"),
-                "arxiv_id": paper.get("externalIds", {}).get("ArXiv", "N/A"),
-                "doi": paper.get("externalIds", {}).get("DOI", "N/A"),
+                "arxiv_id": arxiv or "N/A",
+                "pmc_id": pmc or "N/A",
+                "pm_id": pubmed or "N/A",
+                "doi": doi_id or "N/A",
+                "paper_ids": ids,
+                "source": "semantic_scholar",
             }
-            for paper in self.papers
-            if paper.get("title") and paper.get("authors")
-        }
+            filtered[paper["paperId"]] = metadata
+        self.filtered_papers = filtered
 
         logger.info("Filtered %d papers", len(self.filtered_papers))
 
+    def _get_snippet(self, abstract: str) -> str:
+        """Extract the first one or two sentences from an abstract."""
+        if not abstract or abstract == "N/A":
+            return ""
+        sentences = abstract.split(". ")
+        snippet_sentences = sentences[:2]
+        snippet = ". ".join(snippet_sentences)
+        if not snippet.endswith("."):
+            snippet += "."
+        return snippet
+
     def _create_content(self) -> None:
         """Create the content message for the response."""
         top_papers = list(self.filtered_papers.values())[:3]
-        top_papers_info = "\n".join(
-            [
-                f"{i+1}. {paper['Title']} ({paper['Year']}; "
-                f"semantic_scholar_paper_id: {paper['semantic_scholar_paper_id']}; "
-                f"arXiv ID: {paper['arxiv_id']})"
-                f"doi: {paper['doi']})"
-                for i, paper in enumerate(top_papers)
-            ]
-        )
+        entries = []
+        for i, paper in enumerate(top_papers):
+            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})"
+            if snippet:
+                entry += f"\n   Abstract snippet: {snippet}"
+            entries.append(entry)
+        top_papers_info = "\n".join(entries)
 
         logger.info("-----------Filtered %d papers", self.get_paper_count())
 

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

@@ -5,7 +5,7 @@ Utility for fetching recommendations based on a single paper.
 """
 
 import logging
-from typing import Any, Optional, Dict
+from typing import Any, Optional, Dict, List
 import hydra
 import requests
 
@@ -120,8 +120,26 @@ class SinglePaperRecData:
 
     def _filter_papers(self) -> None:
         """Filter and format papers."""
-        self.filtered_papers = {
-            paper["paperId"]: {
+        # Build filtered recommendations with unified paper_ids
+        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] = []
+            arxiv = ext.get("ArXiv")
+            if arxiv:
+                ids.append(f"arxiv:{arxiv}")
+            pubmed = ext.get("PubMed")
+            if pubmed:
+                ids.append(f"pubmed:{pubmed}")
+            pmc = ext.get("PubMedCentral")
+            if pmc:
+                ids.append(f"pmc:{pmc}")
+            doi_id = ext.get("DOI")
+            if doi_id:
+                ids.append(f"doi:{doi_id}")
+            metadata = {
                 "semantic_scholar_paper_id": paper["paperId"],
                 "Title": paper.get("title", "N/A"),
                 "Abstract": paper.get("abstract", "N/A"),
@@ -135,27 +153,42 @@ class SinglePaperRecData:
                     for author in paper.get("authors", [])
                 ],
                 "URL": paper.get("url", "N/A"),
-                "arxiv_id": paper.get("externalIds", {}).get("ArXiv", "N/A"),
-                "doi": paper.get("externalIds", {}).get("DOI", "N/A"),
+                "arxiv_id": arxiv or "N/A",
+                "pm_id": pubmed or "N/A",
+                "pmc_id": pmc or "N/A",
+                "doi": doi_id or "N/A",
+                "paper_ids": ids,
+                "source": "semantic_scholar",
             }
-            for paper in self.recommendations
-            if paper.get("title") and paper.get("authors")
-        }
+            filtered[paper["paperId"]] = metadata
+        self.filtered_papers = filtered
 
         logger.info("Filtered %d papers", len(self.filtered_papers))
 
