Update app.py

app.py

@@ -1,7 +1,5 @@
-# app.py
 import streamlit as st
 import os
-import tempfile
 from io import BytesIO
 from PyPDF2 import PdfReader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
@@ -59,7 +57,9 @@ with st.sidebar:
                 st.session_state.vectorstore = vector_store
                 st.success("File processed successfully. You can now ask questions.")
             except (PermissionError, OSError) as e:
-                st.error(f"Error processing file: {str(e)}. Check file permissions or server configuration.")
+                st.error(f"File upload failed (Permission or OS error): {str(e)}. Check server permissions or file system access.")
+            except Exception as e:
+                st.error(f"File upload failed (Unexpected error): {str(e)}. Please try again or check server logs.")
     
     # Display chat history
     st.subheader("Chat History")
@@ -133,57 +133,46 @@ def main():
             st.write("**Answer:**", answer)
 
 def process_input(input_data):
-    # Create uploads directory with proper permissions
+    # Create vectorstore directory for FAISS index
     try:
-        os.makedirs("uploads", exist_ok=True)
-        os.chmod("uploads", 0o777)  # Ensure write permissions
+        os.makedirs("vectorstore", exist_ok=True)
+        os.chmod("vectorstore", 0o777)  # Ensure write permissions
     except PermissionError as e:
-        st.error(f"Failed to create uploads directory: {str(e)}")
+        st.error(f"Failed to create vectorstore directory: {str(e)}")
         raise
     
     # Initialize progress bar and status
     progress_bar = st.progress(0)
     status = st.status("Processing PDF file...", expanded=True)
     
-    # Step 1: Save file temporarily
-    status.update(label="Saving PDF file...")
+    # Step 1: Read PDF file in memory
+    status.update(label="Reading PDF file...")
     progress_bar.progress(0.20)
     
-    with tempfile.NamedTemporaryFile(delete=False, dir="uploads", suffix=".pdf") as tmp_file:
-        tmp_file.write(input_data.read())
-        tmp_file_path = tmp_file.name
-    
-    # Step 2: Read PDF file
-    status.update(label="Reading PDF file...")
-    progress_bar.progress(0.40)
+    pdf_reader = PdfReader(BytesIO(input_data.read()))
+    documents = ""
+    for page in pdf_reader.pages:
+        documents += page.extract_text() or ""
     
-    try:
-        pdf_reader = PdfReader(tmp_file_path)
-        documents = ""
-        for page in pdf_reader.pages:
-            documents += page.extract_text() or ""
-    finally:
-        os.remove(tmp_file_path)  # Clean up temporary file
-    
-    # Step 3: Split text
+    # Step 2: Split text
     status.update(label="Splitting text into chunks...")
-    progress_bar.progress(0.60)
+    progress_bar.progress(0.40)
     
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
     texts = text_splitter.split_text(documents)
     
-    # Step 4: Create embeddings
+    # Step 3: Create embeddings
     status.update(label="Creating embeddings...")
-    progress_bar.progress(0.80)
+    progress_bar.progress(0.60)
     
     hf_embeddings = HuggingFaceEmbeddings(
         model_name="sentence-transformers/all-mpnet-base-v2",
         model_kwargs={'device': 'cpu'}
     )
     
-    # Step 5: Initialize FAISS vector store
+    # Step 4: Initialize FAISS vector store
     status.update(label="Building vector store...")
-    progress_bar.progress(0.90)
+    progress_bar.progress(0.80)
     
     dimension = len(hf_embeddings.embed_query("sample text"))
     index = faiss.IndexFlatL2(dimension)
@@ -199,6 +188,9 @@ def process_input(input_data):
     vector_store.add_texts(texts, ids=uuids)
     
     # Save vector store locally
+    status.update(label="Saving vector store...")
+    progress_bar.progress(0.90)
+    
     vector_store.save_local("vectorstore/faiss_index")
     
     # Complete processing