kevinhug commited on
Commit
839da70
·
1 Parent(s): a288e30
Files changed (1) hide show
  1. app.py +28 -19
app.py CHANGED
@@ -10,33 +10,42 @@ db = client.get_collection(name="banks")
10
 
11
 
12
 
13
- def greet(issue):
14
  global db
15
  docs = db.query(query_texts=issue, n_results=5)
16
  return docs
17
 
18
 
19
 
20
- iface = gr.Interface(fn=greet, inputs="text", outputs="text", title="NLP Leads Generation", description="""
21
  Data Scientist: Kevin Wong
 
 
 
 
22
  Using Sentence Embedding to inject Public ML Banks Text Dataset @ https://github.com/kevinwkc/analytics/blob/master/ai/vectorDB.py""",
23
- article="""
24
- put in the issue regarding service, sales, point of failure, product, trend to find out what customer talking about
25
-
26
- Client Experience
27
- ----------
28
- - having bad client experience
29
- - having credit card problem
30
- - late payment fee
31
- - credit score dropping
32
-
33
- Marketing Leads
34
- ----------
35
- - low interest credit card
36
-
37
- Sentiments
38
- ---------
39
- - upset customer
 
 
 
 
 
40
 
41
  """)
42
  iface.launch()
 
10
 
11
 
12
 
13
+ def similar(issue):
14
  global db
15
  docs = db.query(query_texts=issue, n_results=5)
16
  return docs
17
 
18
 
19
 
20
+ iface = gr.Interface(fn=similar, inputs="text", outputs="text", title="NLP Leads Generation", description="""
21
  Data Scientist: Kevin Wong
22
+ ============
23
+ open source ml bank dataset
24
+ https://www.kaggle.com/datasets/trainingdatapro/20000-customers-reviews-on-banks/?select=Banks.csv
25
+
26
  Using Sentence Embedding to inject Public ML Banks Text Dataset @ https://github.com/kevinwkc/analytics/blob/master/ai/vectorDB.py""",
27
+ article="""
28
+
29
+ Description:
30
+ =======
31
+ In today's dynamic financial landscape, the Semantic Similarity Document Search (SSDS) capability is a practical innovation to improve client experience, marketing leads, and sentiment analysis. As a Data Scientist with a decades in the financial industry, I see the value of SSDS in action.
32
+
33
+ Client Experience:
34
+ ------
35
+ When a client faces a bad experience, SSDS helps us swiftly locate relevant documents to understand and address their concerns, be it credit card issues, late payment fees, or credit score drops.
36
+
37
+ Marketing Leads:
38
+ ------
39
+ To enhance marketing strategies, SSDS identifies market trends and consumer preferences, such as the demand for low-interest credit cards. It's a treasure trove for refining our product offerings.
40
+
41
+ Sentiments:
42
+ ------
43
+ SSDS tracks customer sentiment, empowering us to swiftly respond to upset customers. It ensures we address their issues promptly, enhancing trust and loyalty.
44
+ With no need for jargon, SSDS delivers tangible value to our fintech operations. It's about staying agile, informed, and customer-centric in a rapidly changing financial world.
45
+
46
+ Future Improvement
47
+ ============
48
+ tuning the distance for use case
49
 
50
  """)
51
  iface.launch()