+    def _get_snippet(self, abstract: str) -> str:
+        """Extract the first one or two sentences from an abstract."""
+        if not abstract or abstract == "N/A":
+            return ""
+        sentences = abstract.split(". ")
+        snippet_sentences = sentences[:2]
+        snippet = ". ".join(snippet_sentences)
+        if not snippet.endswith("."):
+            snippet += "."
+        return snippet
+
     def _create_content(self) -> None:
         """Create the content message for the response."""
         top_papers = list(self.filtered_papers.values())[:3]
-        top_papers_info = "\n".join(
-            [
-                f"{i+1}. {paper['Title']} ({paper['Year']}; "
-                f"semantic_scholar_paper_id: {paper['semantic_scholar_paper_id']}; "
-                f"arXiv ID: {paper['arxiv_id']})"
-                f"doi: {paper['doi']})"
-                for i, paper in enumerate(top_papers)
-            ]
-        )
+        entries: list[str] = []
+        for i, paper in enumerate(top_papers):
+            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})"
+            if snippet:
+                entry += f"\n   Abstract snippet: {snippet}"
+            entries.append(entry)
+        top_papers_info = "\n".join(entries)
 
         self.content = (
             "Recommendations based on the single paper were successful. "

{aiagents4pharma-1.39.0.dist-info → aiagents4pharma-1.39.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aiagents4pharma
-Version: 1.39.0
+Version: 1.39.1
 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/tree/main/aiagents4pharma/install.md)
 
