Update app.py

app.py

@@ -1,44 +1,54 @@
 import streamlit as st
 import pandas as pd
-from datasets import load_dataset
-from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration
+import torch
+import faiss
+from sentence_transformers import SentenceTransformer
+from transformers import pipeline
 
-# Load AG News dataset from Hugging Face
-dataset = load_dataset("kk0105/ag-news", split="train")
+# Load model for embeddings and QA generation
+embedder = SentenceTransformer('all-MiniLM-L6-v2')
+generator = pipeline("text2text-generation", model="facebook/bart-large")
 
-# Tokenizer and Model setup for RAG
-tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-nq")
-retriever = RagRetriever.from_pretrained("facebook/rag-token-nq", index_name="default")
-model = RagSequenceForGeneration.from_pretrained("facebook/rag-token-nq")
+# Load your climate news dataset (title + description)
+@st.cache_data
+def load_data():
+    df = pd.read_csv("climate_news.csv")  # Make sure your zip extracts to this
+    df["text"] = df["title"].fillna('') + ". " + df["description"].fillna('')
+    return df
 
-# Function to generate response using RAG
-def generate_answer(query):
-    # Tokenize input query
-    inputs = tokenizer(query, return_tensors="pt")
+df = load_data()
+corpus = df["text"].tolist()
+corpus_embeddings = embedder.encode(corpus, convert_to_tensor=True)
 
-    # Retrieve relevant documents from dataset
-    input_ids = inputs["input_ids"]
-    question_embedding = retriever.compute_question_embeddings(input_ids)
-    context_input_ids = retriever.retrieve(input_ids, question_embedding)
+# Build FAISS index for fast similarity search
+index = faiss.IndexFlatL2(corpus_embeddings.shape[1])
+index.add(corpus_embeddings.cpu().detach().numpy())
 
-    # Generate an answer using the retrieved context
-    outputs = model.generate(input_ids=input_ids, context_input_ids=context_input_ids)
-    
-    # Decode the answer and return it
-    answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return answer
-
-# Streamlit interface
-st.title("News Fact Checker")
-st.write("""
-    **Welcome to the News Fact Checker!**
-    Input a claim or question about a news topic, and we will verify or refute it based on recent news snippets.
-""")
+st.title("🧠 Climate News Fact Checker")
 
-# User input for claim
-user_claim = st.text_input("Enter your claim or question:")
+user_input = st.text_input("Enter a claim or statement to verify:")
 
-if user_claim:
-    with st.spinner('Fetching relevant news snippets...'):
-        answer = generate_answer(user_claim)
-    st.write(f"**Fact Check Answer:** {answer}")
+if user_input:
+    # Embed the user query
+    query_embedding = embedder.encode([user_input])
+    
+    # Search similar news articles
+    top_k = 3
+    D, I = index.search(query_embedding, top_k)
+    
+    # Get the top matched articles
+    results = [corpus[i] for i in I[0]]
+    
+    # Display retrieved articles
+    st.subheader("🔍 Retrieved News Snippets")
+    for idx, res in enumerate(results):
+        st.write(f"**Snippet {idx+1}:** {res}")
+    
+    # Combine into context for generation
+    context = " ".join(results)
+    prompt = f"Claim: {user_input}\nContext: {context}\nAnswer:"
+    
+    # Generate answer
+    st.subheader("✅ Fact Check Result")
+    response = generator(prompt, max_length=100, do_sample=False)[0]['generated_text']
+    st.write(response)