Update app.py

app.py

@@ -4,7 +4,7 @@ import re
 import random
 import csv
 import tempfile
-import gradio as gr 
+import gradio as gr
 client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
 def extract_sentences_from_excel(file):
@@ -16,16 +16,16 @@ def extract_sentences_from_excel(file):
         sentences.extend([s.strip() for s in new_sentences if s.strip()])
     return sentences
 
-def generate_text(file, temperature, max_new_tokens, top_p, repetition_penalty, num_sentences=10000):
+def generate_synthetic_data(file, temperature, max_new_tokens, top_p, repetition_penalty):
     sentences = extract_sentences_from_excel(file)
     random.shuffle(sentences)
 
     with tempfile.NamedTemporaryFile(mode='w', newline='', delete=False, suffix='.csv') as tmp:
-        fieldnames = ['Original Sentence', 'Generated Sentence']
+        fieldnames = ['Original Sentence', 'Synthetic Data']
         writer = csv.DictWriter(tmp, fieldnames=fieldnames)
         writer.writeheader()
 
-        for sentence in sentences[:num_sentences]:
+        for sentence in sentences:
             sentence = sentence.strip()
             if not sentence:
                 continue
@@ -40,16 +40,14 @@ def generate_text(file, temperature, max_new_tokens, top_p, repetition_penalty,
             }
 
             try:
-                stream = client.text_generation(sentence, **generate_kwargs, stream=True, details=True, return_full_text=False)
-                output = ""
-                for response in stream:
-                    output += response.token.text
+                output = client.generate(sentence, **generate_kwargs, return_full_text=True)
+                generated_data = output.text.strip()
 
-                generated_sentences = re.split(r'(?<=[\.\!\?:])[\s\n]+', output)
+                generated_sentences = re.split(r'(?<=[\.\!\?:])[\s\n]+', generated_data)
                 generated_sentences = [s.strip() for s in generated_sentences if s.strip() and s != '.']
 
                 for generated_sentence in generated_sentences:
-                    writer.writerow({'Original Sentence': sentence, 'Generated Sentence': generated_sentence})
+                    writer.writerow({'Original Sentence': sentence, 'Synthetic Data': generated_sentence})
 
             except Exception as e:
                 print(f"Error generating data for sentence '{sentence}': {e}")
@@ -57,18 +55,18 @@ def generate_text(file, temperature, max_new_tokens, top_p, repetition_penalty,
         tmp_path = tmp.name
 
     return tmp_path
+
 gr.Interface(
-    fn=generate_text,
+    fn=generate_synthetic_data,
     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"),
         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 sentences", value=10000, minimum=1, maximum=100000, step=1000, interactive=True, info="The number of sentences to generate"),
     ],
-    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.",
+    outputs=gr.File(label="Synthetic Data CSV"),
+    title="Synthetic Data Generation",
+    description="Generate synthetic data from sentences in an Excel file and save it to a CSV file.",
     allow_flagging="never",
-).launch() 
+).launch()