Scale LLM Engine Python client
Project description
LLM Engine
The LLM Engine Python library provides a convenient way of interfacing with a
llmengine
endpoint running on
LLM Engine or on your own infrastructure.
Get Started
Install
pip install scale-llm-engine
Usage
If you are using LLM Engine, you can get your API key from
https://spellbook.scale.com/settings.
Set the SCALE_API_KEY
environment variable to your API key.
If you are using your own infrastructure, you can set the
LLM_ENGINE_BASE_PATH
environment variable to the base URL of your
self-hosted llmengine
endpoint.
from llmengine import Completion
response = Completion.create(
model="llama-2-7b",
prompt="Hello, my name is",
max_new_tokens=10,
temperature=0.2,
)
print(response.outputs[0].text)
Documentation
Documentation is available at https://scaleapi.github.io/llm-engine/.
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
scale_llm_engine-0.0.0b27.tar.gz
(22.2 kB
view hashes)
Built Distribution
Close
Hashes for scale_llm_engine-0.0.0b27.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | edcec2e1abe1fdc44c7d68b09097771c406bbfe327764330a215d6950acbd13e |
|
MD5 | ed33f0cd24f2934d8391d0eefc8bb21f |
|
BLAKE2b-256 | 240c53b5001a7ab326a840b0753fb85f4403e8e81bbfebdf7411d5bd841bbd3d |
Close
Hashes for scale_llm_engine-0.0.0b27-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b5df57c45fd90653865cf9c2f43ecfd429e6e91c78f013685de0112151612894 |
|
MD5 | b8e52f4a71a983b5402c0a47cc3c0e8f |
|
BLAKE2b-256 | 181d853516bb20c9ea9d0fa57714afc2b60955cd4f3cd1e9b88552757e435687 |