Update app.py

app.py

@@ -1,42 +1,32 @@
 import gradio as gr
+from transformers import pipeline
 import pandas as pd
 import io
 
-from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoModelForCausalLM
-import torch
-
-# Model lists
-zero_shot_models = {
+# Define available classification models
+models = {
     "EN: deberta-v3-large-zeroshot": "MoritzLaurer/deberta-v3-large-zeroshot-v2.0",
-    "MULTI: mDeBERTa-v3-base-xnli": "MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7",
+    "MULTI: mDeBERTa-v3-xnli": "MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7",
     "MULTI: xlm-roberta-large-xnli": "joeddav/xlm-roberta-large-xnli"
 }
 
-text_gen_models = {
-    "Mixtral-8x7B-Instruct": "mistralai/Mixtral-8x7B-Instruct-v0.1",
-    "DeepSeek-Qwen3-8B": "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
-    "DeepSeek-52B": "deepseek-ai/DeepSeek-R1-0528",
-    "LLaMA-3.1-8B-Instruct": "meta-llama/Llama-3.1-8B-Instruct"
-}
-
-# Shared storage for results
 response_table = []
 
-def run_classification(questions_text, labels_text, model_name):
-    labels = [label.strip() for label in labels_text.split(",") if label.strip()]
+def classify(questions_text, labels_text, model_choice):
+    labels = [l.strip() for l in labels_text.split(",") if l.strip()]
     questions = [q.strip() for q in questions_text.split("\n") if q.strip()]
     if not labels or not questions:
-        return "Please enter both items and response options.", None
+        return "Please enter both questions and labels.", None
 
-    classifier = pipeline("zero-shot-classification", model=model_name)
+    classifier = pipeline("zero-shot-classification", model=models[model_choice])
     global response_table
     response_table = []
     output_lines = []
 
     for i, question in enumerate(questions, 1):
         result = classifier(question, labels, multi_label=False)
-        row = {"Item #": i, "Item": question}
         output_lines.append(f"{i}. {question}")
+        row = {"Item #": i, "Item": question}
         for label, score in zip(result["labels"], result["scores"]):
             row[label] = round(score, 3)
             output_lines.append(f"→ {label}: {round(score, 3)}")
@@ -45,68 +35,25 @@ def run_classification(questions_text, labels_text, model_name):
 
     return "\n".join(output_lines), None
 
-def run_generation(questions_text, model_name):
-    questions = [q.strip() for q in questions_text.split("\n") if q.strip()]
-    if not questions:
-        return "Please enter at least one item.", None
-
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32)
-    model.eval()
-
-    global response_table
-    response_table = []
-    output_lines = []
-
-    for i, question in enumerate(questions, 1):
-        prompt = f"Please respond to the following item as if you were a survey participant:\n\"{question}\""
-        inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-        outputs = model.generate(**inputs, max_new_tokens=60)
-        response = tokenizer.decode(outputs[0], skip_special_tokens=True).split("\n")[-1]
-        output_lines.append(f"{i}. {question}\n→ {response.strip()}\n")
-        response_table.append({"Item #": i, "Item": question, "Response": response.strip()})
-
-    return "\n".join(output_lines), None
-
 def download_csv():
-    if not response_table:
-        return None
     df = pd.DataFrame(response_table)
-    csv_buffer = io.StringIO()
-    df.to_csv(csv_buffer, index=False)
-    return csv_buffer.getvalue()
+    buffer = io.StringIO()
+    df.to_csv(buffer, index=False)
+    return buffer.getvalue()
 
 with gr.Blocks() as demo:
-    gr.Markdown("# 🧠 LLM Questionnaire Response Tool")
-    gr.Markdown("Choose between **zero-shot classification** and **text generation**. Enter your questionnaire items, select a model, and view responses. You can download all results as a CSV.")
-
-    task_type = gr.Radio(["Zero-shot classification", "Text generation"], label="Task Type", value="Zero-shot classification")
-
-    with gr.Row():
-        model_selector = gr.Dropdown(label="Choose Model")
-        labels_input = gr.Textbox(label="Response Options (comma-separated)", visible=True)
+    gr.Markdown("## 🧠 Zero-Shot Classification Interface")
+    gr.Markdown("Enter questionnaire items and response options. The selected model will return probabilities for each label.")
 
+    model_dropdown = gr.Dropdown(choices=list(models.keys()), label="Choose Classification Model")
+    labels_input = gr.Textbox(label="Response Options (comma-separated)", placeholder="Strongly disagree, Disagree, Neutral, Agree, Strongly agree")
     questions_input = gr.Textbox(label="Questionnaire Items (one per line)", lines=10)
     output_box = gr.Textbox(label="Model Output", lines=20)
-    submit_btn = gr.Button("Run")
+    run_btn = gr.Button("Run Classification")
     download_btn = gr.Button("📥 Download CSV")
-    file_output = gr.File(label="CSV", visible=False)
-
-    def update_model_and_labels(task):
-        if task == "Zero-shot classification":
-            return gr.Dropdown.update(choices=list(zero_shot_models.keys()), value=list(zero_shot_models.keys())[0]), gr.Textbox.update(visible=True)
-        else:
-            return gr.Dropdown.update(choices=list(text_gen_models.keys()), value=list(text_gen_models.keys())[0]), gr.Textbox.update(visible=False)
-
-    task_type.change(fn=update_model_and_labels, inputs=task_type, outputs=[model_selector, labels_input])
-
-    def route_task(questions, labels, model_ui_name, task):
-        if task == "Zero-shot classification":
-            return run_classification(questions, labels, zero_shot_models[model_ui_name])
-        else:
-            return run_generation(questions, text_gen_models[model_ui_name])
+    csv_file = gr.File(label="CSV", visible=False)
 
-    submit_btn.click(fn=route_task, inputs=[questions_input, labels_input, model_selector, task_type], outputs=[output_box, file_output])
-    download_btn.click(fn=download_csv, inputs=[], outputs=file_output)
+    run_btn.click(fn=classify, inputs=[questions_input, labels_input, model_dropdown], outputs=[output_box, csv_file])
+    download_btn.click(fn=download_csv, inputs=[], outputs=csv_file)
 
 demo.launch()