aiagents4pharma 1.14.1__py3-none-any.whl → 1.15.1__py3-none-any.whl

aiagents4pharma/configs/talk2biomodels/agents/t2b_agent/default.yaml

@@ -5,4 +5,10 @@ state_modifier: >
   then pass the use_uploaded_model argument
   as True. If the user asks for simulation
   or param_scan or steady state, suggest a
-  value for the `experiment_name` argument.
+  value for the `experiment_name` argument.
+
+  If the user asks question related to the
+  uploaded document/pdf/article/document,
+  use the tool `query_article` to answer the
+  question. Please note that the `experiment_name`
+  argument may be unrelated to the question asked.

aiagents4pharma/configs/talk2biomodels/tools/ask_question/default.yaml

@@ -0,0 +1,39 @@
+_target_: talk2biomodels.tools.ask_question.AskQuestionTool
+steady_state_prompt: >
+  Following are header columns of the data:
+  `species_name`: Name of the species,
+  `compartment`: Compartment of the species,
+  `initial_concentration`: Concentration of the species at the start of steady state,
+  `steady_state_concentration`: Concentration of the species at steady state,
+  `steady_state_transition_time`: Time taken to reach steady state,
+  `display_name`: An alias for the species name.
+
+  Here are some instructions to help you answer questions:
+
+  1. Before you answer any question, follow the plan and solve
+  technique. Start by understanding the question, then plan your
+  approach to solve the question, and finally solve the question
+  by following the plan. Always give a brief explanation of your
+  answer to the user.
+
+  2. If the user wants to know the time taken by the model to reach
+  steady state, you should look at the steady_state_transition_time
+  column of the data for the model species. The highest value in
+  this column is the time taken by the model to reach steady state.
+
+  3. To get accurate results, trim the data to the relevant columns
+  before performing any calculations. This will help you avoid
+  errors in your calculations, and ignore irrelevant data.
+
+  4. Please use the units provided below to answer the questions.
+simulation_prompt: >
+  Following is the information about the data frame:
+  1. First column is the time column, and the rest of the columns
+  are the species names.
+
+  2. While the time column records the simulation time points, the
+  rest of the columns record the concentration of the species at
+  each time point.
+
+  3. Please use the units provided below to answer the questions.
+  

aiagents4pharma/talk2biomodels/agents/t2b_agent.py

@@ -19,6 +19,7 @@ from ..tools.get_annotation import GetAnnotationTool
 from ..tools.ask_question import AskQuestionTool
 from ..tools.parameter_scan import ParameterScanTool
 from ..tools.steady_state import SteadyStateTool
+from ..tools.query_article import QueryArticle
 from ..states.state_talk2biomodels import Talk2Biomodels
 
 # Initialize logger
@@ -46,7 +47,8 @@ def get_app(uniq_id, llm_model='gpt-4o-mini'):
                     GetModelInfoTool(),
                     SteadyStateTool(),
                     ParameterScanTool(),
-                    GetAnnotationTool()
+                    GetAnnotationTool(),
+                    QueryArticle()
                 ])
 
     # Define the model

aiagents4pharma/talk2biomodels/states/state_talk2biomodels.py

@@ -27,6 +27,7 @@ class Talk2Biomodels(AgentState):
     The state for the Talk2BioModels agent.
     """
     llm_model: str
+    pdf_file_name: str
     # A StateGraph may receive a concurrent updates
     # which is not supported by the StateGraph. Hence,
     # we need to add a reducer function to handle the