 ##### **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/tree/main/aiagents4pharma/install.md)
 
 ##### **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/tree/main/aiagents4pharma).
 
 **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/tree/main/aiagents4pharma/install.md)
 
 #### 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.dist-info → aiagents4pharma-1.39.1.dist-info}/RECORD

@@ -146,7 +146,7 @@ aiagents4pharma/talk2knowledgegraphs/utils/extractions/multimodal_pcst.py,sha256
 aiagents4pharma/talk2knowledgegraphs/utils/extractions/pcst.py,sha256=m5p0yoJb7I19ua5yeQfXPf7c4r6S1XPwttsrM7Qoy94,9336
 aiagents4pharma/talk2scholars/__init__.py,sha256=NOZxTklAH1j1ggu97Ib8Xn9LCKudEWt-8dx8w7yxVD8,180
 aiagents4pharma/talk2scholars/agents/__init__.py,sha256=c_0Pk85bt-RfK5RMyALM3MXo3qXVMoYS7BOqM9wuFME,317
-aiagents4pharma/talk2scholars/agents/main_agent.py,sha256=oCSWPj3TUgTIERmYbBTYipNrU1g956LXJEUx-7-KAQ0,3354
+aiagents4pharma/talk2scholars/agents/main_agent.py,sha256=oQqa1z4nvfUvPWCX-SUHGs9jOCJKtzjw86jXJZ68gCk,3382
 aiagents4pharma/talk2scholars/agents/paper_download_agent.py,sha256=J_kEl8joQfM80211xlNLZA9RkN52fY58dbCisuiEft8,3687
 aiagents4pharma/talk2scholars/agents/pdf_agent.py,sha256=GEXzJMQxIeZ7zLP-AlnTMU-n_KXZ7g22Qd9L3USIc_4,3626
 aiagents4pharma/talk2scholars/agents/s2_agent.py,sha256=oui0CMSyXmBGBJ7LnYq8Ce0V8Qc3BS6GgH5Qx5wI6oM,4565
@@ -156,13 +156,13 @@ aiagents4pharma/talk2scholars/configs/config.yaml,sha256=F7BCgmcnhfkyKT6qFL11E_i
 aiagents4pharma/talk2scholars/configs/agents/__init__.py,sha256=plv5Iw34gvbGZbRyJapvoOiiFXekRQIwjV_yy5AR_SI,104
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/__init__.py,sha256=D94LW4cXLmJe4dNl5qoR9QN0JnBqGLbQDgDLqhCNUE0,213
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/main_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
-aiagents4pharma/talk2scholars/configs/agents/talk2scholars/main_agent/default.yaml,sha256=EmUAxeQSnH4U5Op5_XOzCbcexDCp-Rpz3z0yVPRtQUg,1315
+aiagents4pharma/talk2scholars/configs/agents/talk2scholars/main_agent/default.yaml,sha256=hew5vyrhLeJktoN6DTPRRpnINrXqKZ4trLJQDOuDGOA,4712
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/paper_download_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/pdf_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/s2_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
-aiagents4pharma/talk2scholars/configs/agents/talk2scholars/s2_agent/default.yaml,sha256=_sSt2jCgSILwrXkywDAxkXONCZn896owLBaf46iFI0I,1323
+aiagents4pharma/talk2scholars/configs/agents/talk2scholars/s2_agent/default.yaml,sha256=N3a_brrB1ilUCeqHQrqu97Olz2snko3tTNPMNR8yTHI,208
 aiagents4pharma/talk2scholars/configs/agents/talk2scholars/zotero_agent/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
