Create app.py

app.py

@@ -0,0 +1,53 @@
+import os
+import zipfile
+import pandas as pd
+import gradio as gr
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
+
+# Step 1: Unzip the dataset
+zip_file = "climate.zip"  # your uploaded zip file
+extracted_path = "climate_data"
+
+if not os.path.exists(extracted_path):
+    with zipfile.ZipFile(zip_file, 'r') as zip_ref:
+        zip_ref.extractall(extracted_path)
+
+# Step 2: Load train.csv
+csv_path = os.path.join(extracted_path, "train.csv")
+df = pd.read_csv(csv_path, header=None, names=["label", "title", "description"])
+
+# Combine title and description for semantic search
+df["content"] = df["title"].fillna("") + ". " + df["description"].fillna("")
+
+# Step 3: Encode using SentenceTransformer
+model = SentenceTransformer('all-MiniLM-L6-v2')
+corpus_embeddings = model.encode(df["content"].tolist(), show_progress_bar=True)
+
+# Step 4: Create FAISS index
+embedding_dim = corpus_embeddings.shape[1]
+index = faiss.IndexFlatL2(embedding_dim)
+index.add(corpus_embeddings)
+
+def retrieve_and_respond(claim, k=5):
+    query_embedding = model.encode([claim])
+    D, I = index.search(np.array(query_embedding), k)
+    
+    results = []
+    for idx in I[0]:
+        row = df.iloc[idx]
+        results.append(f"*Title:* {row['title']}\n*Description:* {row['description']}\n*Label:* {row['label']}\n")
+    
+    return "\n\n".join(results)
+
+# Step 5: Gradio Interface
+iface = gr.Interface(
+    fn=retrieve_and_respond,
+    inputs=gr.Textbox(lines=2, placeholder="Enter a news-related claim here..."),
+    outputs="markdown",
+    title="Claim Verifier using RAG (AG News)",
+    description="Enter a claim and retrieve the most relevant AG News articles to verify or refute it."
+)
+
+iface.launch()