Skip to main content

Perceptra Python SDK

Official Python SDK for the Perceptra Hub Computer Vision MLOps platform.

Installation

pip install perceptra

Quick Start

import perceptra

# Initialize with your API key
client = perceptra.Perceptra(api_key="ph_live_abc123...")

# Or set PERCEPTRA_API_KEY environment variable
client = perceptra.Perceptra()

# Create a project
project = client.projects.create(
    name="Hard Hat Detection",
    project_type_id=1,
)

# Upload images
from pathlib import Path
for path in Path("./images").glob("*.jpg"):
    client.images.upload(file=path, project_id=project.project_id)

# Add annotations
client.annotations.create(
    project_id=project.project_id,
    image_id="...",
    annotation_type="bbox",
    annotation_class_id=0,
    data=[0.1, 0.2, 0.5, 0.8],
)

# Split dataset
client.projects.split_dataset(project.project_id, 0.7, 0.2, 0.1)

# Create a dataset version
version = client.versions.create(project.project_id, "v1.0")

# Create and train a model
model = client.models.create(
    project_id=project.project_id,
    name="YOLOv8 Hard Hat",
    task="object-detection",
    framework="yolo",
)

result = client.models.train(
    model_id=model.id,
    dataset_version_id=version.id,
    config={"epochs": 100, "batch_size": 16},
)

# Stream training logs
for line in client.training.stream_logs(result.training_session_id):
    print(line, end="")

Async Support

import asyncio
import perceptra

async def main():
    async with perceptra.AsyncPerceptra(api_key="ph_live_abc123...") as client:
        projects = await client.projects.list()
        for p in projects:
            print(p["name"])

asyncio.run(main())

Error Handling

from perceptra import NotFoundError, RateLimitError, AuthenticationError

try:
    project = client.projects.retrieve("nonexistent-id")
except NotFoundError:
    print("Project not found")
except RateLimitError as e:
    print(f"Rate limited. Retry after {e.retry_after}s")
except AuthenticationError:
    print("Invalid API key")

Available Resources

Resource Description
client.projects Project CRUD, image management, dataset splitting
client.images Image upload, listing, bulk operations
client.annotations Annotation CRUD, batch operations
client.models ML model CRUD, training triggers
client.training Training session monitoring, log streaming
client.versions Dataset version management, export
client.organizations Organization details, members
client.jobs Annotation job management
client.classes Annotation class management
client.tags Image tag management
client.api_keys API key management, rotation
client.storage Storage profile management

Configuration

Parameter Default Environment Variable
api_key — PERCEPTRA_API_KEY
base_url http://localhost:29085 (the data API) PERCEPTRA_BASE_URL
timeout 30.0 —
max_retries 3 —

License

MIT

Metadata

Release files for perceptra 1.1.1

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

Source distribution (sdist)

Source distribution for perceptra 1.1.1
File Size Uploaded Provenance Actions
perceptra-1.1.1.tar.gz 21.5 kB Without provenance Details for perceptra-1.1.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for perceptra 1.1.1
File Interpreter ABI Platform Actions
perceptra-1.1.1-py3-none-any.whl Python 3 none any Details for perceptra-1.1.1-py3-none-any.whl

Total release size: 54.5 kB

Release files / perceptra-1.1.1.tar.gz

Download URL perceptra-1.1.1.tar.gz
Size 21.5 kB
Tags Source
SHA-256 checksum
How to use checksums
64964433d49621f4a2aabf159e8e1d6aeecd0362de84b120cc0fde2bf3896369
BLAKE2b-256 checksum
How to use checksums
d4c15d20338f211e4304ab7ca05ff0aa1d0154dd671ea3bf5f7f28b73e45cfe9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.3

Release files / perceptra-1.1.1-py3-none-any.whl

Download URL perceptra-1.1.1-py3-none-any.whl
Size 33.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
842b9545b8af78c8028540e86650ee8a2edde4900e287336127fb89f7e5656ba
BLAKE2b-256 checksum
How to use checksums
343ab3c9741cd135ccc4dc831245b6667cf4cef46a4fb438e0a76438b78a14fb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.3

Security for perceptra 1.1.1

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.

Release history Release notifications | RSS feed

This release

1.1.1 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page