aiagents4pharma 1.8.0__py3-none-any.whl → 1.15.0__py3-none-any.whl

aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_huggingface.py

@@ -0,0 +1,45 @@
+"""
+Test cases for utils/embeddings/huggingface.py
+"""
+
+import pytest
+from ..utils.embeddings.huggingface import EmbeddingWithHuggingFace
+
+@pytest.fixture(name="embedding_model")
+def embedding_model_fixture():
+    """Return the configuration object for the HuggingFace embedding model and model object"""
+    return EmbeddingWithHuggingFace(
+        model_name="NeuML/pubmedbert-base-embeddings",
+        model_cache_dir="../../cache",
+        truncation=True,
+    )
+
+def test_embedding_with_huggingface_embed_documents(embedding_model):
+    """Test embedding documents using the EmbeddingWithHuggingFace class."""
+    # Perform embedding
+    texts = ["Adalimumab", "Infliximab", "Vedolizumab"]
+    result = embedding_model.embed_documents(texts)
+    # Check the result
+    assert len(result) == 3
+    assert len(result[0]) == 768
+
+def test_embedding_with_huggingface_embed_query(embedding_model):
+    """Test embedding a query using the EmbeddingWithHuggingFace class."""
+    # Perform embedding
+    text = "Adalimumab"
+    result = embedding_model.embed_query(text)
+    # Check the result
+    assert len(result) == 768
+
+
+def test_embedding_with_huggingface_failed():
+    """Test embedding documents using the EmbeddingWithHuggingFace class."""
+    # Check if the model is available on HuggingFace Hub
+    model_name = "aiagents4pharma/embeddings"
+    err_msg = f"Model {model_name} is not available on HuggingFace Hub."
+    with pytest.raises(ValueError, match=err_msg):
+        EmbeddingWithHuggingFace(
+            model_name=model_name,
+            model_cache_dir="../../cache",
+            truncation=True,
+        )

aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_sentencetransformer.py

@@ -0,0 +1,40 @@
+"""
+Test cases for utils/embeddings/sentence_transformer.py
+"""
+
+import pytest
+import numpy as np
+from ..utils.embeddings.sentence_transformer import EmbeddingWithSentenceTransformer
+
+@pytest.fixture(name="embedding_model")
+def embedding_model_fixture():
+    """
+    Fixture for creating an instance of EmbeddingWithSentenceTransformer.
+    """
+    model_name = "sentence-transformers/all-MiniLM-L6-v1"  # Small model for testing
+    return EmbeddingWithSentenceTransformer(model_name=model_name)
+
+def test_embed_documents(embedding_model):
+    """
+    Test the embed_documents method of EmbeddingWithSentenceTransformer class.
+    """
+    # Perform embedding
+    texts = ["This is a test sentence.", "Another test sentence."]
+    embeddings = embedding_model.embed_documents(texts)
+    # Check the result
+    assert len(embeddings) == len(texts)
+    assert len(embeddings[0]) > 0
+    assert len(embeddings[0]) == 384
+    assert embeddings.dtype == np.float32
+
+def test_embed_query(embedding_model):
+    """
+    Test the embed_query method of EmbeddingWithSentenceTransformer class.
+    """
+    # Perform embedding
+    text = "This is a test query."
+    embedding = embedding_model.embed_query(text)
+    # Check the result
+    assert len(embedding) > 0
+    assert len(embedding) == 384
+    assert embedding.dtype == np.float32

aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_enrichments.py

@@ -0,0 +1,39 @@
+"""
+Test cases for utils/enrichments/enrichments.py
+"""
+
+from ..utils.enrichments.enrichments import Enrichments
+
+class TestEnrichments(Enrichments):
+    """Test implementation of the Enrichments interface for testing purposes."""
+
+    def enrich_documents(self, texts: list[str]) -> list[list[float]]:
+        return [
+            f"Additional text description of {text} as the input." for text in texts
+        ]
+
+    def enrich_documents_with_rag(self, texts, docs):
+        # Currently we don't have a RAG model to test this method.
+        # Thus, we will just call the enrich_documents method instead.
+        return self.enrich_documents(texts)
+
+def test_enrich_documents():
+    """Test enriching documents using the Enrichments interface."""
+    enrichments = TestEnrichments()
+    texts = ["text1", "text2"]
+    result = enrichments.enrich_documents(texts)
+    assert result == [
+        "Additional text description of text1 as the input.",
+        "Additional text description of text2 as the input.",
+    ]
+
+def test_enrich_documents_with_rag():
+    """Test enriching documents with RAG using the Enrichments interface."""
+    enrichments = TestEnrichments()
+    texts = ["text1", "text2"]
+    docs = ["doc1", "doc2"]
+    result = enrichments.enrich_documents_with_rag(texts, docs)
+    assert result == [
+        "Additional text description of text1 as the input.",
+        "Additional text description of text2 as the input.",
+    ]

aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_ollama.py

@@ -0,0 +1,117 @@
+"""
+Test cases for utils/enrichments/ollama.py
+"""
+
+import pytest
+import ollama
+from ..utils.enrichments.ollama import EnrichmentWithOllama
+
+@pytest.fixture(name="ollama_config")
+def fixture_ollama_config():
+    """Return a dictionary with Ollama configuration."""
+    return {
+        "model_name": "smollm2:360m",
+        "prompt_enrichment": """
+            Given the input as a list of strings, please return the list of addditional information of
+            each input terms using your prior knowledge.
+
+            Example:
+            Input: ['acetaminophen', 'aspirin']
+            Ouput: ['acetaminophen is a medication used to treat pain and fever', 
+            'aspirin is a medication used to treat pain, fever, and inflammation']
+            
+            Do not include any pretext as the output, only the list of strings enriched.
+
+            Input: {input}
+        """,
+        "temperature": 0.0,
+        "streaming": False,
+    }
+
+def test_no_model_ollama(ollama_config):
+    """Test the case when the Ollama model is not available."""
+    cfg = ollama_config
+    cfg_model = "smollm2:135m" # Choose a small model
+
+    # Delete the Ollama model
+    try:
+        ollama.delete(cfg_model)
+    except ollama.ResponseError:
+        pass
+
+    # Check if the model is available
+    with pytest.raises(
+        ValueError, match=f"Error: Pulled {cfg_model} model and restarted Ollama server."
+    ):
+        EnrichmentWithOllama(
+            model_name=cfg_model,
+            prompt_enrichment=cfg["prompt_enrichment"],
+            temperature=cfg["temperature"],
+            streaming=cfg["streaming"],
+        )
+    ollama.delete(cfg_model)
+
+def test_enrich_nodes_ollama(ollama_config):
+    """Test the Ollama textual enrichment class for node enrichment."""
+    # Prepare enrichment model
+    cfg = ollama_config
+    enr_model = EnrichmentWithOllama(
+        model_name=cfg["model_name"],
+        prompt_enrichment=cfg["prompt_enrichment"],
+        temperature=cfg["temperature"],
+        streaming=cfg["streaming"],
+    )
+
+    # Perform enrichment for nodes
+    nodes = ["Adalimumab", "Infliximab"]
+    enriched_nodes = enr_model.enrich_documents(nodes)
+    # Check the enriched nodes
+    assert len(enriched_nodes) == 2
+    assert all(
+        enriched_nodes[i] != nodes[i] for i in range(len(nodes))
+    )
+
+
+def test_enrich_relations_ollama(ollama_config):
+    """Test the Ollama textual enrichment class for relation enrichment."""
+    # Prepare enrichment model
+    cfg = ollama_config
+    enr_model = EnrichmentWithOllama(
+        model_name=cfg["model_name"],
+        prompt_enrichment=cfg["prompt_enrichment"],
+        temperature=cfg["temperature"],
+        streaming=cfg["streaming"],
+    )
+    # Perform enrichment for relations
+    relations = [
+        "IL23R-gene causation disease-inflammatory bowel diseases",
+        "NOD2-gene causation disease-inflammatory bowel diseases",
+    ]
+    enriched_relations = enr_model.enrich_documents(relations)
+    # Check the enriched relations
+    assert len(enriched_relations) == 2
+    assert all(
+        enriched_relations[i] != relations[i]
+        for i in range(len(relations))
+    )
+
+
+def test_enrich_ollama_rag(ollama_config):
+    """Test the Ollama textual enrichment class for enrichment with RAG (not implemented)."""
+    # Prepare enrichment model
+    cfg = ollama_config
+    enr_model = EnrichmentWithOllama(
+        model_name=cfg["model_name"],
+        prompt_enrichment=cfg["prompt_enrichment"],
+        temperature=cfg["temperature"],
+        streaming=cfg["streaming"],
+    )
+    # Perform enrichment for nodes
+    nodes = ["Adalimumab", "Infliximab"]
+    docs = [r"\path\to\doc1", r"\path\to\doc2"]
+    enriched_nodes = enr_model.enrich_documents_with_rag(nodes, docs)
+    # Check the enriched nodes
+    assert len(enriched_nodes) == 2
+    assert all(
+        enriched_nodes[i] != nodes[i] for i in range(len(nodes))
+    )

