nninteractive-client
Lightweight, torch-free remote client for nnInteractive.
Install this package if you only want to drive a remote nninteractive-server
(e.g. from a GUI, a thin client, or a host with its own torch policy such as 3D
Slicer). It pulls in only the wire dependencies (numpy, httpx, blosc2) —
no torch, no nnU-Net.
pip install nninteractive-client
from nnInteractive.inference.remote import nnInteractiveRemoteInferenceSession
import numpy as np
session = nnInteractiveRemoteInferenceSession("http://gpu-box:1527", api_key="…")
session.set_image(image_4d) # numpy, [C, X, Y, Z]
session.set_target_buffer(np.zeros(image_4d.shape[1:], dtype=np.uint8))
session.add_point_interaction([60, 70, 30], include_interaction=True)
The client exposes the same public API and capability attributes as the local
nnInteractiveInferenceSession, so it is a drop-in replacement. See
SERVER_CLIENT.md
for the full client/server guide.
Need local inference or the server?
Those live in the full package. Installing it gives you everything (it depends on this client):
pip install nnInteractive
If you try to use a full-only feature from a client-only install, you'll get a clear error pointing you here.
Release files for nninteractive-client 2.6.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| nninteractive_client-2.6.0.tar.gz | 25.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| nninteractive_client-2.6.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 51.2 kB
Release files / nninteractive_client-2.6.0.tar.gz
| Download URL | nninteractive_client-2.6.0.tar.gz |
|---|---|
| Size | 25.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e84bbc4983d3e3fc33b17562f964810e2063ae292cf583680be0a1127a9ed351
|
|
BLAKE2b-256 checksum How to use checksums |
d96efcb65fa5664a73cbc28b5dd26de86eb3eaf8d3032f64a4f02361647d7a1d
|
| 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 Sep 26, 2026.
Transparency logRelease files / nninteractive_client-2.6.0-py3-none-any.whl
| Download URL | nninteractive_client-2.6.0-py3-none-any.whl |
|---|---|
| Size | 25.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1186c30d1482c82884024c00b599a7ab0759a52b4a95b6e5850ade937f573af6
|
|
BLAKE2b-256 checksum How to use checksums |
98735dfc942b5bf7b172111a262db6cfe17122831f8c6143dbd1b9871256b1df
|
| 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 Sep 26, 2026.
Transparency log