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_SERVE_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-0.0.0b15.tar.gz
(18.9 kB
view hashes)
Built Distribution
Close
Hashes for scale_llm_engine-0.0.0b15.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3426800e8b096a93ec9e12ce7cf72eabdd53577f89a2647116057f92ac13bfb2 |
|
MD5 | 00e5f1e0496ad29d2ba4917403ac5b46 |
|
BLAKE2b-256 | db14dda3b056af47536166b8d430c96ed4f2ab4c444847dd2477995a8316506f |
Close
Hashes for scale_llm_engine-0.0.0b15-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3cb3557a787c7a17112dbf05917a1f73b4f922604e994622fcf58e994977e004 |
|
MD5 | fb1333d3904c8cec342b998c1df58db3 |
|
BLAKE2b-256 | 366f3d9eba5a853abec88a01575a45a8f2f373729c34f6f608442207430f16e9 |