aiagents4pharma/talk2knowledgegraphs/utils/__init__.py

@@ -0,0 +1,5 @@
+'''
+This file is used to import utlities.
+'''
+from . import enrichments
+from . import embeddings

aiagents4pharma/talk2knowledgegraphs/utils/enrichments/__init__.py

@@ -0,0 +1,5 @@
+"""
+This package contains modules to use the enrichment model
+"""
+from . import enrichments
+from . import ollama

aiagents4pharma/talk2knowledgegraphs/utils/enrichments/enrichments.py

@@ -0,0 +1,36 @@
+"""
+Enrichments interface
+"""
+
+from abc import ABC, abstractmethod
+
+class Enrichments(ABC):
+    """Interface for enrichment models.
+
+    This is an interface meant for implementing text enrichment models.
+
+    Enrichment models are used to enrich node or relation features in a given knowledge graph.
+    """
+
+    @abstractmethod
+    def enrich_documents(self, texts: list[str]) -> list[list[str]]:
+        """Enrich documents.
+
+        Args:
+            texts: List of documents to enrich.
+
+        Returns:
+            List of enriched documents.
+        """
+
+    @abstractmethod
+    def enrich_documents_with_rag(self, texts: list[str], docs: list[str]) -> list[str]:
+        """Enrich documents with RAG.
+
+        Args:
+            texts: List of documents to enrich.
+            docs: List of reference documents to enrich the input texts.
+
+        Returns:
+            List of enriched documents with RAG.
+        """

aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ollama.py

@@ -0,0 +1,123 @@
+#!/usr/bin/env python3
+
+"""
+Enrichment class using Ollama model based on LangChain Enrichment class.
+"""
+
+import time
+from typing import List
+import subprocess
+import ast
+import ollama
+from langchain_ollama import ChatOllama
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.output_parsers import StrOutputParser
+from .enrichments import Enrichments
+
+class EnrichmentWithOllama(Enrichments):
+    """
+    Enrichment class using Ollama model based on the Enrichment abstract class.
+    """
+    def __init__(
+        self,
+        model_name: str,
+        prompt_enrichment: str,
+        temperature: float,
+        streaming: bool,
+    ):
+        """
+        Initialize the EnrichmentWithOllama class.
+
+        Args:
+            model_name: The name of the Ollama model to be used.
+            prompt_enrichment: The prompt enrichment template.
+            temperature: The temperature for the Ollama model.
+            streaming: The streaming flag for the Ollama model.
+        """
+        # Setup the Ollama server
+        self.__setup(model_name)
+
+        # Set parameters
+        self.model_name = model_name
+        self.prompt_enrichment = prompt_enrichment
+        self.temperature = temperature
+        self.streaming = streaming
+
+        # Prepare prompt template
+        self.prompt_template = ChatPromptTemplate.from_messages(
+            [
+                ("system", self.prompt_enrichment),
+                ("human", "{input}"),
+            ]
+        )
+
+        # Prepare model
+        self.model = ChatOllama(
+            model=self.model_name,
+            temperature=self.temperature,
+            streaming=self.streaming,
+        )
+
+    def __setup(self, model_name: str) -> None:
+        """
+        Check if the Ollama model is available and run the Ollama server if needed.
+
+        Args:
+            model_name: The name of the Ollama model to be used.
+        """
+        try:
+            models_list = ollama.list()["models"]
+            if model_name not in [m['model'].replace(":latest", "") for m in models_list]:
+                ollama.pull(model_name)
+                time.sleep(30)
+                raise ValueError(f"Pulled {model_name} model")
+        except Exception as e:
+            with subprocess.Popen(
+                "ollama serve", shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE
+            ):
+                time.sleep(10)
+            raise ValueError(f"Error: {e} and restarted Ollama server.") from e
+
+    def enrich_documents(self, texts: List[str]) -> List[str]:
+        """
+        Enrich a list of input texts with additional textual features using OLLAMA model.
+        Important: Make sure the input is a list of texts based on the defined prompt template
+        with 'input' as the variable name.
+
+        Args:
+            texts: The list of texts to be enriched.
+
+        Returns:
+            The list of enriched texts.
+        """
+
+        # Perform enrichment
+        chain = self.prompt_template | self.model | StrOutputParser()
+
+        # Generate the enriched node
+        # Important: Make sure the input is a list of texts based on the defined prompt template
+        # with 'input' as the variable name
+        enriched_texts = chain.invoke({"input": "[" + ", ".join(texts) + "]"})
+
+        # Convert the enriched nodes to a list of dictionary
+        enriched_texts = ast.literal_eval(enriched_texts.replace("```", ""))
+
+        # Final check for the enriched texts
+        assert len(enriched_texts) == len(texts)
+
+        return enriched_texts
+
+    def enrich_documents_with_rag(self, texts, docs):
+        """
+        Enrich a list of input texts with additional textual features using OLLAMA model with RAG.
+        As of now, we don't have a RAG model to test this method yet.
+        Thus, we will just call the enrich_documents method instead.
+
+        Args:
+            texts: The list of texts to be enriched.
+            docs: The list of reference documents to enrich the input texts.
+        
+        Returns:
+            The list of enriched texts
+        """
+        return self.enrich_documents(texts)

