human-in-the-loop

app.py

@@ -126,7 +126,7 @@ Companies in competitive industries are constantly under pressure to innovate—
 - Lack of insight into customer feedback on competitor features.
 - Difficulty in predicting how new features will be received in the market.
 
-### 🧩 The real question:
+## 🧩 The real question:
 How can your product stay ahead of the competition without a clear understanding of what features your competitors are developing, and how they’re performing with customers?
 
 ### 🎯 The customer need:
@@ -148,7 +148,7 @@ By leveraging AI, market intelligence, and competitive analysis tools, you can t
 
 With the right competitive research, you don’t just react to the market—you anticipate it.
     """)
-  with gr.Tab("Graphrag Marketing Plan"):
+  with gr.Tab("Graphrag Marketing"):
     gr.Markdown("""
     Objective: Develop a Targeted Marketing Plan Aligned with Customer Personas
     =======================
@@ -212,7 +212,7 @@ Quickly generates tailored campaigns, reducing go-to-market time from weeks to h
 Uses customer data and behavior to craft messages that resonate with specific segments.
         """)
 
-  with gr.Tab("Personalized Knowledge Graph"):
+  with gr.Tab("Personalized KG"):
     gr.Markdown("""
 Objective: Transform Personal Pain Points into Actionable Insights with a Dynamic Knowledge Graph Framework
 =====================================
@@ -350,7 +350,7 @@ Allows downstream tasks (like sentiment analysis or topic modeling) to focus on
     """)
 
 
-  with gr.Tab("Classify & Guardrail"):
+  with gr.Tab("Classify"):
     gr.Markdown("""
     Objective: Streamline Customer Insights: Auto-Classify Feedback for Product Optimization
     ================================================
@@ -393,10 +393,12 @@ Proactively flags 5+ fraud types (identity theft, money laundering) with 40% few
 Auto-classifies documents for FINRA/SEC audits (e.g., Morgan Stanley uses NLP to categorize 3M+ annual communications into 50+ compliance buckets).
     """)
 
-  with gr.Tab("Resolution for Call Center"):
+  with gr.Tab("Call Resolution"):
     gr.Markdown("""
     Objective: Proactive Entity Mapping: Clarifying Critical Elements in Complex Call Analysis for Strategic Insight
     ================================================
+    - Graph relationship between entity
+    - summary of the interaction
     """)
     in_verbatim = gr.Textbox(label="Content")
     out_product = gr.Textbox(label="Entity Resolution")
@@ -466,18 +468,18 @@ Example of Call Resolution
 
 ![Resolution for Clear Picture about Customer Issue..](file=./entity.png)
 
-#### Resolution for Clear Picture about Customer Issue
+Resolution for Clear Picture about Customer Issue
 https://i.postimg.cc/J4qsDYtZ/entity.png
 
 Companies like RBC, Comcast, or BMO often face a recurring challenge: long, complex customer service calls filled with vague product references, overlapping account details, and unstructured issue descriptions. This makes it difficult for support teams and analytics engines to extract clear insights or resolve recurring pain points across accounts and products.
 
-How can teams automatically stitch together fragmented mentions of the same customer, product, or issue—across call transcripts, CRM records, and support tickets—to form a unified view of the actual problem?
+#### How can teams automatically stitch together fragmented mentions of the same customer, product, or issue—across call transcripts, CRM records, and support tickets—to form a unified view of the actual problem?
 
 That's where Entity Resolution comes in. By linking related entities hidden across data silos and messy text (like "my internet box" = "ARRIS TG1682G" or "John Smith, J. Smith, and [email protected]"), teams gain a clearer, contextual understanding of customer frustration in real-time.
 
 For example, Comcast reduced repeat service calls by 17% after deploying entity resolution models on long call transcripts—turning messy feedback into actionable product insights and faster resolutions.
 
-The result? Less agent time lost, higher customer satisfaction, and data pipelines that actually speak human.
+### The result? Less agent time lost, higher customer satisfaction, and data pipelines that actually speak human.
     """)
   with gr.Tab("Human Feedback Content"):
     gr.Markdown("""
@@ -496,7 +498,7 @@ The result? Less agent time lost, higher customer satisfaction, and data pipelin
       ],
       [in_verbatim, in_campaign]
     )
-    btn_recommend = gr.Button("Resolve")
+    btn_recommend = gr.Button("Personalized Email")
     btn_recommend.click(fn=email, inputs=[in_verbatim, in_campaign, out_product], outputs=out_product)
 
     h_feedback = gr.Radio(['approved', 'rejected'], label="Human Feedback", info="Which campaign you want to approve?")
@@ -515,7 +517,7 @@ The result? Less agent time lost, higher customer satisfaction, and data pipelin
     
     - 52% faster ROI through AI-driven personalization scaling
     
-    #### Ask: Ready to turn customer frustrations into loyalty drivers with content that feels personally crafted?"
+    ### Ready to turn customer frustrations into loyalty drivers with content that feels personally crafted?
     
     This approach aligns with best-in-class use cases where feedback-driven personalization drives measurable business growth
     """)

entity.py

@@ -51,6 +51,10 @@ class Entity(BaseModel):
 
 
 class DocumentExtraction(BaseModel):
+    summary: str= Field(
+        ...,
+        description="concise summary of the interaction for customer issue and representative solution",
+    )
     entities: List[Entity] = Field(
         ...,
         description="Body of the answer, each fact should be a separate object with a body and a list of sources such as Organization, Agreement Date, Asset...etc",

human.py

@@ -20,8 +20,8 @@ llm_with_tools = llm #.bind_tools(tools)
 from langchain_groq import ChatGroq
 
 llm = ChatGroq(
-    model="llama-3.1-8b-instant",
-    temperature=0,
+    model="gemma2-9b-it", #"llama-3.1-8b-instant",
+    temperature=0.4,
     max_tokens=None,
     timeout=None,
     max_retries=2,
@@ -64,7 +64,7 @@ graph_builder = StateGraph(State)
 
 
 def write_email(state: State):
-  prompt = f"""Write an promotional personalized email for this persona:
+  prompt = f"""Write an promotional personalized email for this persona and offer financial education and setup a meeting for financial advisor, Only the email nothing else:
     {state["persona"]}
     """
   email = llm_with_tools.invoke(prompt)
@@ -115,14 +115,14 @@ def email(persona, campaign, history):
   thread_config = {"configurable": {"thread_id": campaign}}
   for event in graph.stream({"persona": persona}, config=thread_config):
     for value in event.values():
-      return r"\nAssistant: ", value, r"\nValue: ", graph.get_state(thread_config).values
+      return r"Assistant: ", value, r"Value: ", graph.get_state(thread_config).values
 
 
 def feedback(deliver, campaign, history):
   thread_config = {"configurable": {"thread_id": campaign}}
   for event in graph.stream(Command(resume=deliver), config=thread_config):
     for value in event.values():
-      return r"\nAssistant: ", value, r"\nValue: ", graph.get_state(thread_config).values
+      return r"Assistant: ", value, r"Value: ", graph.get_state(thread_config).values
 
 
 '''