LLMLink is a Python package that allows users to easily create LLM-powered Gradio applications
Project description
ChainLink
ChainLink is a Python SDK designed to simplify the creation of chatbot-based applications using Gradio. The SDK offers an efficient way to interact with Language Learning Models (LLMs) and deploy Gradio applications around these models.
Contents
Capabilities
ChainLink's capabilities are all focused around two classes - the Model
class and the App
class.
The Model
class implements the ability to talk to a specific LLM/chatbot, while the App
class implements the Gradio application around the specific Model
.
Installation
To install ChainLink, you can use pip to install directly from the GitHub repository:
pip install git+https://github.com/jacobrenn/chainlink
Quickstart/Usage
Here's a simple example of how you can use ChainLink to create an LLM-powered application, and then deploy it:
import chainlink.model as Model
import chainlink.app as App
model = Model(openai_api_key='<your OpenAI API key>', model='gpt-3.5-turbo', model_type='chat_openai', memory=True)
app = App(model, feedback=True)
app.deploy()
We are currently still working on building the implementation and documentation around ChainLink, so if you have any specific questions please feel free to reach out to us directly.
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
File details
Details for the file llmlink-0.0.2.tar.gz
.
File metadata
- Download URL: llmlink-0.0.2.tar.gz
- Upload date:
- Size: 8.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 06c1d91765df4fc8e94c11d4b5572769ff68884b8fd07feb81c87e3854d3a12d |
|
MD5 | 0259ccdcbcf7f3ece3c90003c28691e6 |
|
BLAKE2b-256 | b4fa7c0807994bbd2dd031bb4925a3deefab406484c50cc1a2d5001aeadbc97a |
File details
Details for the file llmlink-0.0.2-py3-none-any.whl
.
File metadata
- Download URL: llmlink-0.0.2-py3-none-any.whl
- Upload date:
- Size: 9.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 05561ff62133188e073f022828a7d85ac6519d083aafd20dfc3d044d371825b6 |
|
MD5 | f05636a5066d03c3a0fdb9ffaa4a7866 |
|
BLAKE2b-256 | d48df7eb1fa4c567eb581459cf12c8d66b2baeae18173445b48883f1e977387d |