{aiagents4pharma-1.8.0.dist-info → aiagents4pharma-1.15.0.dist-info}/METADATA

@@ -1,11 +1,11 @@
 Metadata-Version: 2.2
 Name: aiagents4pharma
-Version: 1.8.0
+Version: 1.15.0
 Summary: AI Agents for drug discovery, drug development, and other pharmaceutical R&D
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.10
+Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: copasi_basico==0.78
@@ -17,16 +17,19 @@ Requires-Dist: hydra-core==1.3.2
 Requires-Dist: joblib==1.4.2
 Requires-Dist: langchain==0.3.7
 Requires-Dist: langchain-community==0.3.5
-Requires-Dist: langchain-core==0.3.15
+Requires-Dist: langchain-core==0.3.31
 Requires-Dist: langchain-experimental==0.3.3
 Requires-Dist: langchain-openai==0.2.5
-Requires-Dist: langgraph==0.2.62
+Requires-Dist: langchain_ollama==0.2.2
+Requires-Dist: langgraph==0.2.66
 Requires-Dist: matplotlib==3.9.2
 Requires-Dist: openai==1.59.4
+Requires-Dist: ollama==0.4.6
 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
@@ -48,6 +51,9 @@ Requires-Dist: streamlit-feedback
 [![Talk2Cells](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/tests_talk2cells.yml/badge.svg)](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/tests_talk2cells.yml)
 [![Talk2KnowledgeGraphs](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/tests_talk2knowledgegraphs.yml/badge.svg)](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/tests_talk2knowledgegraphs.yml)
 [![Talk2Competitors](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/tests_talk2competitors.yml/badge.svg)](https://github.com/VirtualPatientEngine/AIAgents4Pharma/actions/workflows/tests_talk2competitors.yml)
+![GitHub Release](https://img.shields.io/github/v/release/VirtualPatientEngine/AIAgents4Pharma)
+![Python Version from PEP 621 TOML](https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2FVirtualPatientEngine%2FAIAgents4Pharma%2Frefs%2Fheads%2Fmain%2Fpyproject.toml)
+
 
 <h1 align="center" style="border-bottom: none;">🤖 AIAgents4Pharma</h1>
 
@@ -56,9 +62,9 @@ Welcome to **AIAgents4Pharma** – an open-source project by [Team VPE](https://
 Our toolkit currently consists of three intelligent agents, each designed to simplify and enhance access to specialized data in biology:
 
 - **Talk2BioModels**: Engage directly with mathematical models in systems biology.
-- **Talk2Cells** *(Work in progress)*: Query and analyze sequencing data with ease.
-- **Talk2KnowledgeGraphs** *(Work in progress)*: Access and explore complex biological knowledge graphs for insightful data connections.
-- **Talk2Competitors** *(Coming soon)*: Get recommendations for articles related to your choice. Download, query, and write/retrieve them to your reference manager (currently supporting Zotero).
+- **Talk2Cells** _(Work in progress)_: Query and analyze sequencing data with ease.
+- **Talk2KnowledgeGraphs** _(Work in progress)_: Access and explore complex biological knowledge graphs for insightful data connections.
+- **Talk2Competitors** _(Coming soon)_: Get recommendations for articles related to your choice. Download, query, and write/retrieve them to your reference manager (currently supporting Zotero).
 
 ---
 
@@ -71,68 +77,77 @@ Our toolkit currently consists of three intelligent agents, each designed to sim
 - Forward simulation of both internal and open-source models (BioModels).
 - Adjust parameters within the model to simulate different conditions.
 - Query simulation results.
+- Extract model information such as species, parameters, units and description.
 
