kevinhug commited on
Commit
c7afca9
·
1 Parent(s): 4c3d0df
Files changed (1) hide show
  1. app.py +73 -71
app.py CHANGED
@@ -1,12 +1,13 @@
1
  import gradio as gr
2
- from rag import rbc_product
3
- from tool import rival_product
4
- from graphrag import marketingPlan
5
- from knowledge import graph
6
- from pii import derisk
7
  from classify import judge
8
  from entity import resolve
 
9
  from human import email, feedback
 
 
 
 
10
 
11
  # Define the Google Analytics script
12
  head = """
@@ -94,11 +95,12 @@ Other Links:
94
 
95
  gr.Examples(
96
  [
97
- ["Low APR and great customer service. I would highly recommend if you’re looking for a great credit card company and looking to rebuild your credit. I have had my credit limit increased annually and the annual fee is very low."]
 
98
  ],
99
  [in_verbatim]
100
  )
101
- btn_recommend=gr.Button("Recommend")
102
  btn_recommend.click(fn=rival_product, inputs=in_verbatim, outputs=out_product)
103
 
104
  gr.Markdown("""
@@ -254,7 +256,7 @@ Representative: "Confirmed. Your next payment of $200 will process May 1st. A co
254
 
255
  Customer: "No, thank you."
256
  """
257
- ]
258
  ],
259
  [in_verbatim]
260
  )
@@ -262,7 +264,6 @@ Customer: "No, thank you."
262
  btn_clear = gr.ClearButton(components=[out_product])
263
  btn_recommend.click(fn=graph, inputs=[in_verbatim, out_product], outputs=out_product)
264
 
265
-
266
  gr.Markdown("""
267
  Example of Customer Profile in Graph
268
  =================
@@ -306,15 +307,15 @@ Once created, knowledge graphs can be repurposed across multiple use cases (e.g.
306
  gr.Examples(
307
  [
308
  [
309
- """
310
- He Hua (Hua Hua) Director
311
- hehua@chengdu.com
312
- +86-28-83505513
313
-
314
- Alternative Address Format:
315
- Xiongmao Ave West Section, Jinniu District (listed in some records as 610016 postcode)
316
- """
317
- ]
318
  ],
319
  [in_verbatim]
320
  )
@@ -333,7 +334,6 @@ Removes noise (e.g., irrelevant names or addresses) to make datasets cleaner and
333
  Allows downstream tasks (like sentiment analysis or topic modeling) to focus on content rather than personal identifiers.
334
  """)
335
 
336
-
337
  with gr.Tab("Segmentation"):
338
  gr.Markdown("""
339
  Objective: Streamline Customer Insights: Auto-Classify Feedback for Product Optimization
@@ -353,14 +353,14 @@ Allows downstream tasks (like sentiment analysis or topic modeling) to focus on
353
  gr.Examples(
354
  [
355
  [
356
- """
357
- "The online portal makes managing my mortgage payments so convenient.";
358
- "RBC offer great mortgage for my home with competitive rate thank you";
359
- "Low interest rate compared to other cards I’ve used. Highly recommend for responsible spenders.";
360
- "The mobile check deposit feature saves me so much time. Banking made easy!";
361
- "Affordable premiums with great coverage. Switched from my old provider and saved!"
362
- """
363
- ]
364
  ],
365
  [in_verbatim]
366
  )
@@ -444,7 +444,7 @@ Customer: "No, thank you."
444
  ],
445
  [in_verbatim]
446
  )
447
- btn_recommend=gr.Button("Resolve")
448
  btn_recommend.click(fn=resolve, inputs=in_verbatim, outputs=out_product)
449
 
450
  gr.Markdown("""
@@ -483,7 +483,9 @@ For example, Comcast reduced repeat service calls by 17% after deploying entity
483
 
484
  gr.Examples(
485
  [
486
- ["""My mortgage was assumed by Bank of America when Countrywide mortgages ceased to do business. My mortgage increased without any explanation. When I inquired, they stumbled and gave me the run around. I’d NEVER do business with Bank of America again""", "MORT"],
 
 
487
  ["my credit card limit is too low, I need a card with bigger limit and low fee", "CARD"]
488
  ],
489
  [in_verbatim, in_campaign]
@@ -541,50 +543,50 @@ For example, Comcast reduced repeat service calls by 17% after deploying entity
541
  btn_recommend.click(fn=rbc_product, inputs=in_verbatim, outputs=out_product)
542
 
