app.py

# app.py
import gradio as gr
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
import pandas as pd

# Load your synthetic profitability dataset
df = pd.read_csv('synthetic_profit.csv')

# Initialize the TAPEX small model fine-tuned on WikiSQL
MODEL_ID = "microsoft/tapex-small-finetuned-wikisql"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model     = AutoModelForSeq2SeqLM.from_pretrained(MODEL_ID)

# Build a table-QA pipeline
table_qa = pipeline(
    "table-question-answering",
    model=model,
    tokenizer=tokenizer,
    framework="pt",
    device=-1   # set to 0 if you enable GPU in your Space
)

def answer_profitability(question):
    table = df.to_dict(orient="records")
    try:
        out = table_qa(table=table, query=question)
        return out.get("answer", "No answer found.")
    except Exception as e:
        return f"Error: {e}"

# Gradio interface
iface = gr.Interface(
    fn=answer_profitability,
    inputs=gr.Textbox(lines=2, placeholder="Ask a question about profitability…"),
    outputs="text",
    title="SAP Profitability Q&A (TAPEX-Small)",
    description="""
    Ask free-form questions on the synthetic profitability dataset.
    Powered end-to-end by microsoft/tapex-small-finetuned-wikisql.
    """
)

if __name__ == "__main__":
    iface.launch(server_name="0.0.0.0", server_port=7860)