-### 2. Talk2Cells *(Work in Progress)*
+### 2. Talk2Cells _(Work in Progress)_
 
 **Talk2Cells** is being developed to provide direct access to and analysis of sequencing data, such as RNA-Seq or DNA-Seq, using natural language.
 
-### 3. Talk2KnowledgeGraphs *(Work in Progress)*
+### 3. Talk2KnowledgeGraphs _(Work in Progress)_
 
 **Talk2KnowledgeGraphs** is an agent designed to enable interaction with biological knowledge graphs (KGs). KGs integrate vast amounts of structured biological data into a format that highlights relationships between entities, such as proteins, genes, and diseases.
 
-### 4. Talk2KnowledgeGraphs *(Coming soon)*
+### 4. Talk2Competitors _(Coming soon)_
 
 ## Getting Started
 
-### Prerequisites
-
-- **Python 3.10+**
-- **Git**
-- Required libraries specified in `requirements.txt`
+![Python Version from PEP 621 TOML](https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2FVirtualPatientEngine%2FAIAgents4Pharma%2Frefs%2Fheads%2Fmain%2Fpyproject.toml)
 
 ### Installation
+
 #### Option 1: PyPI
-   ```bash
-   pip install aiagents4pharma
-   ```
+
+```bash
+pip install aiagents4pharma
+```
 
 Check out the tutorials on each agent for detailed instrcutions.
 
 #### Option 2: git
+
 1. **Clone the repository:**
+
    ```bash
    git clone https://github.com/VirtualPatientEngine/AIAgents4Pharma
    cd AIAgents4Pharma
    ```
 
 2. **Install dependencies:**
+
    ```bash
    pip install .
    ```
 
 3. **Initialize OPENAI_API_KEY**
+
    ```bash
-   export OPENAI_API_KEY = ....
+   export OPENAI_API_KEY=....
    ```
 
 4. **[Optional] Set up login credentials**
+
    ```bash
    vi .streamlit/secrets.toml
    ```
+
    and enter
+
    ```
    password='XXX'
    ```
-   Please note that the passowrd will be same for all the users.
+
+   Please note that the passoword will be same for all the users.
 
 5. **[Optional] Initialize LANGSMITH_API_KEY**
+
    ```bash
    export LANGCHAIN_TRACING_V2=true
    export LANGCHAIN_API_KEY=<your-api-key>
    ```
-   Please note that this will create a new tracing project in your Langsmith 
-   account with the name `<user_name>@<uuid>`, where `user_name` is the name 
-   you provided in the previous step. If you skip the previous step, it will 
+
+   Please note that this will create a new tracing project in your Langsmith
+   account with the name `<user_name>@<uuid>`, where `user_name` is the name
+   you provided in the previous step. If you skip the previous step, it will
    default to `default`. <uuid> will be the 128 bit unique ID created for the
    session.
 
@@ -164,6 +179,7 @@ We welcome contributions to AIAgents4Pharma! Here’s how you can help:
 5. **Open a pull request**
 
 ### Current Needs
+
 - **Beta testers** for Talk2BioModels.
 - **Developers** with experience in natural language processing, bioinformatics, or knowledge graphs for contributions to AIAgents4Pharma.
 
@@ -174,19 +190,22 @@ Check out our [CONTRIBUTING.md](CONTRIBUTING.md) for more information.
 ## Roadmap
 
 ### Completed
+
 - **Talk2BioModels**: Initial release with core capabilities for interacting with systems biology models.
 
 ### Planned
+
 - **User Interface**: Interactive web UI for all agents.
 - **Talk2Cells**: Integration of sequencing data analysis tools.
 - **Talk2KnowledgeGraphs**: Interface for biological knowledge graph interaction.
-- **Talk2Competitors**
+- **Talk2Competitors**: Interface for exploring articles
 
-We’re excited to bring AIAgents4Pharma to the bioinformatics and pharmaceutical research community. Together, let’s make data-driven biological research more accessible and insightful. 
+We’re excited to bring AIAgents4Pharma to the bioinformatics and pharmaceutical research community. Together, let’s make data-driven biological research more accessible and insightful.
 
 **Get Started** with AIAgents4Pharma today and transform the way you interact with biological data.
 
 ---
 
 ## Feedback
+
 Questions/Bug reports/Feature requests/Comments/Suggestions? We welcome all. Please use the `Isssues` tab 😀