Sample Python Project for creating a new Python Module
Project description
cx-copilot
🤖 Empower your CX team with open-source AI-powered response auto-drafting. 🤖
🤔 What is cx-copilot?
An open source project that lets you leverage LLMs and latest advancements in AI to automate customer support interactions. By connecting a Large Language Model (LLM) to your knowledge base and historical support tickets via embeddings & vector searching, you can accurately auto-draft responses to all customer requests.
🖥 Where can it be used?
You can use cx-copilot to auto-draft responses in support tools like Helpscout, Intercom, Zendesk and anywhere else you store & respond to customer requests.
⚡️ Installation
- Go to extension directory.
$ cd ./client/chrome-extension/
- Download dependencies and perform initial project setup.
$ yarn
- Edit configuration inside
src/utils/config.js
.
const config = {};
config.API_URL = 'http://localhost:9000';
export default config;
- Run the project.
$ yarn start
- Load your extension on Chrome by doing the following:
- Go to
chrome://extensions/
- Enable
developer mode
- Click on
load unpacked extension
- Select the
build
folder
- Go to
🚀 Live Demo
📖 How does it work?
The basis of cx-copilot is embedding, vector storing and vector searching. Vector embeddings are a way to represent text as a series of numbers in such a way that you can perform mathematical operations, such as similarity comparison. By first embedding all previous historical customer request tickets using an embedding model (like text-embedding-ada-002 from OpenAI) and storing the embeddings & the paired response from your company in a vector database, you can then perform a vector search for incoming support tickets, returning the closest-matching tickets based on cosine similarity. The final step is to prompt a Large Language Model (LLM) with your team's responses to the closest-matching historical tickets, generating an auto-drafted response which will answer your customer’s query while conforming to your tone & formatting tendencies.
🔌 Integrations
Integrations | |
---|---|
Helpscout | |
Gmail | |
Intercom (coming soon) | |
Zendesk (coming soon) | |
Discord (coming soon) |
📱 Community
Join the Discord community for cx-copilot for support & project updates.
👩💻 Contributing
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
Built Distribution
Hashes for cx_copilot-0.0.9-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 915aaf5ff618089896d046d82c839ee1b48a2b6d46af28fac52a60e7ddd64cd0 |
|
MD5 | 25144fde4766b9911480bed5d40680d1 |
|
BLAKE2b-256 | 8baf5330a382a97a6fe549c6aff277a2aefc5452e4539294b80271da8a20fed0 |