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
Release history Release notifications | RSS feed
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-0.1.1.tar.gz
(6.0 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file nxlook_client-0.1.1.tar.gz.
File metadata
- Download URL: nxlook_client-0.1.1.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
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1cf447ef32640e2f2a19a9c0e906f1cff268def66deb0dea9b13a43c2064dd63
|
|
| MD5 |
83879c2e36ebfcb0b624fb728825f9ff
|
|
| BLAKE2b-256 |
5b079a8db76c35d505b5d077e6a8b994918bb898ae807798debf8768a164ac23
|
File details
Details for the file nxlook_client-0.1.1-py3-none-any.whl.
File metadata
- Download URL: nxlook_client-0.1.1-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
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
85ad96d3df8f079f9991a1949d2fb20128407794767fc1ca8c526e927f244a9d
|
|
| MD5 |
920de77230c0ccfb4260ba9c45e7571a
|
|
| BLAKE2b-256 |
5ca9b5804d3cfdf8c26d4700ce9420fbdcfb761e9c39fceb282c467ad21348dc
|