-aiagents4pharma/talk2scholars/configs/agents/talk2scholars/zotero_agent/default.yaml,sha256=SOdjRiGUxjW9JeCRDd_U1RjCclItkoPODrj5RpIrxSY,2030
+aiagents4pharma/talk2scholars/configs/agents/talk2scholars/zotero_agent/default.yaml,sha256=FUbJIiH_FHeL0n1M-HSsLX_R2gMBRxBnPcejhd0HrYc,399
 aiagents4pharma/talk2scholars/configs/app/__init__.py,sha256=tXpOW3R4eAfNoqvoaHfabSG-DcMHmUGSTg_4zH_vlgw,94
 aiagents4pharma/talk2scholars/configs/app/frontend/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2scholars/configs/app/frontend/default.yaml,sha256=A6nYjrgzEyRv5JYsGN7oqNX4-tufMBZ6mg-A7bMX6V4,906
@@ -186,48 +186,55 @@ aiagents4pharma/talk2scholars/configs/tools/zotero_write/default.yaml,sha256=gB7
 aiagents4pharma/talk2scholars/state/__init__.py,sha256=ReScKLpEvedq4P6ww52NRQS0Xr6SSQV7hqoQ83Mt75U,138
 aiagents4pharma/talk2scholars/state/state_talk2scholars.py,sha256=Z2zV-SXB2SMnn8PnjWjmK-OD5KjUwMTChBpXBAcl2hg,3885
 aiagents4pharma/talk2scholars/tests/__init__.py,sha256=U3PsTiUZaUBD1IZanFGkDIOdFieDVJtGKQ5-woYUo8c,45
-aiagents4pharma/talk2scholars/tests/test_llm_main_integration.py,sha256=FBRqS06IKJYFOudQEHQr-9oJ4tftkH-gTCowTAqwWSg,3686
-aiagents4pharma/talk2scholars/tests/test_main_agent.py,sha256=IZYSocYVwqPil2lF6L07mKm8PUq7vjopmqNiCm6IJEA,6876
+aiagents4pharma/talk2scholars/tests/test_main_agent.py,sha256=4Z3xLq8MGlayGhQE5qKOirYotwJrlf7fk8rqAaORorg,7617
+aiagents4pharma/talk2scholars/tests/test_nvidia_nim_reranker_utils.py,sha256=-q4Y2CMTAOvrSyyZ1MmpeEuKvJcZSPe6jmUD0rZhUew,947
 aiagents4pharma/talk2scholars/tests/test_paper_download_agent.py,sha256=gKSQp-sw62FplNnGYW0wv2ZIUEefh3o0tFWbRzy9yLs,5068
 aiagents4pharma/talk2scholars/tests/test_paper_download_biorxiv.py,sha256=gosuW4VBXyorQXbf0TpgAIT2hQjEeuvTTnT1jnoBYqM,6405
 aiagents4pharma/talk2scholars/tests/test_paper_download_medrxiv.py,sha256=iNq9vEIVapmnUZTRJXCv_UoaWThGapW7Vt_2BmZG9NE,6414
-aiagents4pharma/talk2scholars/tests/test_paper_download_tools.py,sha256=3mycLeEgH5XkwxuoXfTpQb8c8xFtIX2HjVnACPrSf60,7141
-aiagents4pharma/talk2scholars/tests/test_pdf_agent.py,sha256=scGCTgka2JuoUhzZwzDn0OgIYihOLhXbwb5uGFR02aI,4302
-aiagents4pharma/talk2scholars/tests/test_question_and_answer_tool.py,sha256=KR4GjjGgBjWXwEVzSh4ZpYjcWPq-EaZTT_fzRheb0uY,37286
+aiagents4pharma/talk2scholars/tests/test_paper_download_tools.py,sha256=lGXbHl3lEXDjMHAX9uCgrREBOUuOHWv9TsYEshiG_tc,10421
+aiagents4pharma/talk2scholars/tests/test_pdf_agent.py,sha256=9Kr0FcyFWmUDTasYh6ZdS-OWQqy37mH9K3p5Y0dqQHw,4283
+aiagents4pharma/talk2scholars/tests/test_question_and_answer_tool.py,sha256=7S9bqQSdvm7xihtBSAQD3RQimFtVHejPIkaaEddeNRs,22057
 aiagents4pharma/talk2scholars/tests/test_read_helper_utils.py,sha256=yTT1aLpTydDSdGcRZur5cMktwYZbFK5NEUgOBvltcWg,3819
-aiagents4pharma/talk2scholars/tests/test_routing_logic.py,sha256=g79tG68ZrUOL3-duCCJwvFK6OieR5KedRf3yTUDqIFk,2784
