AI-Parrot Pipelines

ai-parrot-pipelines provides planogram compliance and vision workflows for AI-Parrot agents.

Installation

pip install ai-parrot-pipelines

Install the optional local-OCR dependencies when needed:

pip install "ai-parrot-pipelines[planogram]"

Features

Planogram Compliance — a perceive → identify → compare cycle for six types
Layout Profiles — validated, per-type geometry and identification settings
Optional Local OCR — RapidOCR is auto-detected when the planogram extra is installed
Migration Utility — converts and preflights six planogram configuration types

Available Pipelines

Pipeline/type	Description
`PlanogramCompliance`	Planogram compliance pipeline
`ProductOnShelves`	Product-facing shelves
`InkWall`	Price-tag-anchored ink walls
`EndcapBacklitMultitier`	Multi-tier endcaps
`EndcapNoShelvesPromotional`	Zone-based promotional endcaps
`GraphicPanelDisplay`	Zone-only graphic panels
`ProductCounter`	Product and zone counters

Quick Start

from parrot_pipelines.planogram.plan import PlanogramCompliance
from parrot_pipelines.models import PlanogramConfig

config = PlanogramConfig(
    config_name="example",
    planogram_type="product_on_shelves",
    planogram_config={},
    slots_definition={
        "version": "1",
        "shelves": [
            {
                "shelf_id": "shelf_1",
                "shelf_number": 1,
                "facings": [
                    {
                        "facing_id": "facing_1",
                        "shelf_id": "shelf_1",
                        "slot": 1,
                        "product": "example_product",
                        "descriptors": {"display_name": "Example product"},
                    }
                ],
            }
        ],
        "zones": [],
    },
)

pipeline = PlanogramCompliance(planogram_config=config, llm="openai:gpt-4o-mini")
result = await pipeline.run("shelf_photo.jpg")

Provide a complete, validated slots definition and rule bindings before a production run. See the cycle reference and the migration runbook.

Dependencies

Python >= 3.11
ai-parrot >= 0.24.2
opencv-python-headless >= 4.8
Optional planogram extra: rapidocr and onnxruntime

1.1.0 breaking changes

The removed detector APIs and required configuration migration are documented in the migration runbook.

License

MIT

Metadata

Release files for ai-parrot-pipelines 1.3.2

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

Source distribution (sdist)

Source distribution for ai-parrot-pipelines 1.3.2
File	Size	Uploaded
ai_parrot_pipelines-1.3.2.tar.gz	138.8 kB	Oct 14, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for ai-parrot-pipelines 1.3.2
File	Interpreter	ABI	Platform	Reset
ai_parrot_pipelines-1.3.2-py3-none-any.whl 170.3 kB Oct 14, 2026	Python 3	none	any	Details

Total release size: 309.1 kB

Release files / ai_parrot_pipelines-1.3.2.tar.gz

Download URL	ai_parrot_pipelines-1.3.2.tar.gz
Size	138.8 kB
Tags	Source
SHA-256 checksum How to use checksums	`fa05b69e772f4280aadd443c6382ce9254e8eae731d7cb8c8e876c2cc091731b`
BLAKE2b-256 checksum How to use checksums	`ea5fbb12eda44e65d0191814439a761ad0659a8d7ce0d77ef33071e7ba16fcf6`
Upload date	Oct 14, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

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.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/phenobarbital/ai-parrot
Publishing commit: github.com/phenobarbital/ai-parrot/tree/994d9ae389936c3e1fcf30d9344b5d3b23ce2225

Workflow

Publishing configuration: github.com/phenobarbital/ai-parrot/blob/994d9ae389936c3e1fcf30d9344b5d3b23ce2225/.github/workflows/release.yml
Publishing logs: github.com/phenobarbital/ai-parrot/actions/runs/38490804737/attempts/1

Artifact

Subject: ai_parrot_pipelines-1.3.2.tar.gz
SHA-256 checksum: fa05b69e772f4280aadd443c6382ce9254e8eae731d7cb8c8e876c2cc091731b Verifying attestations

Release files / ai_parrot_pipelines-1.3.2-py3-none-any.whl

Download URL	ai_parrot_pipelines-1.3.2-py3-none-any.whl
Size	170.3 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`9cf4414c2a420d9b843c0d17cd783304145bdb9388eef13b67268662a4aa483f`
BLAKE2b-256 checksum How to use checksums	`8bcfe6ef35f60c418d90220795fbac8c9d07497b3598cdb0367123cda7e81275`
Upload date	Oct 14, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/phenobarbital/ai-parrot
Publishing commit: github.com/phenobarbital/ai-parrot/tree/994d9ae389936c3e1fcf30d9344b5d3b23ce2225

Workflow

Publishing configuration: github.com/phenobarbital/ai-parrot/blob/994d9ae389936c3e1fcf30d9344b5d3b23ce2225/.github/workflows/release.yml
Publishing logs: github.com/phenobarbital/ai-parrot/actions/runs/38490804737/attempts/1

Artifact

Subject: ai_parrot_pipelines-1.3.2-py3-none-any.whl
SHA-256 checksum: 9cf4414c2a420d9b843c0d17cd783304145bdb9388eef13b67268662a4aa483f Verifying attestations