Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,20 +1,24 @@
|
|
|
|
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
import pandas as pd
|
| 3 |
import torch
|
| 4 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
|
| 5 |
|
| 6 |
-
# 1) Load
|
| 7 |
df = pd.read_csv('synthetic_profit.csv')
|
| 8 |
|
| 9 |
-
# 2)
|
| 10 |
MODEL_ID = "microsoft/tapex-base-finetuned-wikisql"
|
| 11 |
|
| 12 |
-
# 3)
|
| 13 |
device = 0 if torch.cuda.is_available() else -1
|
| 14 |
|
|
|
|
| 15 |
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
|
| 16 |
model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_ID)
|
| 17 |
|
|
|
|
| 18 |
table_qa = pipeline(
|
| 19 |
"table-question-answering",
|
| 20 |
model=model,
|
|
@@ -23,23 +27,29 @@ table_qa = pipeline(
|
|
| 23 |
device=device,
|
| 24 |
)
|
| 25 |
|
| 26 |
-
#
|
| 27 |
def answer_profitability(question: str) -> str:
|
| 28 |
-
|
|
|
|
|
|
|
| 29 |
try:
|
| 30 |
out = table_qa(table=table, query=question)
|
| 31 |
return out.get("answer", "No answer found.")
|
| 32 |
except Exception as e:
|
| 33 |
return f"Error: {e}"
|
| 34 |
|
| 35 |
-
#
|
| 36 |
iface = gr.Interface(
|
| 37 |
fn=answer_profitability,
|
| 38 |
inputs=gr.Textbox(lines=2, placeholder="Ask a question about profitability…"),
|
| 39 |
outputs="text",
|
| 40 |
title="SAP Profitability Q&A (TAPEX-Base)",
|
| 41 |
-
description=
|
|
|
|
|
|
|
|
|
|
| 42 |
)
|
| 43 |
|
|
|
|
| 44 |
if __name__ == "__main__":
|
| 45 |
iface.launch(server_name="0.0.0.0", server_port=7860)
|
|
|
|
| 1 |
+
# app.py
|
| 2 |
+
|
| 3 |
import gradio as gr
|
| 4 |
import pandas as pd
|
| 5 |
import torch
|
| 6 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
|
| 7 |
|
| 8 |
+
# 1) Load your synthetic profitability dataset
|
| 9 |
df = pd.read_csv('synthetic_profit.csv')
|
| 10 |
|
| 11 |
+
# 2) Choose the publicly available TAPEX WikiSQL model
|
| 12 |
MODEL_ID = "microsoft/tapex-base-finetuned-wikisql"
|
| 13 |
|
| 14 |
+
# 3) Set device: GPU if available, else CPU
|
| 15 |
device = 0 if torch.cuda.is_available() else -1
|
| 16 |
|
| 17 |
+
# 4) Load tokenizer and model
|
| 18 |
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
|
| 19 |
model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_ID)
|
| 20 |
|
| 21 |
+
# 5) Build the table-question-answering pipeline
|
| 22 |
table_qa = pipeline(
|
| 23 |
"table-question-answering",
|
| 24 |
model=model,
|
|
|
|
| 27 |
device=device,
|
| 28 |
)
|
| 29 |
|
| 30 |
+
# 6) Define the QA function, casting all cells to strings to avoid float issues
|
| 31 |
def answer_profitability(question: str) -> str:
|
| 32 |
+
# Cast entire DataFrame to string
|
| 33 |
+
df_str = df.astype(str)
|
| 34 |
+
table = df_str.to_dict(orient="records")
|
| 35 |
try:
|
| 36 |
out = table_qa(table=table, query=question)
|
| 37 |
return out.get("answer", "No answer found.")
|
| 38 |
except Exception as e:
|
| 39 |
return f"Error: {e}"
|
| 40 |
|
| 41 |
+
# 7) Define Gradio interface
|
| 42 |
iface = gr.Interface(
|
| 43 |
fn=answer_profitability,
|
| 44 |
inputs=gr.Textbox(lines=2, placeholder="Ask a question about profitability…"),
|
| 45 |
outputs="text",
|
| 46 |
title="SAP Profitability Q&A (TAPEX-Base)",
|
| 47 |
+
description=(
|
| 48 |
+
"Free-form questions on the synthetic profitability dataset, "
|
| 49 |
+
"powered end-to-end by microsoft/tapex-base-finetuned-wikisql."
|
| 50 |
+
)
|
| 51 |
)
|
| 52 |
|
| 53 |
+
# 8) Launch the app
|
| 54 |
if __name__ == "__main__":
|
| 55 |
iface.launch(server_name="0.0.0.0", server_port=7860)
|