sayou-wrapper

Overview

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.

1. Architecture & Role

The Wrapper sits between Chunking and Assembly. It transforms raw dictionaries (Chunks) into standardized Objects (Nodes) with globally unique URIs.

graph LR
    Chunks[Raw Chunks] --> Pipeline[Wrapper Pipeline]
    
    subgraph Logic
        Schema[Schema Mapping]
        URI[URI Generation]
        Attr[Attribute Norm]
    end
    
    Pipeline --> Logic
    Logic --> Nodes[SayouNodes]

1.1. Core Features

Ontology Enforcement: Assigns strict classes (e.g., sayou:Topic, sayou:Function) based on chunk metadata.
URI Normalization: Generates idempotent IDs (e.g., sayou:doc:hash_123) to prevent duplication.
Metadata Preservation: Carries over source coordinates (page numbers, line numbers) into node attributes.

2. Available Strategies

sayou-wrapper applies different mapping rules based on the source domain.

Strategy Key	Target Domain	Description
`document_chunk`	PDF, Markdown	Maps headers to `sayou:Topic` and text to `sayou:TextFragment`. Preserves hierarchy metadata.
`code_chunk`	Python, Java	Maps AST objects to `sayou:Class`, `sayou:Function`, or `sayou:Module`.
`video_chunk`	YouTube, MP4	Maps timestamps to `sayou:VideoSegment`. Preserves start/end times.
`general`	Plain Text	[Default] Treats everything as generic `sayou:Unstructured` nodes.

3. Installation

pip install sayou-wrapper

4. Usage

The WrapperPipeline converts a list of dictionaries (Chunks) into a WrapperOutput object containing nodes.

Case A: Document Processing (Default)

Converts hierarchical chunks into Topic and Fragment nodes.

from sayou.wrapper import WrapperPipeline

chunks = [
    {
        "content": "# Introduction",
        "metadata": {
            "chunk_id": "h_1", 
            "semantic_type": "heading", 
            "depth": 1
        }
    },
    {
        "content": "Sayou is great.",
        "metadata": {
            "chunk_id": "p_1", 
            "parent_id": "h_1",
            "semantic_type": "text"
        }
    }
]

result = WrapperPipeline.process(
    data=chunks,
    strategy="document_chunk"
)

for node in result.nodes:
    print(f"[{node.node_class}] {node.node_id}")

Case B: Code Processing

Converts AST-based chunks into structural code nodes.

from sayou.wrapper import WrapperPipeline

code_chunks = [
    {
        "content": "def my_func(): pass",
        "metadata": {"type": "function", "name": "my_func"}
    }
]

result = WrapperPipeline.process(
    data=code_chunks,
    strategy="code_chunk"
)

print(f"Node Class: {result.nodes[0].node_class}")

5. Configuration Keys

The config dictionary controls how IDs are generated and which schema strictness to apply.

namespace: The prefix for URIs (default: sayou:).
id_strategy: hash (deterministic) or uuid (random).
strict_mode: If True, raises error for unknown semantic types.
attribute_filter: List of metadata keys to exclude from the final Node attributes.

6. License

7. Plugin List

Plugin	Example	Description
`Code Chunk Wrapper`	▶
`Document Chunk Wrapper`	▶
`Video Chunk Wrapper`	▶
`Embedding Wrapper`	▶
`Metatdata Wrapper`	▶

Metadata

Release files for sayou-wrapper 0.5.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for sayou-wrapper 0.5.1
File	Size	Uploaded	Provenance
sayou_wrapper-0.5.1.tar.gz	41.2 kB	Apr 10, 2026	Without provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for sayou-wrapper 0.5.1
File	Interpreter	ABI	Platform	Reset
sayou_wrapper-0.5.1-py3-none-any.whl 20.7 kB Apr 10, 2026 Without provenance	Python 3	none	any	Details

Total release size: 62.0 kB

Release files / sayou_wrapper-0.5.1.tar.gz

Download URL	sayou_wrapper-0.5.1.tar.gz
Size	41.2 kB
Tags	Source
SHA-256 checksum How to use checksums	`44fad919e9849c27891cfafa9a25d2a3c2b15110bb5985ef3864b6e7d8074585`
BLAKE2b-256 checksum How to use checksums	`9a65829ff82f07f8c4ba66169ff44aec94667c0663528c980f3d0b8ff1e8f833`
Upload date	Apr 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.1.0 CPython/3.13.12`

Release files / sayou_wrapper-0.5.1-py3-none-any.whl

Download URL	sayou_wrapper-0.5.1-py3-none-any.whl
Size	20.7 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`a86045d84ad0e43a9a2663d613918ad5042ba94db45e2f9682287656c443c622`
BLAKE2b-256 checksum How to use checksums	`258bee1336dc7550877b87a9e0fdf0bba7aabddf7462de34f249edad12dafa17`
Upload date	Apr 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.1.0 CPython/3.13.12`

Security for sayou-wrapper 0.5.1

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.