example output

app.py

@@ -107,6 +107,11 @@ Other Links:
     btn_recommend.click(fn=rival_product, inputs=in_verbatim, outputs=out_product)
 
     gr.Markdown("""
+Example Output
+==========
+The U.S. Bank Cash+ Visa Secured Card, Capital One Quicksilver Secured Cash Rewards Credit Card, and Bank of America Customized Cash Rewards Secured Credit
+ Card are all options that may meet the customer's requirements.
+
 Companies in competitive industries are constantly under pressure to innovate—but often face the same challenge:
 ==================
 ### 📉 Pain points:
@@ -417,6 +422,41 @@ Customer: "No, thank you."
     btn_recommend.click(fn=graph, inputs=[in_verbatim, out_product], outputs=out_product)
 
     gr.Markdown("""
+Example Output
+==============
+```
+{'edges': [{'color': 'black', 'label': 'hasAccount', 'source': 1, 'target': 2},
+           {'color': 'black',
+            'label': 'disputeCaseIsFor',
+            'source': 1,
+            'target': 5},
+           {'color': 'black', 'label': 'causedBy', 'source': 3, 'target': 4},
+           {'color': 'black',
+            'label': 'hasChargeDispute',
+            'source': 2,
+            'target': 4}],
+ 'nodes': [{'color': 'orange',
+            'id': 4,
+            'label': '$329 Charge Dispute',
+            'record_date': datetime.date(2023, 3, 15)},
+           {'color': 'orange',
+            'id': 2,
+            'label': 'Apple Card',
+            'record_date': datetime.date(2023, 4, 5)},
+           {'color': 'orange',
+            'id': 5,
+            'label': 'GS-2025-0422-8830',
+            'record_date': datetime.date(2023, 4, 5)},
+           {'color': 'orange',
+            'id': 3,
+            'label': 'TechElectronics',
+            'record_date': datetime.date(2023, 3, 15)},
+           {'color': 'orange',
+            'id': 1,
+            'label': 'Michael Chen',
+            'record_date': datetime.date(2023, 4, 5)}]}
+
+```    
 Example of Customer Profile in Graph
 =================
 ![Customer Needs and Pain Points](https://i.postimg.cc/D03Sstqd/knowledge-graph1.png)
@@ -779,10 +819,14 @@ For example, Comcast reduced repeat service calls by 17% after deploying entity
       ],
       [in_verbatim]
     )
-    btn_recommend = gr.Button("Recommend")
+    btn_recommend = gr.Button("Recommend (disabled due to embedding too big for download in huggingface)", interactive=False)
     btn_recommend.click(fn=rbc_product, inputs=in_verbatim, outputs=out_product)
 
     gr.Markdown("""
+    Example Output
+    ===========
+    RBC Newcomer Mortgage
+
     Companies pour millions into product catalogs, marketing funnels, and user acquisition—yet many still face the same challenge:
     ==================
     ### 📉 Pain points:
@@ -857,6 +901,25 @@ For example, Comcast reduced repeat service calls by 17% after deploying entity
     btn_recommend = gr.Button("Mask PII")
     btn_recommend.click(fn=derisk, inputs=in_verbatim, outputs=out_product)
     gr.Markdown("""
+Example Output
+=========
+GUARDRAILED: 
+    He Hua (<PERSON>) Director
+    hehua@chengdu.com
+    <PHONE_NUMBER>
+
+    Alternative Address Format:
+    Xiongmao Ave West Section, Jinniu District (listed in some records as 610016 postcode)
+
+
+    Best Viewing: Before 9:00 AM during summer hours (7:30 AM-5:00 PM)
+
+    Caretaker: <Caretaker_0>"Grandpa <PERSON>")
+
+    Additional Contacts
+    Charitable Donations: <PHONE_NUMBER>
+    Dining Reservations: <PHONE_NUMBER>
+
 "Is your personal banking AI trained on customer conversations—or customer identities?"
 ===========
 At RBC, generative AI is transforming personal banking—from real-time support to automated financial advice. But the same customer data powering these insights can expose the bank to regulatory violations, data breaches, and biased models—especially when names, emails, and phone numbers slip through into training or inference pipelines.

