Update app.py

app.py

@@ -1,21 +1,23 @@
+# app.py
+
 import gradio as gr
 import pandas as pd
 from transformers import pipeline
 
-# 1) Load your data
+# 1) Load your synthetic SAP data
 df = pd.read_csv("synthetic_profit.csv")
 table = df.astype(str).to_dict(orient="records")
 
-# 2) TAPAS pipeline
+# 2) Use TAPEX fine-tuned on WikiTableQuestions
 qa = pipeline(
     "table-question-answering",
-    model="google/tapas-base-finetuned-wtq",
-    tokenizer="google/tapas-base-finetuned-wtq",
-    device=-1
+    model="microsoft/tapex-base-finetuned-wtq",
+    tokenizer="microsoft/tapex-base-finetuned-wtq",
+    device=-1  # CPU; switch to 0 if you have GPU
 )
 
-# 3) Four few-shot examples: sum revenue, sum cost, sum margin, **mean margin**
-EXAMPLE_PROMPT = """
+# 3) Few-shot examples teaching “filter + sum”
+EXAMPLES = """
 Example 1:
 Q: What is the total revenue for Product A in EMEA in Q1 2024?
 A: Filter Product=A & Region=EMEA & FiscalYear=2024 & FiscalQuarter=Q1, then sum Revenue → 3075162.49
@@ -27,14 +29,10 @@ A: Filter Product=A & Region=EMEA & FiscalYear=2024 & FiscalQuarter=Q1, then sum
 Example 3:
 Q: What is the total margin for Product A in EMEA in Q1 2024?
 A: Filter Product=A & Region=EMEA & FiscalYear=2024 & FiscalQuarter=Q1, then sum ProfitMargin → 0.18
-
-Example 4:
-Q: What is the average profit margin for Product A in EMEA in Q1 2024?
-A: Filter Product=A & Region=EMEA & FiscalYear=2024 & FiscalQuarter=Q1, then mean ProfitMargin → 0.18
 """
 
 def answer_question(question: str) -> str:
-    prompt = EXAMPLE_PROMPT + f"\nQ: {question}\nA:"
+    prompt = EXAMPLES + f"\nQ: {question}\nA:"
     try:
         out = qa(table=table, query=prompt)
         return out.get("answer", "No answer found.")
@@ -44,13 +42,10 @@ def answer_question(question: str) -> str:
 # 4) Gradio UI
 iface = gr.Interface(
     fn=answer_question,
-    inputs=gr.Textbox(lines=2, placeholder="e.g. What is the average profit margin by region?", label="Your question"),
-    outputs=gr.Textbox(lines=4, label="Answer"),
-    title="SAP Profitability Q&A (TAPAS)",
-    description=(
-        "Ask simple sum/mean questions on your SAP data.  \n"
-        "Powered by google/tapas-base-finetuned-wtq with four few-shot examples."
-    ),
+    inputs=gr.Textbox(lines=2, placeholder="e.g. What is the total revenue for Product A in EMEA in Q1 2024?", label="Your question"),
+    outputs=gr.Textbox(lines=3, label="Answer"),
+    title="SAP Profitability Q&A (TAPEX)",
+    description="Ask basic sum questions on SAP data, powered by TAPEX with few-shot examples.",
     allow_flagging="never",
 )