aiagents4pharma/talk2biomodels/tests/test_query_article.py

@@ -0,0 +1,76 @@
+'''
+Test cases for Talk2Biomodels query_article tool.
+'''
+
+from pydantic import BaseModel, Field
+from langchain_core.messages import HumanMessage, ToolMessage
+from langchain_openai import ChatOpenAI
+from ..agents.t2b_agent import get_app
+
+class Article(BaseModel):
+    '''
+    Article schema.
+    '''
+    title: str = Field(description="Title of the article.")
+
+def test_query_article_with_an_article():
+    '''
+    Test the query_article tool by providing an article.
+    '''
+    unique_id = 12345
+    app = get_app(unique_id)
+    config = {"configurable": {"thread_id": unique_id}}
+    # Update state by providing the pdf file name
+    app.update_state(config,
+      {"pdf_file_name": "aiagents4pharma/talk2biomodels/tests/article_on_model_537.pdf"})
+    prompt = "What is the title of the article?"
+    # Test the tool query_article
+    response = app.invoke(
+                        {"messages": [HumanMessage(content=prompt)]},
+                        config=config
+                    )
+    # Get the response from the tool
+    assistant_msg = response["messages"][-1].content
+    # Prepare a LLM that can be used as a judge
+    llm = ChatOpenAI(model='gpt-4o-mini', temperature=0)
+    # Make it return a structured output
+    structured_llm = llm.with_structured_output(Article)
+    # Prepare a prompt for the judge
+    prompt = "Given the text below, what is the title of the article?"
+    prompt += f"\n\n{assistant_msg}"
+    # Get the structured output
+    article = structured_llm.invoke(prompt)
+    # Check if the article title is correct
+    expected_title = "A Multiscale Model of IL-6–Mediated "
+    expected_title += "Immune Regulation in Crohn’s Disease"
+    # Check if the article title is correct
+    assert article.title == expected_title
+
+def test_query_article_without_an_article():
+    '''
+    Test the query_article tool without providing an article.
+    The status of the tool should be error.
+    '''
+    unique_id = 12345
+    app = get_app(unique_id)
+    config = {"configurable": {"thread_id": unique_id}}
+    prompt = "What is the title of the uploaded article?"
+    # Test the tool query_article
+    app.invoke(
+            {"messages": [HumanMessage(content=prompt)]},
+            config=config
+        )
+    current_state = app.get_state(config)
+    # Get the messages from the current state
+    # and reverse the order
+    reversed_messages = current_state.values["messages"][::-1]
+    # Loop through the reversed messages
+    # until a ToolMessage is found.
+    tool_status_is_error = False
+    for msg in reversed_messages:
+        if isinstance(msg, ToolMessage):
+            # Skip until it finds a ToolMessage
+            if msg.name == "query_article" and msg.status == "error":
+                tool_status_is_error = True
+                break
+    assert tool_status_is_error

aiagents4pharma/talk2biomodels/tools/__init__.py

@@ -10,3 +10,4 @@ from . import parameter_scan
 from . import steady_state
 from . import load_biomodel
 from . import get_annotation
+from . import query_article

aiagents4pharma/talk2biomodels/tools/query_article.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python3
+
+"""
+Tool for asking questions to the article.
+"""
+
+import logging
+from typing import Type, Annotated
+from pydantic import BaseModel, Field
+from langchain_core.tools import BaseTool
+from langchain_core.vectorstores import InMemoryVectorStore
+from langchain_openai.embeddings import OpenAIEmbeddings
+from langchain_community.document_loaders import PyPDFLoader
+from langgraph.prebuilt import InjectedState
+
+# Initialize logger
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+class QueryArticleInput(BaseModel):
+    """
+    Input schema for the query_articles tool.
+    """
+    question: Annotated[str, Field(description="User question to search articles.")]
+    state: Annotated[dict, InjectedState]
+
+# Note: It's important that every field has type hints. BaseTool is a
+# Pydantic class and not having type hints can lead to unexpected behavior.
+class QueryArticle(BaseTool):
+    """
+    Tool to ask questions to the article.
+    """
+    name: str = "query_article"
+    description: str = "Ask questions to the article."
+    args_schema: Type[BaseModel] = QueryArticleInput
+
+    def _run(self,
+             question: str,
+             state: Annotated[dict, InjectedState]):
+        """
+        Run the tool.
+
+        Args:
+            query (str): The search query.
+        """
+        logger.log(logging.INFO, "loading the article from %s", state['pdf_file_name'])
+        logger.log(logging.INFO, "searching the article with the question: %s", question)
+        # Load the article
+        loader = PyPDFLoader(state['pdf_file_name'])
+        # Load the pages of the article
+        pages = []
+        for page in loader.lazy_load():
+            pages.append(page)
+        # Create a vector store from the pages
+        vector_store = InMemoryVectorStore.from_documents(pages, OpenAIEmbeddings())
+        # Search the article with the question
+        docs = vector_store.similarity_search(question)
+        # Return the content of the pages
+        return "\n".join([doc.page_content for doc in docs])

