multi class

app.py

@@ -63,6 +63,8 @@ Relevant offers encourage repeat visits and build long-term loyalty.
 - Inventory Optimization
 Promotes underperforming products or clears surplus stock with strategic recommendations.
 
+If you're experiencing declining market share or inefficiencies in your operations, here's how I can help:
+==============
 Marketing
 ------------
 - GraphRAG: Models customer-product relationship networks for next-best-action predictions
@@ -253,7 +255,7 @@ Allows downstream tasks (like sentiment analysis or topic modeling) to focus on
     Objective: Classify customer feedback into product bucket
     ================================================
     """)
-    in_verbatim = gr.Textbox(label="Customer Feedback")
+    in_verbatim = gr.Textbox(label="Customer Feedback separate by ;")
     out_product = gr.Textbox(label="Classification")
 
     gr.Examples(

classify.py

@@ -22,20 +22,22 @@ client = instructor.from_openai(
     ),
     mode=instructor.Mode.JSON,
 )
+
+    chain_of_thought:List[str]= Field(default_factory=list, description="the chain of thought led to the prediction", examples=["Let's think step by step. the customer explicitly mention donation, and there is a tag name with donation, tag the text with donation"])
 """
 llm = 'llama-3.1-8b-instant' if os.getenv("GROQ_API_KEY") else "deepseek-r1"
 
 
 class Tag(BaseModel):
 
-    chain_of_thought:List[str]= Field(default_factory=list, description="the chain of thought led to the prediction", examples=["Let's think step by step. the customer explicitly mention donation, and there is a tag name with donation, tag the text with donation"])
+
     name: str
     id: int= Field(..., description="id for the specific tag")
     confidence: float = Field(
         default=0.5,
         ge=0,
         le=1,
-        description="The confidence of the prediction for name and id, 0 is low, 1 is high",examples=[0.5,0.1,0.9]
+        description="The confidence of the prediction(id, name) for the text, 0 is low, 1 is high",examples=[0.5,0.1,0.9]
     )
 
     @field_validator('confidence', mode="after")
@@ -157,7 +159,7 @@ texts = """
 """
 
 def bucket(texts):
-  texts=texts.split(";")
+  texts=map(lambda t: t.strip(), texts.split(";"))
   request = TagRequest(texts=texts, tags=tags)
 
   response = asyncio.run(tag_request(request))