Update app.py

app.py

@@ -1,13 +1,10 @@
 from huggingface_hub import InferenceClient
-import gradio as gr
 import pandas as pd
 import re
 import random
 import csv
-import os
-import io
 import tempfile
-
+import gradio as gr
 client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
 def extract_sentences_from_excel(file):
@@ -19,21 +16,16 @@ def extract_sentences_from_excel(file):
         sentences.extend([s.strip() for s in new_sentences if s.strip()])
     return sentences
 
-def save_to_csv(sentence, output, filename="synthetic_data.csv"):
-    with open(filename, mode='a', newline='', encoding='utf-8') as file:
-        writer = csv.writer(file)
-        writer.writerow([sentence, output])
-
-def generate(file, temperature, max_new_tokens, top_p, repetition_penalty, num_sentences=10000):
+def generate_text(file, temperature, max_new_tokens, top_p, repetition_penalty, num_sentences=10000):
     sentences = extract_sentences_from_excel(file)
-    random.shuffle(sentences)  # Shuffle sentences
+    random.shuffle(sentences)
 
     with tempfile.NamedTemporaryFile(mode='w', newline='', delete=False, suffix='.csv') as tmp:
         fieldnames = ['Original Sentence', 'Generated Sentence']
         writer = csv.DictWriter(tmp, fieldnames=fieldnames)
         writer.writeheader()
 
-        for sentence in sentences[:num_sentences]:  # Process the first num_sentences sentences
+        for sentence in sentences[:num_sentences]:
             sentence = sentence.strip()
             if not sentence:
                 continue
@@ -65,9 +57,8 @@ def generate(file, temperature, max_new_tokens, top_p, repetition_penalty, num_s
         tmp_path = tmp.name
 
     return tmp_path
-
 gr.Interface(
-    fn=generate,
+    fn=generate_text,
     inputs=[
         gr.File(label="Upload Excel File", file_count="single", file_types=[".xlsx", ".xls"]),
         gr.Slider(label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Higher values produce more diverse outputs"),
@@ -76,8 +67,8 @@ gr.Interface(
         gr.Slider(label="Repetition penalty", value=1.0, minimum=1.0, maximum=2.0, step=0.1, interactive=True, info="Penalize repeated tokens"),
         gr.Slider(label="Number of sentences", value=10000, minimum=1, maximum=100000, step=1000, interactive=True, info="The number of sentences to generate"),
     ],
-    outputs=gr.File(label="Synthetic Data"),
-    title="SDG",
-    description="AYE QABIL.",
+    outputs=gr.File(label="Generated CSV"),
+    title="Text Generation from Excel",
+    description="Generate text from sentences in an Excel file and save it to a CSV file.",
     allow_flagging="never",
 ).launch()