{aiagents4pharma-1.14.1.dist-info → aiagents4pharma-1.15.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: aiagents4pharma
-Version: 1.14.1
+Version: 1.15.1
 Summary: AI Agents for drug discovery, drug development, and other pharmaceutical R&D
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
@@ -29,6 +29,7 @@ Requires-Dist: pandas==2.2.3
 Requires-Dist: plotly==5.24.1
 Requires-Dist: pydantic==2.9.2
 Requires-Dist: pylint==3.3.1
+Requires-Dist: pypdf==5.2.0
 Requires-Dist: pytest==8.3.3
 Requires-Dist: pytest-asyncio==0.25.2
 Requires-Dist: streamlit==1.39.0

{aiagents4pharma-1.14.1.dist-info → aiagents4pharma-1.15.1.dist-info}/RECORD

@@ -4,12 +4,13 @@ aiagents4pharma/configs/config.yaml,sha256=4t7obD0gOSfqnDDZZBB53ZC7zsmk7QDcM7T_1
 aiagents4pharma/configs/talk2biomodels/__init__.py,sha256=safyFKhkd5Wlirl9dMZIHWDLTpY2oLw9wjIM7ZtLIHk,88
 aiagents4pharma/configs/talk2biomodels/agents/__init__.py,sha256=_ZoG8snICK2bidWtc2KOGs738LWg9_r66V9mOMnEb-E,71
 aiagents4pharma/configs/talk2biomodels/agents/t2b_agent/__init__.py,sha256=-fAORvyFmG2iSvFOFDixmt9OTQRR58y89uhhu2EgbA8,46
-aiagents4pharma/configs/talk2biomodels/agents/t2b_agent/default.yaml,sha256=w0ES09GSuY61x7C9FSx9auwhoGc6xVeG51roe6tT4Bk,317
+aiagents4pharma/configs/talk2biomodels/agents/t2b_agent/default.yaml,sha256=eLrJIezoPJ6_DvrSYsi3eALl03o0hJhntej3ESoeKKg,551
 aiagents4pharma/configs/talk2biomodels/tools/__init__.py,sha256=WxK7h5n39l-NSMvjLZyxDqzwWlVA6mQ69gzsbJ17vEk,72
 aiagents4pharma/configs/talk2biomodels/tools/ask_question/__init__.py,sha256=-fAORvyFmG2iSvFOFDixmt9OTQRR58y89uhhu2EgbA8,46
+aiagents4pharma/configs/talk2biomodels/tools/ask_question/default.yaml,sha256=yy-Sq1u4dBlTFi_UeoWYoHkWRDWueJWVNK_rcUCC5bw,1747
 aiagents4pharma/talk2biomodels/__init__.py,sha256=2ICwVh1u07SZv31Jd2DKHobauOxWNWY29_Gqq3kOnNQ,159
 aiagents4pharma/talk2biomodels/agents/__init__.py,sha256=sn5-fREjMdEvb-OUan3iOqrgYGjplNx3J8hYOaW0Po8,128
-aiagents4pharma/talk2biomodels/agents/t2b_agent.py,sha256=13aSlBZBWtjXOLq7c99u33c923fi2Ab0VW--eX5gF-o,3366
+aiagents4pharma/talk2biomodels/agents/t2b_agent.py,sha256=5h4n7dF13KuT5f9vzfK7EQTu_b0a0hB7ScLFlTKaNko,3449
 aiagents4pharma/talk2biomodels/api/__init__.py,sha256=_GmDQqDLYpsUPUeE1nBNlT5AI9oTXIcqgOfNfvmonqA,123
 aiagents4pharma/talk2biomodels/api/kegg.py,sha256=QzYDAfJ16E7tbHGxP8ZNWRizMkMRS_HJuucueXEC1Gg,2943
