OntoAligner is a Python library designed to simplify ontology alignment and matching for researchers, practitioners, and developers. With a modular architecture and robust features, OntoAligner provides powerful tools to bridge ontologies effectively.
You can install OntoAligner from PyPI using pip
:
pip install ontoaligner
Alternatively, to get the latest version directly from the source, use the following commands:
git clone [email protected]:sciknoworg/OntoAligner.git
pip install ./ontoaligner
Comprehensive documentation for OntoAligner, including detailed guides and examples, is available at ontoaligner.readthedocs.io.
Tutorials
Example | Tutorial | Script |
---|---|---|
Lightweight | 📚 Fuzzy Matching | 📝 Code |
Retrieval | 📚 Retrieval Aligner | 📝 Code |
Large Language Models | 📚 Large Language Models Aligner | 📝 Code |
Retrieval Augmented Generation | 📚 Retrieval Augmented Generation | 📝 Code |
FewShot | 📚 FewShot RAG | 📝 Code |
In-Context Vectors Learning | 📚 In-Context Vectors RAG | 📝 Code |
Below is an example of using Retrieval-Augmented Generation (RAG) step-by-step approach for ontology matching:
from ontoaligner.ontology import MaterialInformationMatOntoOMDataset
from ontoaligner.utils import metrics, xmlify
from ontoaligner.ontology_matchers import MistralLLMBERTRetrieverRAG
from ontoaligner.encoder import ConceptParentRAGEncoder
from ontoaligner.postprocess import rag_hybrid_postprocessor
# Step 1: Initialize the dataset object for MaterialInformation MatOnto dataset
task = MaterialInformationMatOntoOMDataset()
print("Test Task:", task)
# Step 2: Load source and target ontologies along with reference matchings
dataset = task.collect(
source_ontology_path="assets/MI-MatOnto/mi_ontology.xml",
target_ontology_path="assets/MI-MatOnto/matonto_ontology.xml",
reference_matching_path="assets/MI-MatOnto/matchings.xml"
)
# Step 3: Encode the source and target ontologies
encoder_model = ConceptParentRAGEncoder()
encoded_ontology = encoder_model(source=dataset['source'], target=dataset['target'])
# Step 4: Define configuration for retriever and LLM
retriever_config = {"device": 'cuda', "top_k": 5,}
llm_config = {"device": "cuda", "max_length": 300, "max_new_tokens": 10, "batch_size": 15}
# Step 5: Initialize Generate predictions using RAG-based ontology matcher
model = MistralLLMBERTRetrieverRAG(retriever_config=retriever_config, llm_config=llm_config)
predicts = model.generate(input_data=encoded_ontology)
# Step 6: Apply hybrid postprocessing
hybrid_matchings, hybrid_configs = rag_hybrid_postprocessor(predicts=predicts,
ir_score_threshold=0.1,
llm_confidence_th=0.8)
evaluation = metrics.evaluation_report(predicts=hybrid_matchings, references=dataset['reference'])
print("Hybrid Matching Evaluation Report:", evaluation)
# Step 7: Convert matchings to XML format and save the XML representation
xml_str = xmlify.xml_alignment_generator(matchings=hybrid_matchings)
open("matchings.xml", "w", encoding="utf-8").write(xml_str)
Ontology alignment pipeline using RAG method:
import ontoaligner
pipeline = ontoaligner.OntoAlignerPipeline(
task_class=ontoaligner.ontology.MouseHumanOMDataset,
source_ontology_path="assets/MI-MatOnto/mi_ontology.xml",
target_ontology_path="assets/MI-MatOnto/matonto_ontology.xml",
reference_matching_path="assets/MI-MatOnto/matchings.xml",
)
matchings, evaluation = pipeline(
method="rag",
encoder_model=ontoaligner.encoder.ConceptRAGEncoder(),
model_class=ontoaligner.ontology_matchers.MistralLLMBERTRetrieverRAG,
postprocessor=ontoaligner.postprocess.rag_hybrid_postprocessor,
llm_path='mistralai/Mistral-7B-v0.3',
retriever_path='all-MiniLM-L6-v2',
llm_threshold=0.5,
ir_threshold=0.7,
top_k=5,
max_length=512,
max_new_tokens=10,
device='cuda',
batch_size=32,
return_matching=True,
evaluate=True
)
print("Matching Evaluation Report:", evaluation)
We welcome contributions to enhance OntoAligner and make it even better! Please review our contribution guidelines in CONTRIBUTING.md before getting started. Your support is greatly appreciated.
If you encounter any issues or have questions, please submit them in the GitHub issues tracker.
If you use OntoAligner in your work or research, please cite the following:
@software{babaei_giglou_ontoaligner_2024,
author = {Hamed Babaei Giglou and Jennifer D'Souza and Oliver Karras and S{"o}ren Auer},
title = {OntoAligner: A Comprehensive Modular and Robust Python Toolkit for Ontology Alignment},
version = {1.0.0},
year = {2024},
url = {https://github.com/sciknoworg/OntoAligner},
}
This software is licensed under the Apache 2.0.