Update README.md
Browse files
README.md
CHANGED
@@ -1,40 +1,107 @@
|
|
1 |
-
|
2 |
-
|
|
|
|
|
|
|
|
|
3 |
Features
|
4 |
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
|
10 |
Setup
|
11 |
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
Usage
|
18 |
|
|
|
|
|
|
|
|
|
19 |
Enter a query (e.g., “How do I reset my password?”) in the Gradio UI.
|
20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
Example output:
|
22 |
-
Response: “Go to the login page, click ‘Forgot Password,’...”
|
23 |
-
Cleanup Stats: “Cleaned FAQs: 3 (removed 2 junk entries)”
|
24 |
|
25 |
|
26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
Data Cleanup
|
28 |
|
29 |
-
|
30 |
-
|
31 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
|
33 |
Technical Details
|
34 |
|
|
|
|
|
|
|
|
|
35 |
Stack: Python, Hugging Face (all-MiniLM-L6-v2), FAISS (CPU), Gradio, Pandas, Matplotlib, Seaborn.
|
36 |
-
|
37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
|
39 |
Purpose
|
40 |
-
|
|
|
|
1 |
+
title: Customer Experience Bot Demo emoji: 🤖 colorFrom: blue colorTo: purple sdk: gradio sdk_version: "4.44.0" app_file: app.py pinned: false
|
2 |
+
|
3 |
+
Customer Experience Bot Demo
|
4 |
+
|
5 |
+
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.
|
6 |
+
|
7 |
Features
|
8 |
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
|
13 |
+
RAG Pipeline: Retrieves FAQs using all-MiniLM-L6-v2 and FAISS for accurate, context-aware responses.
|
14 |
+
|
15 |
+
|
16 |
+
|
17 |
+
Data Cleanup: Filters nulls, duplicates, and low-quality FAQs (e.g., short answers) to ensure reliable outputs.
|
18 |
+
|
19 |
+
|
20 |
+
|
21 |
+
Performance Visualization: Displays latency and accuracy metrics with Matplotlib/Seaborn to monitor data quality.
|
22 |
+
|
23 |
+
|
24 |
+
|
25 |
+
Gradio Interface: User-friendly UI for querying, viewing FAQs, and checking cleanup statistics.
|
26 |
|
27 |
Setup
|
28 |
|
29 |
+
|
30 |
+
|
31 |
+
|
32 |
+
|
33 |
+
Clone this repository to a Hugging Face Space (free tier, public).
|
34 |
+
|
35 |
+
|
36 |
+
|
37 |
+
Create requirements.txt with the listed dependencies.
|
38 |
+
|
39 |
+
|
40 |
+
|
41 |
+
Upload app.py (includes embedded sample FAQs for simplicity).
|
42 |
+
|
43 |
+
|
44 |
+
|
45 |
+
Configure the Space to run with Python 3.9+ and no GPU.
|
46 |
|
47 |
Usage
|
48 |
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
Enter a query (e.g., “How do I reset my password?”) in the Gradio UI.
|
54 |
+
|
55 |
+
|
56 |
+
|
57 |
+
View the bot’s response, retrieved FAQs, data cleanup statistics, and RAG pipeline plot.
|
58 |
+
|
59 |
+
|
60 |
+
|
61 |
Example output:
|
|
|
|
|
62 |
|
63 |
|
64 |
|
65 |
+
|
66 |
+
|
67 |
+
Response: “Go to the login page, click ‘Forgot Password,’ and follow the email instructions.”
|
68 |
+
|
69 |
+
|
70 |
+
|
71 |
+
Cleanup Stats: “Cleaned FAQs: 3 (removed 2 junk entries)”
|
72 |
+
|
73 |
Data Cleanup
|
74 |
|
75 |
+
|
76 |
+
|
77 |
+
|
78 |
+
|
79 |
+
FAQ Preprocessing: Removes nulls, duplicates, and answers shorter than 20 characters to ensure high-quality data.
|
80 |
+
|
81 |
+
|
82 |
+
|
83 |
+
Query Validation: Rejects empty or overly short queries (<5 characters) for reliable input processing.
|
84 |
+
|
85 |
+
|
86 |
+
|
87 |
+
Impact: Clean data is essential for accurate, scalable CX solutions, ensuring robust performance for enterprise Partners.
|
88 |
|
89 |
Technical Details
|
90 |
|
91 |
+
|
92 |
+
|
93 |
+
|
94 |
+
|
95 |
Stack: Python, Hugging Face (all-MiniLM-L6-v2), FAISS (CPU), Gradio, Pandas, Matplotlib, Seaborn.
|
96 |
+
|
97 |
+
|
98 |
+
|
99 |
+
Free Tier Compatibility: Lightweight design with no GPU requirements, optimized for Hugging Face Spaces.
|
100 |
+
|
101 |
+
|
102 |
+
|
103 |
+
Extensibility: Easily adaptable for CRM integrations (e.g., Salesforce) and cloud deployments (e.g., AWS Lambda).
|
104 |
|
105 |
Purpose
|
106 |
+
|
107 |
+
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.
|