Update app.py

app.py

@@ -1,25 +1,42 @@
 import streamlit as st
+import os
+import cv2
+import torch
+import torchaudio
+import torchvision
+import tensorflow as tf
 from transformers import pipeline
+from groq import Groq
+from openai import OpenAI
 
-# Load Fake News Detection Model from Hugging Face
-fake_news_pipeline = pipeline("text-classification", model="mrm8488/bert-tiny-finetuned-fake-news-detection")
+# Set up the Groq client
+client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
 
-# Additional models (if available)
-try:
-    alternative_model = pipeline("text-classification", model="nlptown/bert-base-multilingual-uncased-sentiment")
-except:
-    alternative_model = None  # Fallback in case of failure
+# Load a fake news detection model from Hugging Face
+fake_news_pipeline = pipeline("text-classification", model="mrm8488/bert-tiny-finetuned-fake-news-detection")
 
 # Streamlit UI
 st.set_page_config(page_title="Fake News Detector", layout="wide")
 st.title("📰 Fake News Detector")
 
 # Tabs for Input and Results
-tab1, tab2, tab3 = st.tabs(["Input", "Results", "Reliable News Sources"])
+tab1, tab2 = st.tabs(["Input", "Results"])
+
+# Function to fetch real news links from various open sources
+def fetch_real_news_links():
+    return [
+        "https://www.bbc.com/news",
+        "https://www.cnn.com",
+        "https://www.reuters.com",
+        "https://huggingface.co/datasets/misinformation",
+        "https://www.wildfire.ai/deepfake-news-dataset",
+        "https://www.snopes.com",
+        "https://www.factcheck.org"
+    ]
 
 with tab1:
     st.sidebar.title("Select Input Type")
-    option = st.sidebar.radio("Choose an option", ["Text"])
+    option = st.sidebar.radio("Choose an option", ["Text", "Image", "Video Link"])
 
     if option == "Text":
         news_text = st.text_area("Enter the news content to check:", height=200)
@@ -29,59 +46,55 @@ with tab1:
             else:
                 st.session_state["news_text"] = news_text
                 st.session_state["analyze"] = True
-                st.rerun()
-                
+                st.experimental_rerun()
+
+    elif option == "Image":
+        uploaded_file = st.file_uploader("Upload an image of a news article", type=["jpg", "png", "jpeg"])
+        if uploaded_file is not None:
+            st.image(uploaded_file, caption="Uploaded Image", use_column_width=True)
+            st.info("🔍 Image analysis coming soon!")
+
+    elif option == "Video Link":
+        video_url = st.text_input("Enter a video news link to check")
+        if st.button("Analyze Video"):
+            if not video_url.strip():
+                st.warning("Please enter a valid URL.")
+            else:
+                st.info("🔍 Video analysis coming soon!")
 
 with tab2:
     if st.session_state.get("analyze", False):
         news_text = st.session_state.get("news_text", "")
         with st.spinner("Analyzing..."):
+            # Check using Groq API
+            chat_completion = client.chat.completions.create(
+                messages=[{"role": "user", "content": f"Classify this news as Real or Fake: {news_text}"}],
+                model="llama-3.3-70b-versatile",
+                stream=False,
+            )
+            groq_result = chat_completion.choices[0].message.content.strip().lower()
+            
             # Check using Hugging Face model
-            result = fake_news_pipeline(news_text)[0]['label'].lower()
-
-            # Alternative analysis if available
-            alternative_result = None
-            if alternative_model:
-                alternative_result = alternative_model(news_text)[0]['label'].lower()
-
-            # Decision logic
-            if "fake" in result or (alternative_result and "fake" in alternative_result):
+            hf_result = fake_news_pipeline(news_text)[0]['label'].lower()
+            
+            # Display result
+            if "fake" in groq_result or hf_result == "fake":
                 st.error("❌ This news is likely **Fake**!", icon="⚠️")
-                conclusion = "The analysis suggests that this news might be fabricated or misleading."
-            elif "real" in result or (alternative_result and "real" in alternative_result):
+                st.markdown('<style>div.stAlert {background-color: #ffdddd;}</style>', unsafe_allow_html=True)
+                conclusion = "The analysis suggests that this news might be fabricated or misleading. Please verify from credible sources."
+            elif "real" in groq_result or hf_result == "real":
                 st.success("✅ This news is likely **Real**!", icon="✅")
+                st.markdown('<style>div.stAlert {background-color: #ddffdd;}</style>', unsafe_allow_html=True)
                 conclusion = "The analysis indicates that this news appears to be credible and factual."
             else:
                 st.info("🤔 The result is uncertain. Please verify from trusted sources.")
-                conclusion = "Further verification is recommended."
-
+                conclusion = "There is uncertainty in the classification. Further verification is recommended."
+            
             # Conclusion Section
             st.subheader("📌 Conclusion")
             st.write(conclusion)
-
-with tab3:
-    st.subheader("🔗 Reliable News Sources")
-    reliable_sources = [
-        "https://www.bbc.com/news",
-        "https://www.cnn.com",
-        "https://www.reuters.com",
-        "https://www.nytimes.com",
-        "https://www.aljazeera.com",
-        "https://www.theguardian.com/international",
-        "https://www.washingtonpost.com",
-        "https://www.npr.org",
-        "https://www.apnews.com"
-    ]
-    for link in reliable_sources:
-        st.markdown(f"[🔗 {link}]({link})")
-
-    st.subheader("📚 Open Datasets for Fake News Detection")
-    datasets = [
-        "https://huggingface.co/datasets/misinformation/fake_news",
-        "https://huggingface.co/datasets/liar_dataset",
-        "https://huggingface.co/datasets/news-category-dataset",
-        "https://huggingface.co/datasets/ccdv/realnews",
-        "https://huggingface.co/datasets/Shoonya-Data/fact-verification"
-    ]
-    for dataset in datasets:
-        st.markdown(f"[📂 {dataset}]({dataset})")
+            
+            # Display real news sources
+            st.subheader("🔗 Reliable News Sources")
+            for link in fetch_real_news_links():
+                st.markdown(f"[🔗 {link}]({link})")