A lightweight library to support the development of applications using LLMs.
Project description
ralf is a Python library intended to assist developers in creating applications that involve calls to Large Language Models (LLMs). A core concept in ralf is the idea of composability, which allows chaining together LLM calls such that the output of one call can be used to form the prompt of another. ralf makes it easy to chain together both LLM-based and Python-based actions-- enabling developers to construct complex information processing pipelines composed of simpler building blocks. Using LLMs in this way can lead to more capable, robust, steerable and inspectable applications.
Currently, the ralf base library offers generic functionality for action chaining
(through the Dispatcher
and Action
classes) as well as text classificaiton
(through the ZeroShotClassifier
class). Check out the other projects within
the RALF ecosystem for more specialized functionality, like dialogue management
and information extraction.
Getting Started
First, clone the Github repository:
git clone https://gitlab.jhuapl.edu/ralf/ralf
Next, install the requirements using pip
:
pip install -r requirements.txt
Then, build the package using flit
and install it using pip
:
flit build
pip install .
Or if you would like an editable installation, you can instead use:
pip install -e .
Documentation & Tutorials
The best way to get started with ralf is to follow the tutorials in the [TODO] Documentation site. If you're eager to get started and want to skip the tutorials, you might instead consider checking out the dispatcher_demo.py
and classifier_demo.py
files in the demo/
directory.
License
[TODO]
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
Built Distribution
Hashes for ralf_jhuapl-0.0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | cc1341881319425d5d15be7ea1ac8c4d1cb0aa5b2d06afcf503873e23e62a5e0 |
|
MD5 | ec94deb97b4fbb1e260498d349cad788 |
|
BLAKE2b-256 | 46c4ac22d8e3c9bd751a809664a7dccfa6322884e6b03b7f5ac9fd720241ebbb |