sayou-brain

Overview

The Central Nervous System (Orchestrator) of Sayou Fabric.

sayou-brain acts as the Control Tower for the entire Sayou ecosystem. It provides high-level Pipeline Facades that abstract away the complexity of connecting individual modules (connector, document, chunking, etc.).

Instead of manually wiring components, you simply invoke a Pipeline, and the Brain handles routing, configuration propagation, and error handling.

1. Architecture & Role

The Brain sits between the User and the low-level modules. It directs data flow based on the chosen Pipeline strategy.

graph LR
    User -->|Invoke| Brain[Sayou Brain]
    
    subgraph Pipelines
        SP[StandardPipeline]
        NP[NormalPipeline]
    end
    
    Brain --> SP & NP
    
    SP -->|Layout Preserving| Doc[Document Parser]
    NP -->|Logic/Time Based| Chunk[Context Chunker]
    
    Doc & Chunk --> Wrap[Wrapper]
    Wrap --> Assem[Assembler]
    Assem --> Load[Loader]

1.1. Core Features

Facade Pattern: Users only interact with Pipeline.process(). No need to import sub-modules directly.
Config Propagation: A single config dictionary is distributed to all sub-modules.
Smart Routing: Automatically selects the optimal Connector based on the input source string.

2. Available Pipelines

Sayou Brain provides two distinct pipelines optimized for different data types.

Pipeline	Best For	Description
`StandardPipeline`	PDF, Office, HWP	Uses `sayou-document` to preserve spatial layout, headers, and tables. Maintains visual hierarchy.
`NormalPipeline`	Code, Video, Web	Bypasses layout parsing. Focuses on semantic logic (AST for code, Timeline for video).

3. Installation

Installing sayou-brain automatically installs all core dependencies and sub-modules.

pip install sayou-brain

4. Usage

Case A: StandardPipeline (Document-Centric)

Use this for documents where visual layout matters (e.g., Financial Reports, Papers).

from sayou.brain import StandardPipeline

result = StandardPipeline.process(
    source="./reports/financial_q1.pdf",
    destination="./examples/output/financial_graph.json"
)

print(f"Processed Nodes: {len(result['nodes'])}")

Case B: NormalPipeline (Logic-Centric)

Use this for structured data, code, or multimedia streams.

from sayou.brain import NormalPipeline

result = NormalPipeline.process(
    source="github://sayouzone/sayou-fabric",
    destination="./examples/output/code_graph.json",
    token="GITHUB_TOKEN",
    path="packages/sayou-connector/src/sayou/connector",
)

nodes = result.get("nodes", [])
edges = result.get("edges", [])

print(f"Total Nodes: {len(nodes)}")
print(f"Total Edges: {len(edges)}")

5. Configuration Keys

The following keys can be used in the config dictionary passed to the Pipeline:

connector: User-Agent, Timeout settings, Proxy config.
refinery: PII masking rules, Unicode normalization, Regex filters.
chunking: Strategy selection (Token/Line/Semantic), Size limits, Overlap.
loader: Database credentials, Output paths, File modes.

6. License

7. Plugin List

Plugin	Example	Description
`Normal Pipeline`	▶
`Bypass Pipeline`	▶
`Transfer Pipeline`	▶
`Standard Pipeline`	▶
`Structure Pipeline`	▶

Metadata

Release files for sayou-brain 0.5.2

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-brain 0.5.2
File	Size	Uploaded	Provenance
sayou_brain-0.5.2.tar.gz	33.3 kB	Apr 10, 2026	Without provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for sayou-brain 0.5.2
File	Interpreter	ABI	Platform	Reset
sayou_brain-0.5.2-py3-none-any.whl 21.4 kB Apr 10, 2026 Without provenance	Python 3	none	any	Details

Total release size: 54.7 kB

Release files / sayou_brain-0.5.2.tar.gz

Download URL	sayou_brain-0.5.2.tar.gz
Size	33.3 kB
Tags	Source
SHA-256 checksum How to use checksums	`9e609b0a8724e717a1a4c3420366a1bed20607132c5bada89fd4b4ab12ef6c60`
BLAKE2b-256 checksum How to use checksums	`0cd1f9296a4222284a7d3cbe029c50697c073758a029f9f1ff8a140733521b75`
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_brain-0.5.2-py3-none-any.whl

Download URL	sayou_brain-0.5.2-py3-none-any.whl
Size	21.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`d9bb9a9baad3cf43a3f96a3be17572ce5993378527e773718fcee0278b911451`
BLAKE2b-256 checksum How to use checksums	`43e1a6f3746fc0a008fff8afbbd5f1fb2f37617122b8d48eef17f55411e71c40`
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-brain 0.5.2

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.