Update app.py

app.py

@@ -3,7 +3,7 @@ import gradio as gr
 import random
 import pandas as pd
 from io import BytesIO 
-import csv 
+import csv
 import os
 import io 
 import tempfile
@@ -11,23 +11,23 @@ import re
 
 client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
-def extract_text_from_excel(file):
+def extract_sentences_from_excel(file):
     df = pd.read_excel(file)
-    text = ' '.join(df['Unnamed: 1'].astype(str))
-    return text
+    text = ' '.join(df['Column_Name'].astype(str))
+    sentences = text.split('.')
+    sentences = [s.strip() for s in sentences if s.strip()]
+    return sentences
 
-def save_to_csv(prompt, sentence, output, filename="synthetic_data.csv"):
+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([prompt, sentence, output])
+        writer.writerow([sentence, output])
 
-def generate(file, prompt, temperature, max_new_tokens, top_p, repetition_penalty, num_similar_sentences):
-    text = extract_text_from_excel(file)
-    sentences = text.split('.')
-    random.shuffle(sentences)  # Shuffle sentences
+def generate(file, prompt, temperature, max_new_tokens, top_p, repetition_penalty):
+    sentences = extract_sentences_from_excel(file)
 
     with tempfile.NamedTemporaryFile(mode='w', newline='', delete=False, suffix='.csv') as tmp:
-        fieldnames = ['Prompt', 'Original Sentence', 'Generated Sentence']
+        fieldnames = ['Original Sentence', 'Generated Sentence']
         writer = csv.DictWriter(tmp, fieldnames=fieldnames)
         writer.writeheader()  
 
@@ -46,7 +46,7 @@ def generate(file, prompt, temperature, max_new_tokens, top_p, repetition_penalt
             }
 
             try:
-                stream = client.text_generation(prompt + sentence, **generate_kwargs, stream=True, details=True, return_full_text=False)
+                stream = client.text_generation(f"{prompt} {sentence}", **generate_kwargs, stream=True, details=True, return_full_text=False)
                 output = ""
                 for response in stream:
                     output += response.token.text
@@ -54,34 +54,27 @@ def generate(file, prompt, temperature, max_new_tokens, top_p, repetition_penalt
                 generated_sentences = re.split(r'(?<=[\.\!\?:])[\s\n]+', output)
                 generated_sentences = [s.strip() for s in generated_sentences if s.strip() and s != '.']
 
-                for _ in range(num_similar_sentences):
-                    if not generated_sentences:
-                        break
-                    generated_sentence = generated_sentences.pop(random.randrange(len(generated_sentences)))
-                    writer.writerow({'Prompt': prompt, 'Original Sentence': sentence, 'Generated Sentence': generated_sentence})
+                for generated_sentence in generated_sentences:
+                    writer.writerow({'Original Sentence': sentence, 'Generated Sentence': generated_sentence})
 
             except Exception as e:
                 print(f"Error generating data for sentence '{sentence}': {e}")
 
         tmp_path = tmp.name
 
-    return tmp_path, output
+    return tmp_path
 
 gr.Interface( 
     fn=generate,
     inputs=[
         gr.File(label="Upload Excel File", file_count="single", file_types=[".xlsx"]),
-        gr.Textbox(label="Prompt", placeholder="Enter your prompt here..."),
+        gr.Textbox(label="Prompt", placeholder="Enter your prompt here"),
         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"),
         gr.Slider(label="Max new tokens", value=256, minimum=0, maximum=5120, step=64, interactive=True, info="The maximum numbers of new tokens"),
         gr.Slider(label="Top-p (nucleus sampling)", value=0.95, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more low-probability tokens"),
         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 similar sentences", value=10, minimum=1, maximum=20, step=1, interactive=True, info="Number of similar sentences to generate for each original sentence"),
-    ],
-    outputs=[
-        gr.File(label="Synthetic Data"),
-        gr.Textbox(label="Generated Output")
     ],
+    outputs=gr.File(label="Synthetic Data "),
     title="SDG",
     description="AYE QABIL.",
     allow_flagging="never",