-aiagents4pharma/talk2scholars/tests/test_s2_agent.py,sha256=xvlPU4Lz_DdQLTpdtoHW9l_AMvFrzC-FXE5royGbtLM,7806
-aiagents4pharma/talk2scholars/tests/test_s2_display.py,sha256=Q1q0TEavO2kkXBjo2yeSbzV7xHspnDSvTveaUB-NkQE,3116
+aiagents4pharma/talk2scholars/tests/test_s2_agent.py,sha256=TsdNlZ6vHz18bbX6Vto28nbBLRDI94wSFt5-1acDK64,7768
+aiagents4pharma/talk2scholars/tests/test_s2_display_dataframe.py,sha256=2VPPZitQRWDZV0ceaK2-hQqkIvoigSPWNHoFOgKJjQE,3107
 aiagents4pharma/talk2scholars/tests/test_s2_multi.py,sha256=VCTfexhtX7FgWOBS0YtSm1zghbByZnni1NBLGVTJVGI,11166
-aiagents4pharma/talk2scholars/tests/test_s2_query.py,sha256=8Em_bcexpv3odC20TRPi6eoz-6fPXGKabob1Ye0jdsg,3286
-aiagents4pharma/talk2scholars/tests/test_s2_retrieve.py,sha256=YtA2nbPRtoSR7mPqEjqLF5ERGVzTfeULztsNoCI48X8,2003
+aiagents4pharma/talk2scholars/tests/test_s2_query_dataframe.py,sha256=6FBA1RwYx3_n-y1rntJuw3R5a0WMgcQuYVChhpM8uSo,7603
+aiagents4pharma/talk2scholars/tests/test_s2_retrieve.py,sha256=bCcy4i3LyoVf4qm0kcCqsmyjhwqEif3v38jsalqD8yc,2130
 aiagents4pharma/talk2scholars/tests/test_s2_search.py,sha256=mCGpoCYVn0SJ9BPcEjTz2MLy_K2XJIxvPngwsMoKijA,9945
 aiagents4pharma/talk2scholars/tests/test_s2_single.py,sha256=KjSh7V2cl1IuO_M9O6dj0vnMHr13H-xKxia_ZgT4qag,10313
+aiagents4pharma/talk2scholars/tests/test_s2_utils_ext_ids.py,sha256=6xbHzClkYI_ZcR3-Xl7nGs8-hB0IyLlxn8rzeXrJxFQ,15129
 aiagents4pharma/talk2scholars/tests/test_state.py,sha256=A2lqA4h37QptLnwKWwm1Y79yELE4wtEBXzCiQ13YdLw,1270
-aiagents4pharma/talk2scholars/tests/test_zotero_agent.py,sha256=jFEtfQVEwEQ6v3kq7A1_p2MKCu5wbtX47V4bE-fKD6M,6158
+aiagents4pharma/talk2scholars/tests/test_tool_helper_utils.py,sha256=gJBzV1-hkzGi3VY9SG4JSoKTyz7KavPy1HjEF6bnfIQ,6141
+aiagents4pharma/talk2scholars/tests/test_zotero_agent.py,sha256=iWbWlat5RWE8mmCSqKGNG7Xzbdieua6cKGq-jwqP4ws,6119
 aiagents4pharma/talk2scholars/tests/test_zotero_human_in_the_loop.py,sha256=YelLQu9Y_r1SNQsC1xoLHJoJ3soIZtBt1MFbbNhY-Dg,10744
 aiagents4pharma/talk2scholars/tests/test_zotero_path.py,sha256=Ko0HyXCrpm-vs8Bkf-syxp3MfL1IvZwXXgPExyQy_F8,18618
 aiagents4pharma/talk2scholars/tests/test_zotero_pdf_downloader_utils.py,sha256=N9CBRG0rQyqptKRCaYCH2VJk87O-wc9Cc1KI5MMnyjA,1670
-aiagents4pharma/talk2scholars/tests/test_zotero_read.py,sha256=E7ncgspEzhJTvmZuKplugZJPPWsoiFU_xLUg-oz6qkI,29100
+aiagents4pharma/talk2scholars/tests/test_zotero_read.py,sha256=qkudWMjxjjTYKJ1zvpWs0EJXCIvFx-iNKyKs_Tv1CSI,29061
 aiagents4pharma/talk2scholars/tests/test_zotero_write.py,sha256=qWlO0XoZJ6vxUxgisjYv9Np87CoTEDxiQBEOhdj9foo,6111
 aiagents4pharma/talk2scholars/tools/__init__.py,sha256=c8pYHDqR9P0Frz2jWjbvyizfSTBMlMFzGsiQzx2KC9c,189
 aiagents4pharma/talk2scholars/tools/paper_download/__init__.py,sha256=Lu5FmBxDH8mIIYE41G8_BKYXUf-vHIYVwujidbeydl4,295
