|
|
--- |
|
|
license: mit |
|
|
title: Customer Experience Bot Demo |
|
|
sdk: gradio |
|
|
colorFrom: purple |
|
|
colorTo: green |
|
|
short_description: CX AI LLM |
|
|
--- |
|
|
title: Customer Experience Bot Demo emoji: 🤖 colorFrom: blue colorTo: purple sdk: gradio sdk_version: "4.44.0" app_file: app.py pinned: false |
|
|
|
|
|
Customer Experience Bot Demo |
|
|
|
|
|
A Retrieval-Augmented Generation (RAG) based customer experience (CX) bot deployed on Hugging Face Spaces (free tier). Demonstrates robust data cleanup and query validation to deliver high-quality, multilingual CX solutions for enterprise applications in SaaS, HealthTech, FinTech, and eCommerce. |
|
|
|
|
|
Features |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
RAG Pipeline: Retrieves FAQs using all-MiniLM-L6-v2 and FAISS for accurate, context-aware responses. |
|
|
|
|
|
|
|
|
|
|
|
Data Cleanup: Filters nulls, duplicates, and low-quality FAQs (e.g., short answers) to ensure reliable outputs. |
|
|
|
|
|
|
|
|
|
|
|
Performance Visualization: Displays latency and accuracy metrics with Matplotlib/Seaborn to monitor data quality. |
|
|
|
|
|
|
|
|
|
|
|
Gradio Interface: User-friendly UI for querying, viewing FAQs, and checking cleanup statistics. |
|
|
|
|
|
Setup |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Clone this repository to a Hugging Face Space (free tier, public). |
|
|
|
|
|
|
|
|
|
|
|
Create requirements.txt with the listed dependencies. |
|
|
|
|
|
|
|
|
|
|
|
Upload app.py (includes embedded sample FAQs for simplicity). |
|
|
|
|
|
|
|
|
|
|
|
Configure the Space to run with Python 3.9+ and no GPU. |
|
|
|
|
|
Usage |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Enter a query (e.g., “How do I reset my password?”) in the Gradio UI. |
|
|
|
|
|
|
|
|
|
|
|
View the bot’s response, retrieved FAQs, data cleanup statistics, and RAG pipeline plot. |
|
|
|
|
|
|
|
|
|
|
|
Example output: |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Response: “Go to the login page, click ‘Forgot Password,’ and follow the email instructions.” |
|
|
|
|
|
|
|
|
|
|
|
Cleanup Stats: “Cleaned FAQs: 3 (removed 2 junk entries)” |
|
|
|
|
|
Data Cleanup |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
FAQ Preprocessing: Removes nulls, duplicates, and answers shorter than 20 characters to ensure high-quality data. |
|
|
|
|
|
|
|
|
|
|
|
Query Validation: Rejects empty or overly short queries (<5 characters) for reliable input processing. |
|
|
|
|
|
|
|
|
|
|
|
Impact: Clean data is essential for accurate, scalable CX solutions, ensuring robust performance for enterprise Partners. |
|
|
|
|
|
Technical Details |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Stack: Python, Hugging Face (all-MiniLM-L6-v2), FAISS (CPU), Gradio, Pandas, Matplotlib, Seaborn. |
|
|
|
|
|
|
|
|
|
|
|
Free Tier Compatibility: Lightweight design with no GPU requirements, optimized for Hugging Face Spaces. |
|
|
|
|
|
|
|
|
|
|
|
Extensibility: Easily adaptable for CRM integrations (e.g., Salesforce) and cloud deployments (e.g., AWS Lambda). |
|
|
|
|
|
Purpose |
|
|
|
|
|
Developed to showcase expertise in designing, building, and deploying CX bots with a strong focus on data quality, tailored for AI-driven customer experience platforms. |
