Skip to main content

Wrapper components for the Sayou Data Platform

Project description

sayou-wrapper

PyPI version License Docs

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 = [
        {
            "content": "# Introduction",
            "metadata": {
                "chunk_id": "h_1", 
                "semantic_type": "heading", 
                "is_header": True
            }
        },
        {
            "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

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sayou_wrapper-0.3.5.tar.gz (18.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sayou_wrapper-0.3.5-py3-none-any.whl (17.5 kB view details)

Uploaded Python 3

File details

Details for the file sayou_wrapper-0.3.5.tar.gz.

File metadata

  • Download URL: sayou_wrapper-0.3.5.tar.gz
  • Upload date:
  • Size: 18.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for sayou_wrapper-0.3.5.tar.gz
Algorithm Hash digest
SHA256 48f362e8cf88d26563fda2c23db565c5ffca6ae1e1869d981f0be1754496c328
MD5 c4fa611de19ab170bf183d111efce7f2
BLAKE2b-256 f9fa19e28c9ffda816c074dcafe8bc07f6def9b7038ce86487e4c2abdb9e4ea0

See more details on using hashes here.

File details

Details for the file sayou_wrapper-0.3.5-py3-none-any.whl.

File metadata

  • Download URL: sayou_wrapper-0.3.5-py3-none-any.whl
  • Upload date:
  • Size: 17.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for sayou_wrapper-0.3.5-py3-none-any.whl
Algorithm Hash digest
SHA256 286bccdde14c6b08b33d7d4a1d98267e121448acbff05d898b3fc478e27546d8
MD5 28bbc277aab22641fc4f7c526ad9240d
BLAKE2b-256 aec7674554e13ef77b050b7c461e4f8b7fc20f5e5657e4560dcc48c423aef526

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page