543
  gr.Markdown("""
544
- Companies pour millions into product catalogs, marketing funnels, and user acquisition—yet many still face the same challenge:
545
- ==================
546
- ### 📉 Pain points:
547
- - High bounce rates and low conversion despite heavy traffic
548
- - Customers struggle to find relevant products on their own
549
- - One-size-fits-all promotions result in wasted ad spend and poor ROI
550
-
551
- ### 🧩 The real question:
552
- What if your product catalog could *adapt itself* to each user in real time—just like your best salesperson would?
553
-
554
- ### 🎯 The customer need:
555
- Businesses need a way to dynamically personalize product discovery, so every customer sees the most relevant items—without manually configuring hundreds of rules.
556
-
557
- ## ✅ Enter: Product Recommender Systems
558
-
559
- By analyzing behavioral data, preferences, and historical purchases, a recommender engine surfaces what each user is most likely to want—boosting engagement and revenue.
560
-
561
- ### 📌 Real-world use cases:
562
- - **Amazon** attributes up to 35% of its revenue to its recommender system, which tailors the home page, emails, and checkout cross-sells per user.
563
- - **Netflix** leverages personalized content recommendations to reduce churn and increase watch time—saving the company over $1B annually in retention value.
564
- - **Stitch Fix** uses machine learning-powered recommendations to curate clothing boxes tailored to individual style profiles—scaling personal styling.
565
-
566
- ### 💡 Business benefits:
567
- - Higher conversion rates through relevant discovery
568
- - Increased average order value (AOV) via cross-sell and upsell
569
- - Improved retention and lower customer acquisition cost (CAC)
570
-
571
- If your product discovery experience isn’t working as hard as your marketing budget, it’s time to make your catalog intelligent—with recommendations that convert.
572
  """)
573
 
574
- with gr.Tab("LLM Evals"):
575
  gr.Markdown("""
576
- 🏦 LLMs for Application Security in Personal Banking
577
- ====================
578
- What happens when your generative AI exposes customer data before you even launch?
579
-
580
- LLM evals reduce security risks in generative AI banking apps by identifying vulnerabilities and guiding secure fixes.
581
-
582
- Personal banking apps increasingly rely on generative AI—but insecure logic and hallucinations expose sensitive customer data. LLM evals help assess code and AI-generated responses for correctness, task completion, hallucination risk, and safety—enabling proactive guardrails against vulnerabilities before deployment.
583
-
584
- I’ve led cross-functional model risk initiatives, building pipelines that transform LLM evaluations into automated alerts and remediation workflows—strengthening regulatory compliance and protecting customer trust.
585
-
586
- Using open-source frameworks, I identify flaws in LLM prompt and translate risks into explainable insights for business, risk, and engineering stakeholders.
587
- https://postimg.cc/3WtG4ZK2
588
  """)
589
 
590
- demo.launch(allowed_paths=["."])
 
1
  import gradio as gr
2
+
 
 
 
 
3
  from classify import judge
4
  from entity import resolve
5
+ from graphrag import marketingPlan
6
  from human import email, feedback
7
+ from knowledge import graph
8
+ from pii import derisk
9
+ from rag import rbc_product
10
+ from tool import rival_product
11
 
12
  # Define the Google Analytics script
13
  head = """
 
95
 
96
  gr.Examples(
97
  [
98
+ [
99
+ "Low APR and great customer service. I would highly recommend if you’re looking for a great credit card company and looking to rebuild your credit. I have had my credit limit increased annually and the annual fee is very low."]
100
  ],
101
  [in_verbatim]
102
  )
103
+ btn_recommend = gr.Button("Recommend")
104
  btn_recommend.click(fn=rival_product, inputs=in_verbatim, outputs=out_product)
105
 
106
  gr.Markdown("""
 
256
 
257
  Customer: "No, thank you."
258
  """
259
+ ]
260
  ],
261
  [in_verbatim]
262
  )
 
264
  btn_clear = gr.ClearButton(components=[out_product])
265
  btn_recommend.click(fn=graph, inputs=[in_verbatim, out_product], outputs=out_product)
266
 
 
267
  gr.Markdown("""
268
  Example of Customer Profile in Graph
269
  =================
 
307
  gr.Examples(
308
  [
309
  [
310
+ """
311
+ He Hua (Hua Hua) Director
312
+ hehua@chengdu.com
313
+ +86-28-83505513
314
+
315
+ Alternative Address Format:
316
+ Xiongmao Ave West Section, Jinniu District (listed in some records as 610016 postcode)
317
+ """
318
+ ]
319
  ],
320
  [in_verbatim]
321
  )
 
334
  Allows downstream tasks (like sentiment analysis or topic modeling) to focus on content rather than personal identifiers.
335
  """)
336
 
