sayou-wrapper 0.1.5

Wrapper components for the Sayou Data Platform

sayou-wrapper

The Ontology Mapper for Sayou Fabric.

sayou-wrapper takes the fragmented chunks produced by sayou-chunking and wraps them into a standardized graph structure (SayouNode). This is the final preparation step before data is assembled into a Knowledge Graph or loaded into a Vector DB.

It applies the Sayou Ontology Schema (Namespace -> Class -> Predicate) to raw data, turning simple text into semantically rich entities.

💡 Core Philosophy

"From Data to Knowledge."

While Chunking slices the data, Wrapper gives it meaning.

• It assigns Ontology Classes (e.g., sayou:Topic, sayou:Table) based on metadata.
• It defines Relationships (e.g., sayou:hasParent) to preserve context.
• It normalizes IDs into URIs (e.g., sayou:doc:123) for global uniqueness.

📦 Installation

pip install sayou-wrapper

⚡ Quick Start

from sayou.wrapper.pipeline import WrapperPipeline

def run_demo():
    # 1. Initialize
    pipeline = WrapperPipeline()
    pipeline.initialize()

    # 2. Input Data (Simulated output from sayou-chunking)
    chunks = [
        {
            "chunk_content": "# Introduction",
            "metadata": {
                "chunk_id": "h_1", 
                "semantic_type": "heading", 
                "is_header": True
            }
        },
        {
            "chunk_content": "Sayou is great.",
            "metadata": {
                "chunk_id": "p_1", 
                "parent_id": "h_1",
                "semantic_type": "text"
            }
        }
    ]

    # 3. Run Wrapper
    output = pipeline.run(chunks, strategy="document_chunk")

    # 4. Result (SayouNodes)
    for node in output.nodes:
        print(f"[{node.node_class}] {node.node_id}")
        print(f"   Attrs: {node.attributes}")
        print(f"   Rels : {node.relationships}")

if __name__ == "__main__":
    run_demo()

🔑 Key Components

Adapters

• DocumentChunkAdapter: The standard adapter. Converts document chunks into sayou:Topic, sayou:TextFragment, etc., and links them via sayou:hasParent.

Schema (Sayouzone Standard)

• SayouNode: The atomic unit of the Knowledge Graph. Contains ID, Class, Attributes, and Relationships.
• WrapperOutput: A container holding a list of nodes and global metadata.

🤝 Contributing

We welcome adapters for other data sources (e.g., SqlRecordAdapter, LogAdapter).

📜 License

Apache 2.0 License © 2025 Sayouzone