knowledge.py

@@ -7,6 +7,7 @@ from pydantic import BaseModel, Field
 
 import os
 from datetime import date
+
 from groq import Groq
 # Initialize with API key
 client = Groq(api_key=os.getenv("GROQ_API_KEY"))
@@ -210,7 +211,9 @@ Representative: "Confirmed. Your next payment of $200 will process May 1st. A co
 Customer: "No, thank you."
          """
   graph = generate_graph(query)
-
+  from pprint import pprint
+  pprint(graph.model_dump())
+  '''
   graph2 = generate_graph("My mortgage rate is 9%, I cannot afford it anymore, I need to refinance and I'm unemploy right now.", graph)
   graph2.draw()
-
+  '''

rag.py

@@ -2,7 +2,7 @@ import dspy
 
 import pandas as pd
 
-#lm = dspy.LM('ollama_chat/deepseek-r1', api_base='http://localhost:11434', api_key='')
+#lm = dspy.LM('ollama_chat/llama3.2', api_base='http://localhost:11434', api_key='')
 #lm = dspy.LM('huggingface/Qwen/Qwen2.5-Coder-32B-Instruct')
 #lm = dspy.LM('huggingface/meta-llama/Llama-3.2-1B')
 lm = dspy.LM('groq/qwen-qwq-32b')
@@ -13,21 +13,22 @@ df['content']=df['product']+"; "+df['purpose']+"; "+df['benefit']+"; "+df['fee']
 
 corpus = [row['content'] for i,row in df.iterrows()]
 
-'huggingface/BAAI/bge-small-en-v1.5'
+
 """
 from sentence_transformers import SentenceTransformer
 
 # Load an extremely efficient local model for retrieval
-model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2", device="cpu")
+model = SentenceTransformer('huggingface/BAAI/bge-small-en-v1.5', device="cpu")
 embedder = dspy.Embedder(model.encode)
 """
 
+"sentence-transformers/all-MiniLM-L6-v2"
 import numpy as np
 def my_embedder(texts):
   return np.random.rand(len(texts), 10)
 
 embedder = dspy.Embedder(my_embedder)
-#embedder = dspy.Embedder('huggingface/BAAI/bge-small-en-v1.5')
+#embedder = dspy.Embedder('huggingface/BAAI/llm-embedder') #BAAI/bge-small-en-v1.5')  #not working
 class RecommendProduct(dspy.Signature):
   """
   Recommend RBC financial product based on verbatim
@@ -55,4 +56,7 @@ qa = RAG(num_passages=2)
 
 def rbc_product(customer:str):
   response = qa(verbatim=f"Which RBC personal banking product best serve the follow customer needs, pain points: {customer}")
-  return response.product
+  return response.product
+
+if __name__ == '__main__':
+    print(rbc_product(customer))

tool.py

@@ -4,7 +4,7 @@ import dspy
 from dspy.predict.react import Tool
 from tavily import TavilyClient
 
-#lm = dspy.LM('ollama_chat/deepseek-r1', api_base='http://localhost:11434', api_key='')
+#lm = dspy.LM('ollama_chat/llama3.2', api_base='http://localhost:11434', api_key='')
 #lm = dspy.LM('huggingface/Qwen/Qwen2.5-Coder-32B-Instruct')
 #lm = dspy.LM('huggingface/meta-llama/Llama-3.2-1B')
 lm = dspy.LM('groq/qwen-qwq-32b')
@@ -24,4 +24,7 @@ customer="Low APR and great customer service. I would highly recommend if you’
 
 def rival_product(customer:str):
     prediction = agent(verbatim=f"Which banking product name best serve this customer needs: {customer}")
-    return prediction.product
+    return prediction.product
+
+if __name__ == '__main__':
+    print(rival_product(customer))