Update app.py

app.py

@@ -5,7 +5,8 @@ from dotenv import load_dotenv
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 from llama_index.core import Settings
 import os
-import base64
+from youtube_transcript_api import YouTubeTranscriptApi
+import shutil
 import time
 
 # Load environment variables
@@ -46,7 +47,32 @@ def data_ingestion():
     storage_context = StorageContext.from_defaults()
     index = VectorStoreIndex.from_documents(documents,show_progress=True)
     index.storage_context.persist(persist_dir=PERSIST_DIR)
+    
+def extract_transcript_details(youtube_video_url):
+    try:
+        video_id=youtube_video_url.split("=")[1]
+        
+        transcript_text=YouTubeTranscriptApi.get_transcript(video_id)
+
+        transcript = ""
+        for i in transcript_text:
+            transcript += " " + i["text"]
+       
+        return transcript
+
+    except Exception as e:
+        st.error(e)
 
+def remove_old_files():
+    # Specify the directory path you want to clear
+    directory_path = "data"
+
+    # Remove all files and subdirectories in the specified directory
+    shutil.rmtree(directory_path)
+
+    # Recreate an empty directory if needed
+    os.makedirs(directory_path)
+    
 def handle_query(query):
     storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
     index = load_index_from_storage(storage_context)
@@ -96,12 +122,22 @@ for message in st.session_state.messages:
 with st.sidebar:
     st.title("Menu:")
     uploaded_file = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button")
+    video_url = st.text_input("Enter Youtube Video Link: ")
     if st.button("Submit & Process"):
         with st.spinner("Processing..."):
-            filepath = "data/saved_pdf.pdf"
-            with open(filepath, "wb") as f:
-                f.write(uploaded_file.getbuffer())
-            # displayPDF(filepath)  # Display the uploaded PDF
+            if len(os.listdir("data")) !=0:
+                remove_old_files()
+                
+            if uploaded_file:
+                filepath = "data/saved_pdf.pdf"
+                with open(filepath, "wb") as f:
+                    f.write(uploaded_file.getbuffer())
+        
+            if video_url:
+                extracted_text = extract_transcript_details(video_url)
+                with open("data/saved_text.txt", "w") as file:
+                    file.write(extracted_text)
+                
             data_ingestion()  # Process PDF every time new file is uploaded
             st.success("Done")