-aiagents4pharma/talk2scholars/tools/paper_download/download_arxiv_input.py,sha256=WTWvXbh0C96OoMoPf8Bgu0AgorsdkWslac_WqlHc4bo,3900
+aiagents4pharma/talk2scholars/tools/paper_download/download_arxiv_input.py,sha256=e3S8JusJVVSEC_tFh8H5CS9ZqD20jX8hkFO9EYESBXo,5653
 aiagents4pharma/talk2scholars/tools/paper_download/download_biorxiv_input.py,sha256=R92OaR4Omilj-v-rT0Me_BhxN8-AF0sbDwhUxNCUTm4,3718
 aiagents4pharma/talk2scholars/tools/paper_download/download_medrxiv_input.py,sha256=UaHsdZXseUMQfiIovD0kS8r9DZ6KJpRGtTZyOCTRYVs,3786
 aiagents4pharma/talk2scholars/tools/pdf/__init__.py,sha256=DPpOfON3AySko5EBBAe_3udOoSaAdQWNyGeNvJyV5R8,138
-aiagents4pharma/talk2scholars/tools/pdf/question_and_answer.py,sha256=pzJhSOdchyS3J4Tzoh7aFMALJFCqEk4Xh4LCDa-5I1I,23406
+aiagents4pharma/talk2scholars/tools/pdf/question_and_answer.py,sha256=PI9ltnKZpORXAPPowPt6qVbXclXXoY4mamj8ZKA0tsM,5586
+aiagents4pharma/talk2scholars/tools/pdf/utils/__init__.py,sha256=Ghsh5nnESckMqvnokMRW_3mo2sDstOPKAAuiAHF1b8o,273
+aiagents4pharma/talk2scholars/tools/pdf/utils/generate_answer.py,sha256=YvnBWD7yn12H5nchPBFBD9txviwJtX56f3fDRwkGBBE,3299
+aiagents4pharma/talk2scholars/tools/pdf/utils/nvidia_nim_reranker.py,sha256=M4OSqact8QMk-Ov05Bcz7Y7tr2rBAgdM3DRsQKB0r0o,2851
+aiagents4pharma/talk2scholars/tools/pdf/utils/retrieve_chunks.py,sha256=agV7SHy5ool0x_N7WmNI-C1Wpc-6EToYoiqkMJX6xWs,2599
+aiagents4pharma/talk2scholars/tools/pdf/utils/tool_helper.py,sha256=maOIh6sLSOqU3PTsty5AZKIoBGxziFDi-LliSULQyK0,4702
+aiagents4pharma/talk2scholars/tools/pdf/utils/vector_store.py,sha256=8yumaryNLZdRP_WcRt6GHk9Oi8asYPkOS9vKSn7zJak,5810
 aiagents4pharma/talk2scholars/tools/s2/__init__.py,sha256=w_eiw0pG8HNp79F9O_icXs_Yl_4odsmagYNKDTjIsvk,428
-aiagents4pharma/talk2scholars/tools/s2/display_dataframe.py,sha256=wOZ7UJq4b8vl7NU9mU3BW_nRmCIkeBvc6nbGGegysek,3181
-aiagents4pharma/talk2scholars/tools/s2/multi_paper_rec.py,sha256=N7-6dzRI71bK7MG3-A4G505YnNvAMJW_Qjjtcoo4JYw,2799
-aiagents4pharma/talk2scholars/tools/s2/query_dataframe.py,sha256=uI6-UnZu96Uirzohx-F7vMHOVSPlPrD4XJdwgF5GcMo,2866
-aiagents4pharma/talk2scholars/tools/s2/retrieve_semantic_scholar_paper_id.py,sha256=llzMMnEQKeYVamJbF4_DTMx-BgVe79vwDcUIFGLrmUY,2615
-aiagents4pharma/talk2scholars/tools/s2/search.py,sha256=p86RLy_9bMxm3KTDL2L0Ilb3yeF4K6IIkZCgbt4CsiE,2529
-aiagents4pharma/talk2scholars/tools/s2/single_paper_rec.py,sha256=rnl6Bb7mKXg_lsProAYaSEJNIzWgNVZuDHqD-dDe9EI,2763
+aiagents4pharma/talk2scholars/tools/s2/display_dataframe.py,sha256=qnY7AQDnAs0SrmV7AZ9pWm10HEmPlO7EBfzYvpb3jvs,3965
+aiagents4pharma/talk2scholars/tools/s2/multi_paper_rec.py,sha256=NY8nTsW9xP6qakiQ0wbq9AXP2mcT5-GMZoa9cnr4EjY,3770
+aiagents4pharma/talk2scholars/tools/s2/query_dataframe.py,sha256=omff-2g85qcLZj5Qo35m2LJlE1AOzESEfT4jt3ZVYz0,7066
