Update app.py

app.py

@@ -1,51 +1,53 @@
 import streamlit as st
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-import torch
+import zipfile
+import os
 import pandas as pd
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
 
+# Paths
+ZIP_FILE = "xnli-multilingual-nli-dataset.zip"
+EXTRACT_DIR = "extracted_data"
+
+@st.cache_data
+def extract_and_load():
+    if not os.path.exists(EXTRACT_DIR):
+        with zipfile.ZipFile(ZIP_FILE, "r") as zip_ref:
+            zip_ref.extractall(EXTRACT_DIR)
+    csv_files = [f for f in os.listdir(EXTRACT_DIR) if f.endswith('.csv')]
+    return csv_files
+
+# Load model and tokenizer
 @st.cache_resource
 def load_model():
-    model_name = "MoritzLaurer/mDeBERTa-v3-base-mnli-xnli"
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    model = AutoModelForSequenceClassification.from_pretrained(model_name)
-    return tokenizer, model
+    tokenizer = AutoTokenizer.from_pretrained("MoritzLaurer/mDeBERTa-v3-base-mnli-xnli")
+    model = AutoModelForSequenceClassification.from_pretrained("MoritzLaurer/mDeBERTa-v3-base-mnli-xnli")
+    nli_pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer)
+    return nli_pipeline
 
-@st.cache_data
-def load_sample_data():
-    # Assuming you've uploaded the CSV to Hugging Face Space `/app` directory
-    try:
-        df = pd.read_csv("xnli_sample.csv")  # rename appropriately
-        return df[['premise', 'hypothesis', 'label']]
-    except FileNotFoundError:
-        return pd.DataFrame(columns=["premise", "hypothesis", "label"])
-
-def predict_label(premise, hypothesis, tokenizer, model):
-    inputs = tokenizer(premise, hypothesis, return_tensors="pt", truncation=True, padding=True)
-    with torch.no_grad():
-        outputs = model(**inputs)
-        probs = torch.nn.functional.softmax(outputs.logits, dim=1)
-    label_id = torch.argmax(probs).item()
-    labels = model.config.id2label
-    return labels[label_id], probs[0][label_id].item()
-
-st.set_page_config(page_title="Multilingual RAG NLI App", layout="wide")
-st.title("Multilingual NLI with mDeBERTa-v3")
-
-tokenizer, model = load_model()
-
-st.subheader("Check Natural Language Inference")
-premise = st.text_input("Premise", "A man inspects the uniform of a figure in some East Asian country.")
-hypothesis = st.text_input("Hypothesis", "The man is sleeping.")
-
-if st.button("Predict"):
-    label, confidence = predict_label(premise, hypothesis, tokenizer, model)
-    st.success(f"Prediction: {label} ({confidence:.2f} confidence)")
-
-st.markdown("---")
-st.subheader("Explore Sample Data")
-
-df = load_sample_data()
-if not df.empty:
-    st.dataframe(df.sample(10))
-else:
-    st.warning("Upload a file named `xnli_sample.csv` for sample data display.")
+st.set_page_config(page_title="Multilingual NLI App", layout="centered")
+
+st.title("🌍 Multilingual NLI (Natural Language Inference) Explorer")
+st.markdown("Upload premise & hypothesis pairs or use the dataset to explore entailment, contradiction, or neutrality.")
+
+nli_pipeline = load_model()
+
+csv_files = extract_and_load()
+selected_csv = st.selectbox("Choose a language CSV file:", csv_files)
+
+df = pd.read_csv(os.path.join(EXTRACT_DIR, selected_csv)).dropna()
+sample_df = df.sample(5).reset_index(drop=True)
+
+st.subheader("Sample from Dataset")
+st.dataframe(sample_df[['premise', 'hypothesis', 'label']])
+
+st.subheader("🔍 Run Inference")
+index = st.number_input("Select Sample Index", min_value=0, max_value=len(sample_df)-1, value=0, step=1)
+premise = sample_df.loc[index, 'premise']
+hypothesis = sample_df.loc[index, 'hypothesis']
+
+st.markdown(f"**Premise:** {premise}")
+st.markdown(f"**Hypothesis:** {hypothesis}")
+
+if st.button("Run NLI Prediction"):
+    result = nli_pipeline(f"{premise} </s> {hypothesis}")
+    st.success(f"**Prediction:** {result[0]['label']} (Score: {result[0]['score']:.2f})")