 aiagents4pharma/talk2biomodels/api/ols.py,sha256=qq0Qy-gJDxanQW-HfCChDsTQsY1M41ua8hMlTnfuzrA,2202
@@ -18,7 +19,7 @@ aiagents4pharma/talk2biomodels/models/__init__.py,sha256=5fTHHm3PVloYPNKXbgNlcPg
 aiagents4pharma/talk2biomodels/models/basico_model.py,sha256=PH25FTOuUjsmw_UUxoRb-4kptOYpicEn4GqS0phS3nk,4807
 aiagents4pharma/talk2biomodels/models/sys_bio_model.py,sha256=JeoiGQAvQABHnG0wKR2XBmmxqQdtgO6kxaLDUTUmr1s,2001
 aiagents4pharma/talk2biomodels/states/__init__.py,sha256=YLg1-N0D9qyRRLRqwqfLCLAqZYDtMVZTfI8Y0b_4tbA,139
-aiagents4pharma/talk2biomodels/states/state_talk2biomodels.py,sha256=WriIk_MH9XyUD-WAcIFVjHZMegwrh2-zQpXleTzpHEU,1332
+aiagents4pharma/talk2biomodels/states/state_talk2biomodels.py,sha256=d_tDh93ip36hlUpMh-KOkYfBZ2SQwZlaY8p-1ZWKPhY,1355
 aiagents4pharma/talk2biomodels/tests/__init__.py,sha256=Jbw5tJxSrjGoaK5IX3pJWDCNzhrVQ10lkYq2oQ_KQD8,45
 aiagents4pharma/talk2biomodels/tests/test_api.py,sha256=7Kz2r5F5tjmn3F0LoM33oP-21W633936YHiyf5toGg0,1716
 aiagents4pharma/talk2biomodels/tests/test_ask_question.py,sha256=yRkKK9HLB1bGGWm_WwOckwaUmmRfRAD9z2NFFGLIGTY,1560
@@ -27,11 +28,12 @@ aiagents4pharma/talk2biomodels/tests/test_get_annotation.py,sha256=mKOacH28OB6xp
 aiagents4pharma/talk2biomodels/tests/test_getmodelinfo.py,sha256=6kChSc_MCnzXlDao_R8pKdhIELlg3MZrUa7hg8piJ4E,883
 aiagents4pharma/talk2biomodels/tests/test_integration.py,sha256=ZsBXWSFLIcdzrO8obLJx8Ib2f9AAW3BI7H9Eqjdc5to,5057
 aiagents4pharma/talk2biomodels/tests/test_param_scan.py,sha256=vRbnn4uVWFbfZbU4gVCjHi5WDCUrErut8ElzAPE5y84,2648
+aiagents4pharma/talk2biomodels/tests/test_query_article.py,sha256=HhFgU5HzCipecEYlfbpPxN-SCIPKep22gpXCutWXRb8,2820
 aiagents4pharma/talk2biomodels/tests/test_search_models.py,sha256=8ODFubLxWYD3I3KQWuUnJ2GZRzMjFpXInFBLxKxG_ME,929
 aiagents4pharma/talk2biomodels/tests/test_simulate_model.py,sha256=GjLE1DZpcKUAFSmoHD86vkfK0b5LJPM8a4WYyraazig,1487
 aiagents4pharma/talk2biomodels/tests/test_steady_state.py,sha256=zt15KQoQku6jyzvpJXwINGTyhEnQl8wX81ueHlxnUCA,3467
 aiagents4pharma/talk2biomodels/tests/test_sys_bio_model.py,sha256=HSmBBViMi0jYf4gWX21IbppAfDzG0nr_S3KtKS9fZVQ,2165
-aiagents4pharma/talk2biomodels/tools/__init__.py,sha256=ZiOdSFaeHW6y3hdtBfsKf0vSb3MuCLuy9MDyjARggb4,322
+aiagents4pharma/talk2biomodels/tools/__init__.py,sha256=6H2HWv5Q4NZYEmw-Ti5KZnJlEqhaC2HXSDZa6kiSl-U,350
 aiagents4pharma/talk2biomodels/tools/ask_question.py,sha256=hWXg7o0sTMDWH1ZnxtashTALvXpvNoaomfcniEhw-Bw,4684
