quixio / template-llm-support

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

LLM-powered customer success dashboard

This template uses Quix and Llama 2 to create a Customer Success Dashboard with Sentiment Analysis.

Technologies used

Some of the technologies used by this template project are listed here.

Infrastructure:

Backend:

Frontend:

The project pipeline

This project consists of following applications:

  1. AI Customer: an LLM-powered chatbot simulating a customer requesting support regarding a defect of an appliance they bought from an electronics company.
  2. AI Customer Support Agent: an LLM-powered customer support agent trying to assist the AI Customer with a support request.
  3. Sentiment Analyzer: an application performing sentiment analysis on the conversation between the customer and the customer support agent.
  4. Redis Sink: an application that saves conversation history and the results of sentiment analysis to Redis.
  5. Streamlit Dashboard: a customer success dashboard displaying active conversations between customers and support agents and the results of sentiment analysis to gain insights into customer satisfaction and improve customer success and support efforts.

Prerequisites

To get started make sure you have a free Quix account.

If you are new to Quix it is worth reviewing the recent changes page, as that contains very useful information about the significant recent changes, and also has a number of useful videos you can watch to gain familiarity with Quix.

Git provider

You also need to have a Git account. This could be GitHub, Bitbucket, GitLab, or any other Git provider you are familar with, and that supports SSH keys. The simplest option is to create a free GitHub account.

While this project uses an external Git account, Quix can also provide a Quix-hosted Git solution using Gitea for your own projects. You can watch a video on how to create a project using Quix-hosted Git.

Tutorial

Check out our tutorials. A specific tutorial for this template is coming soon.

About


Languages

Language:Python 98.1%Language:Shell 0.8%Language:Batchfile 0.7%Language:CSS 0.3%