+aiagents4pharma/talk2scholars/tools/s2/retrieve_semantic_scholar_paper_id.py,sha256=aJTIbUKXLvjD9P7S-SM0O5iTRdUdomOcE67lHwsmGjg,3954
+aiagents4pharma/talk2scholars/tools/s2/search.py,sha256=SUAN32x1d9dNikFKitcXZZ0BhFfsGMdLDk0z0DpJXuA,3334
+aiagents4pharma/talk2scholars/tools/s2/single_paper_rec.py,sha256=3lvrIPlgP8gp_3YQCcUQKyHmNMHevN8OqLTq4mPeBEY,3502
 aiagents4pharma/talk2scholars/tools/s2/utils/__init__.py,sha256=wBTPVgiXbmIJUMouOQRwojgk5PJXeEinDJzHzEToZbU,229
-aiagents4pharma/talk2scholars/tools/s2/utils/multi_helper.py,sha256=kjzZ90Cd23hXBQ861Z2BEjE1VvI02zxc1mIj2S7YWFo,7379
-aiagents4pharma/talk2scholars/tools/s2/utils/search_helper.py,sha256=AembYVndEOwgcDz_n1VWAydfL8ufQ5pEokTKkrx47jA,6474
-aiagents4pharma/talk2scholars/tools/s2/utils/single_helper.py,sha256=zLENnFSyQIpXqmJKow1XHS9pWbf27tsSUEvzydNCj9I,7094
+aiagents4pharma/talk2scholars/tools/s2/utils/multi_helper.py,sha256=Z5G4e7R7cUO60_HYbcd3BJC_-jtybc5DGcOC8yjpprY,8642
+aiagents4pharma/talk2scholars/tools/s2/utils/search_helper.py,sha256=wVkQW2KTmS2av4W5PqqRhCb53n-egZLpAD95xV2mO68,7839
+aiagents4pharma/talk2scholars/tools/s2/utils/single_helper.py,sha256=ClTOpDfjgj1BtfCFtBVkl7ANAIZhG_mUh6WCTUegtlQ,8363
 aiagents4pharma/talk2scholars/tools/zotero/__init__.py,sha256=wXiQILLq-utV35PkDUpm_F074mG9yRMyGQAFlr9UAOw,197
 aiagents4pharma/talk2scholars/tools/zotero/zotero_read.py,sha256=Fgv7PIkIlRqfl8EprcXqr1S4wtbSG8itv7x-3nMf3Rc,3990
 aiagents4pharma/talk2scholars/tools/zotero/zotero_review.py,sha256=iqwpolg7GWAjXizubLrPaAsgOpsOhKz-tFRyLOiBvC0,6325
@@ -238,8 +245,8 @@ aiagents4pharma/talk2scholars/tools/zotero/utils/review_helper.py,sha256=IPD1V9y
 aiagents4pharma/talk2scholars/tools/zotero/utils/write_helper.py,sha256=ALwLecy1QVebbsmXJiDj1GhGmyhq2R2tZlAyEl1vfhw,7410
 aiagents4pharma/talk2scholars/tools/zotero/utils/zotero_path.py,sha256=oIrfbOySgts50ksHKyjcWjRkPRIS88g3Lc0v9mBkU8w,6375
 aiagents4pharma/talk2scholars/tools/zotero/utils/zotero_pdf_downloader.py,sha256=ERBha8afU6Q1EaRBe9qB8tchOzZ4_KfFgDW6EElOJoU,4816
-aiagents4pharma-1.39.0.dist-info/licenses/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
-aiagents4pharma-1.39.0.dist-info/METADATA,sha256=ITwj9yujMnDVZtQM3n09ZxDv4ueGCGDlG2JZOvU3n7k,16788
-aiagents4pharma-1.39.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-aiagents4pharma-1.39.0.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
-aiagents4pharma-1.39.0.dist-info/RECORD,,
+aiagents4pharma-1.39.1.dist-info/licenses/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
+aiagents4pharma-1.39.1.dist-info/METADATA,sha256=9ncdNvJh3EUIjSlFJI9w8DF7k2DPmaRlOFiQ0tj1HSs,14578
+aiagents4pharma-1.39.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+aiagents4pharma-1.39.1.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
+aiagents4pharma-1.39.1.dist-info/RECORD,,