 aiagents4pharma/talk2biomodels/tools/custom_plotter.py,sha256=HWwKTX3o4dk0GcRVTO2hPrFSu98mtJ4TKC_hbHXOe1c,4018
 aiagents4pharma/talk2biomodels/tools/get_annotation.py,sha256=jCGkidvafuk1YzAH9GFwaVUF35maXTjg6XqBg_zLk44,12475
@@ -39,6 +41,7 @@ aiagents4pharma/talk2biomodels/tools/get_modelinfo.py,sha256=qA-4FOI-O728Nmn7s8J
 aiagents4pharma/talk2biomodels/tools/load_arguments.py,sha256=bffNIlBDTCSFYiZprA73yi8Jbb8z3Oh2decVNh1UnZc,4162
 aiagents4pharma/talk2biomodels/tools/load_biomodel.py,sha256=pyVzLQoMnuJYEwsjeOlqcUrbU1F1Z-pNlgkhFaoKpy0,689
 aiagents4pharma/talk2biomodels/tools/parameter_scan.py,sha256=aNh94LgBgVXBIczuNkbSsOZ9j54YVEdZWmZbZr7Nk8k,12465
+aiagents4pharma/talk2biomodels/tools/query_article.py,sha256=1tpYiE69MYcqiNcRaBgNiYzkkNmuTnlxLuBL_FnRuBU,2058
 aiagents4pharma/talk2biomodels/tools/search_models.py,sha256=Iq2ddofOOfZYtAurCISq3bAq5rbwB3l_rL1lgEFyFCI,2653
 aiagents4pharma/talk2biomodels/tools/simulate_model.py,sha256=qXs9lg9XgA7EaRiX3wBS8w_ug8tI-G3pzhcRg6dTRio,5060
 aiagents4pharma/talk2biomodels/tools/steady_state.py,sha256=j3ckuNlUtv7lT922MbN0JhT9H0JpWAdx2mLPwao6uu8,7123
@@ -93,8 +96,8 @@ aiagents4pharma/talk2knowledgegraphs/utils/embeddings/sentence_transformer.py,sh
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/__init__.py,sha256=tW426knki2DBIHcWyF_K04iMMdbpIn_e_TpPmTgz2dI,113
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/enrichments.py,sha256=Bx8x6zzk5614ApWB90N_iv4_Y_Uq0-KwUeBwYSdQMU4,924
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ollama.py,sha256=8eoxR-VHo0G7ReQIwje7xEhE-SJlHdef7_wJRpnvFIc,4116
-aiagents4pharma-1.14.1.dist-info/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
-aiagents4pharma-1.14.1.dist-info/METADATA,sha256=zwewL1DN0qEv3L7l901tNdc6PaX1wrKvRIkZ0dFIqHU,8609
-aiagents4pharma-1.14.1.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-aiagents4pharma-1.14.1.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
-aiagents4pharma-1.14.1.dist-info/RECORD,,
+aiagents4pharma-1.15.1.dist-info/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
+aiagents4pharma-1.15.1.dist-info/METADATA,sha256=J1AkLBxq9Pb1bo2tfkr8isyCozXB1aUi79jOlx6KDp8,8637
+aiagents4pharma-1.15.1.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+aiagents4pharma-1.15.1.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
+aiagents4pharma-1.15.1.dist-info/RECORD,,