Update app.py

app.py

@@ -1,8 +1,8 @@
 import streamlit as st
-# Set page config as the very first Streamlit command
+# This MUST be the first Streamlit command
 st.set_page_config(page_title="Advanced File Downloader", layout="wide")
 
-# Now import all other libraries
+# Now all other imports
 import os
 import subprocess
 from playwright.async_api import async_playwright, TimeoutError as PlaywrightTimeoutError
@@ -19,34 +19,42 @@ import zipfile
 import tempfile
 import mimetypes
 import requests
-
-# -------------------- spaCy Model Setup --------------------
 import spacy
 import spacy.cli
 from spacy.language import Language
+from sentence_transformers import SentenceTransformer, util
+from transformers import pipeline
 
-@Language.factory("spacy-curated-transformers_RobertaTransformer_v1")
-def dummy_roberta_transformer(nlp, name):
-    def dummy(doc):
-        return doc
-    return dummy
+# Initialize logging
+logging.basicConfig(
+    filename='advanced_download_log.txt',
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger()
 
+# Model initialization with caching
 @st.cache_resource
-def load_nlp_model():
+def initialize_models():
+    # spaCy
     try:
-        try:
-            nlp_model = spacy.load("en_core_web_sm")
-        except OSError:
-            st.write("Model en_core_web_sm not found. Downloading it now...")
-            spacy.cli.download("en_core_web_sm")
-            nlp_model = spacy.load("en_core_web_sm")
-    except Exception as e:
-        st.error(f"Error loading model: {e}")
-        return None
-    return nlp_model
+        nlp = spacy.load("en_core_web_sm")
+    except OSError:
+        spacy.cli.download("en_core_web_sm")
+        nlp = spacy.load("en_core_web_sm")
+    
+    # SentenceTransformer
+    semantic_model = SentenceTransformer('all-MiniLM-L6-v2')
+    
+    # Transformers
+    summarizer = pipeline("summarization")
+    
+    return nlp, semantic_model, summarizer
+
+# Initialize models
+nlp_model, semantic_model, summarizer = initialize_models()
 
-# Load models after page config
-nlp_model = load_nlp_model()
+# Rest of your code...