Skip to main content

pixano-inference-client (deprecated)

This distribution is a deprecated alias. The client and the wire schemas it used to hold are part of the base install of pixano-inference, which needs only httpx, pydantic and numpy: the server stack (ray[serve], fastapi, uvicorn) is behind the server extra, so an application that only calls a server never installs it.

pip install pixano-inference            # client and wire schemas, no server stack
pip install "pixano-inference[masks]"   # plus the mask codecs (Pillow, pycocotools)

Migrating

Replace the dependency and the imports. The classes are the same objects, so nothing else changes.

With pixano-inference-client With pixano-inference
pip install pixano-inference-client pip install pixano-inference
pip install pixano-inference-client[masks] pip install "pixano-inference[masks]"
from pixano_inference_client import SyncPixanoInferenceClient from pixano_inference.client import SyncPixanoInferenceClient
from pixano_inference_client import PixanoInferenceError from pixano_inference.client import PixanoInferenceError
from pixano_inference_client import DetectionRequest, NDArray … from pixano_inference.schemas import DetectionRequest, NDArray …
from pixano_inference_client.rle import CompressedRLE from pixano_inference.schemas.rle import CompressedRLE
from pixano_inference.client import SyncPixanoInferenceClient
from pixano_inference.schemas import DetectionRequest

client = SyncPixanoInferenceClient("http://localhost:7463", api_key="…")
det = client.detection(DetectionRequest(model="my-detector", image="https://example.com/cat.jpg"))
print(det.data.boxes, det.data.scores, det.data.classes)

What this version does

pixano-inference-client 0.2 depends on pixano-inference >= 0.7, < 0.8 and re-exports the same names as 0.1 (pixano_inference_client and its submodules), so existing imports keep working. Importing it emits a DeprecationWarning; a test suite that turns warnings into errors fails on that import until it is migrated.

Do not install pixano-inference-client 0.1 next to pixano-inference 0.7 or later: each would bring its own copy of the wire types, and an object built from one does not validate against the other. pixano-inference 0.6 keeps working with pixano-inference-client 0.1.

Metadata

Release files for pixano-inference-client 0.2.0

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

Source distribution (sdist)

Source distribution for pixano-inference-client 0.2.0
File Size Uploaded
pixano_inference_client-0.2.0.tar.gz 14.5 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for pixano-inference-client 0.2.0
File Interpreter ABI Platform
pixano_inference_client-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 38.3 kB

Release files / pixano_inference_client-0.2.0.tar.gz

Download URL pixano_inference_client-0.2.0.tar.gz
Size 14.5 kB
Tags Source
SHA-256 checksum
How to use checksums
1620cfef2b1efc2ec633134576705897189f744b2ef6e22b4c704f0266eff43e
BLAKE2b-256 checksum
How to use checksums
4e7ae613012bdd8dbe8eac6079e7761be43433e86c6e847020e9abeeb60988f1
Upload date
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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 6, 2026.

Transparency log

Release files / pixano_inference_client-0.2.0-py3-none-any.whl

Download URL pixano_inference_client-0.2.0-py3-none-any.whl
Size 23.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a6d9326df8949cc6ac7ff15ae7b2ddf3e850db8c4920b0dcba5fdc84437a9d22
BLAKE2b-256 checksum
How to use checksums
40a87c035aaa59865f33d2e8976aba3d3d107bd18c0fd006eda5f1492705ec35
Upload date
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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 6, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.2.0 This release

2 release files

0.1.0

2 release files

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