 
337
  with gr.Tab("Segmentation"):
338
  gr.Markdown("""
339
  Objective: Streamline Customer Insights: Auto-Classify Feedback for Product Optimization
 
353
  gr.Examples(
354
  [
355
  [
356
+ """
357
+ "The online portal makes managing my mortgage payments so convenient.";
358
+ "RBC offer great mortgage for my home with competitive rate thank you";
359
+ "Low interest rate compared to other cards I’ve used. Highly recommend for responsible spenders.";
360
+ "The mobile check deposit feature saves me so much time. Banking made easy!";
361
+ "Affordable premiums with great coverage. Switched from my old provider and saved!"
362
+ """
363
+ ]
364
  ],
365
  [in_verbatim]
366
  )
 
444
  ],
445
  [in_verbatim]
446
  )
447
+ btn_recommend = gr.Button("Resolve")
448
  btn_recommend.click(fn=resolve, inputs=in_verbatim, outputs=out_product)
449
 
450
  gr.Markdown("""
 
483
 
484
  gr.Examples(
485
  [
486
+ [
487
+ """My mortgage was assumed by Bank of America when Countrywide mortgages ceased to do business. My mortgage increased without any explanation. When I inquired, they stumbled and gave me the run around. I’d NEVER do business with Bank of America again""",
488
+ "MORT"],
489
  ["my credit card limit is too low, I need a card with bigger limit and low fee", "CARD"]
490
  ],
491
  [in_verbatim, in_campaign]
 
543
  btn_recommend.click(fn=rbc_product, inputs=in_verbatim, outputs=out_product)
544
 
545
  gr.Markdown("""
546
+ Companies pour millions into product catalogs, marketing funnels, and user acquisition—yet many still face the same challenge:
547
+ ==================
548
+ ### 📉 Pain points:
549
+ - High bounce rates and low conversion despite heavy traffic
550
+ - Customers struggle to find relevant products on their own
551
+ - One-size-fits-all promotions result in wasted ad spend and poor ROI
552
+
553
+ ### 🧩 The real question:
554
+ What if your product catalog could *adapt itself* to each user in real time—just like your best salesperson would?
555
+
556
+ ### 🎯 The customer need:
557
+ Businesses need a way to dynamically personalize product discovery, so every customer sees the most relevant items—without manually configuring hundreds of rules.
558
+
559
+ ## ✅ Enter: Product Recommender Systems
560
+
561
+ By analyzing behavioral data, preferences, and historical purchases, a recommender engine surfaces what each user is most likely to want—boosting engagement and revenue.
562
+
563
+ ### 📌 Real-world use cases:
564
+ - **Amazon** attributes up to 35% of its revenue to its recommender system, which tailors the home page, emails, and checkout cross-sells per user.
565
+ - **Netflix** leverages personalized content recommendations to reduce churn and increase watch time—saving the company over $1B annually in retention value.
566
+ - **Stitch Fix** uses machine learning-powered recommendations to curate clothing boxes tailored to individual style profiles—scaling personal styling.
567
+
568
+ ### 💡 Business benefits:
569
+ - Higher conversion rates through relevant discovery
570
+ - Increased average order value (AOV) via cross-sell and upsell
571
+ - Improved retention and lower customer acquisition cost (CAC)
572
+
573
+ If your product discovery experience isn’t working as hard as your marketing budget, it’s time to make your catalog intelligent—with recommendations that convert.
574
  """)
575
 
576
+ with gr.Tab("Eval"):
577
  gr.Markdown("""
578
+ 🏦 LLMs for Application Security in Personal Banking
579
+ ====================
580
+ What happens when your generative AI exposes customer data before you even launch?
581
+
582
+ LLM evals reduce security risks in generative AI banking apps by identifying vulnerabilities and guiding secure fixes.
583
+
584
+ Personal banking apps increasingly rely on generative AI—but insecure logic and hallucinations expose sensitive customer data. LLM evals help assess code and AI-generated responses for correctness, task completion, hallucination risk, and safety—enabling proactive guardrails against vulnerabilities before deployment.
585
+
586
+ I’ve led cross-functional model risk initiatives, building pipelines that transform LLM evaluations into automated alerts and remediation workflows—strengthening regulatory compliance and protecting customer trust.
587
+
588
+ Using open-source frameworks, I identify flaws in LLM prompt and translate risks into explainable insights for business, risk, and engineering stakeholders.
589
+ https://postimg.cc/3WtG4ZK2
590
  """)
591
 
592
+ demo.launch(allowed_paths=["."])