Skip to main content

NxLook Inference library for Epistemic AI models. Non-reverse-engineerable, inference-only.

Project description

NxLook Epistemic AI Inference Library

Inference-only Python library for Epistemic AI trained models. No training, no reverse engineering.

Installation

pip install nxlook-client

Usage

Non-interactive Inference

from nxlook_client import non_interactive_inference

response = non_interactive_inference(
    model_path="path/to/your/model.pth",
    prompt="What is the meaning of life?"
)
print(response)

##Interactive Chat Mode

from nxlook_client import interactive_inference

interactive_inference("path/to/your/model.pth", temperature=0.6)
Unified inference() Function
from epistemic_infer import inference

# Non-interactive
response = inference("model.pth", prompt="Hello world")

# Interactive
inference("model.pth", interactive=True)

#Requirements Python 3.8+ PyTorch 2.0+

#License MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nxlook_client-0.1.0.tar.gz (6.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nxlook_client-0.1.0-py3-none-any.whl (6.9 kB view details)

Uploaded Python 3

File details

Details for the file nxlook_client-0.1.0.tar.gz.

File metadata

  • Download URL: nxlook_client-0.1.0.tar.gz
  • Upload date:
  • Size: 6.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for nxlook_client-0.1.0.tar.gz
Algorithm Hash digest
SHA256 7d4fc3f4451bd46c588d214b83137852f2cabcc36334cd2973ba2254ae416494
MD5 e17910e23ade6531cd58a78a143d60ee
BLAKE2b-256 84780d6e6f84e70d87ae44a8f75a19de9238d9ee51f423c6ebe00838cbe08e81

See more details on using hashes here.

File details

Details for the file nxlook_client-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: nxlook_client-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 6.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for nxlook_client-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 783d6f2493d212647b9fcdbaad770a652f714c0893a99543dabde06269387dae
MD5 9d371ef87f27cac57fe4ce0a622d5f1e
BLAKE2b-256 4f19829db8da71d90983192fbb4fb368731b26607ae1e8bdfd777f7b703c14f0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page