Skip to main content

portweights

Deploy a LoRA adapter as a private, OpenAI-compatible API on Portweights. Python 3.9+. Only dependency: certifi (root certificates, for Pythons that ship without them).

pip install portweights
portweights login                                   # token from https://portweights.com/app/tokens
portweights deploy ./my-adapter --name "Triage"     # adapter_config.json + adapter_model.safetensors
portweights deploy --hf owner/repo                  # or import from Hugging Face
portweights deploy ./my-adapter --region eu         # run it in India (in, default), the US (us) or Europe (eu)
portweights list
portweights key <deployment> --rotate
portweights balance

deploy uploads, waits until the adapter is serving, and prints the base URL, model ID and a new API key (shown once). Call it with any OpenAI SDK.

As a library:

from portweights import Client
pw = Client()                       # PORTWEIGHTS_TOKEN, or the token saved by `portweights login`
d = pw.deploy("./my-adapter", name="Triage")
key = pw.create_key(d["id"])

Metadata

Release files for portweights 0.1.1

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

Source distribution (sdist)

Source distribution for portweights 0.1.1
File Size Uploaded Provenance Actions
portweights-0.1.1.tar.gz 6.3 kB Without provenance Details for portweights-0.1.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for portweights 0.1.1
File Interpreter ABI Platform Actions
portweights-0.1.1-py3-none-any.whl Python 3 none any Details for portweights-0.1.1-py3-none-any.whl

Total release size: 14.4 kB

Release files / portweights-0.1.1.tar.gz

Download URL portweights-0.1.1.tar.gz
Size 6.3 kB
Tags Source
SHA-256 checksum
How to use checksums
d893df4088d719e15461d383a226814236caf5162a194b0055197096e7c0b009
BLAKE2b-256 checksum
How to use checksums
81a3840be06d531974bc1c2639df45c1ef92a2d442b9bbf180da89699ab8d627
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.9.0

Release files / portweights-0.1.1-py3-none-any.whl

Download URL portweights-0.1.1-py3-none-any.whl
Size 8.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
1cd97615798fbf60b70fc42e4862f07c771322b1a84156c3e5ea3c0e5eb2eb56
BLAKE2b-256 checksum
How to use checksums
c0497f252cde29d513686d90cab7cfe6bd0012f2303ae6cd13f1b78abd5f79fc
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.9.0

Security for portweights 0.1.1

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

0.1.1 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