aiagents4pharma/talk2scholars/tests/test_llm_main_integration.py

@@ -1,89 +0,0 @@
-"""
-Integration tests for talk2scholars system with OpenAI.
-This test triggers all sub-agents by sending a conversation that covers:
-- Searching Semantic Scholar (S2 agent)
-- Retrieving Zotero results (Zotero agent)
-- Querying PDF content (PDF agent)
-- Downloading paper details from arXiv (Paper Download agent)
-"""
-
-# This will be covered in the next pr.
-
-#
-# import os
-# import pytest
-# import hydra
-# from langchain_openai import ChatOpenAI
-# from langchain_core.messages import HumanMessage, AIMessage
-# from ..agents.main_agent import get_app
-# from ..state.state_talk2scholars import Talk2Scholars
-#
-# # pylint: disable=redefined-outer-name,too-few-public-methods
-#
-#
-# @pytest.mark.skipif(
-#     not os.getenv("OPENAI_API_KEY"), reason="Requires OpenAI API key to run"
-# )
-# def test_main_agent_real_llm():
-#     """
-#     Integration test for the Talk2Scholars system using a real OpenAI LLM.
-#     This test verifies that the supervisor correctly routes to all sub-agents by
-#     providing a conversation with queries intended to trigger each agent.
-#     """
-#     # Load Hydra configuration EXACTLY like in main_agent.py
-#     with hydra.initialize(version_base=None, config_path="../configs"):
-#         cfg = hydra.compose(
-#             config_name="config", overrides=["agents/talk2scholars/main_agent=default"]
-#         )
-#     hydra_cfg = cfg.agents.talk2scholars.main_agent
-#     assert hydra_cfg is not None, "Hydra config failed to load"
-#
-#     # Use the real OpenAI API (ensure OPENAI_API_KEY is set in environment)
-#     llm = ChatOpenAI(model="gpt-4o-mini", temperature=hydra_cfg.temperature)
-#
-#     # Initialize the main agent workflow (with real Hydra config)
-#     thread_id = "test_thread"
-#     app = get_app(thread_id, llm)
-#
-#     # Provide a multi-turn conversation intended to trigger all sub-agents:
-#     # - S2 agent: "Search Semantic Scholar for AI papers on transformers."
-#     # - Zotero agent: "Retrieve Zotero results for these papers."
-#     # - PDF agent: "Analyze the attached PDF and summarize its key findings."
-#     # - Paper Download agent: "Download the paper details from arXiv."
-#     initial_state = Talk2Scholars(
-#         messages=[
-#             HumanMessage(
-#                 content="Search Semantic Scholar for AI papers on transformers."
-#             ),
-#             HumanMessage(content="Also, retrieve Zotero results for these papers."),
-#             HumanMessage(
-#                 content="I have attached a PDF; analyze it and tell me the key findings."
-#             ),
-#             HumanMessage(content="Finally, download the paper from arXiv."),
-#         ]
-#     )
-#
-#     # Invoke the agent (which routes to the appropriate sub-agents)
-#     result = app.invoke(
-#         initial_state,
-#         {"configurable": {"config_id": thread_id, "thread_id": thread_id}},
-#     )
-#
-#     # Assert that the result contains messages and that the final message is valid.
-#     assert "messages" in result, "Expected 'messages' in the response"
-#     last_message = result["messages"][-1]
-#     assert isinstance(
-#         last_message, (HumanMessage, AIMessage, str)
-#     ), "Last message should be a valid response type"
-#
-#     # Concatenate message texts (if available) to perform keyword checks.
-#     output_text = " ".join(
-#         msg.content if hasattr(msg, "content") else str(msg)
-#         for msg in result["messages"]
-#     ).lower()
-#
-#     # Check for keywords that suggest each sub-agent was invoked.
-#     for keyword in ["semantic scholar", "zotero", "pdf", "arxiv"]:
-#         assert (
-#             keyword in output_text
-#         ), f"Expected keyword '{keyword}' in the output response"