Create app.py

app.py

@@ -0,0 +1,52 @@
+import streamlit as st
+import pandas as pd
+import zipfile
+import os
+from sentence_transformers import SentenceTransformer, util
+from transformers import pipeline
+
+# Constants
+ZIP_FILE = "xnli-multilingual-nli-dataset.zip"
+CSV_FILE = "en_test.csv"
+EXTRACT_FOLDER = "extracted_data"
+
+# Load and extract ZIP
+@st.cache_data
+def extract_and_load():
+    if not os.path.exists(EXTRACT_FOLDER):
+        with zipfile.ZipFile(ZIP_FILE, "r") as zip_ref:
+            zip_ref.extractall(EXTRACT_FOLDER)
+    csv_path = os.path.join(EXTRACT_FOLDER, CSV_FILE)
+    df = pd.read_csv(csv_path).dropna().sample(500)
+    return df[['premise', 'hypothesis', 'label']]
+
+df = extract_and_load()
+
+# Load models
+nli_model = pipeline("text-classification", model="joeddav/xlm-roberta-large-xnli")
+embedder = SentenceTransformer("sentence-transformers/distiluse-base-multilingual-cased-v2")
+
+# UI
+st.title("🌐 Multilingual RAG-style NLI Explorer")
+st.markdown("Enter a sentence in **any language**, and the app will find a related statement from the dataset and infer their relationship.")
+
+user_input = st.text_input("Enter your **hypothesis** (your own sentence):")
+
+if user_input:
+    with st.spinner("Finding most relevant premise..."):
+        premise_embeddings = embedder.encode(df['premise'].tolist(), convert_to_tensor=True)
+        user_embedding = embedder.encode(user_input, convert_to_tensor=True)
+
+        top_hit = util.semantic_search(user_embedding, premise_embeddings, top_k=1)[0][0]
+        match_idx = top_hit['corpus_id']
+        selected_premise = df.iloc[match_idx]['premise']
+
+        st.subheader("🔍 Most Relevant Premise:")
+        st.write(selected_premise)
+
+        # Run NLI classification
+        full_input = f"{selected_premise} </s> {user_input}"
+        result = nli_model(full_input)[0]
+
+        st.subheader("🧠 Predicted Relationship:")
+        st.write(f"**{result['label']}** (confidence: {result['score']:.2f})")