Update app.py

app.py

@@ -1,97 +1,50 @@
 import streamlit as st
+import os
 from pdf2image import convert_from_path
+from PIL import Image
 import pytesseract
-import os
-from pathlib import Path
-from sentence_transformers import SentenceTransformer
-import pinecone
-import tempfile
-import shutil
-
-# Debug: Check PATH and pdfinfo accessibility
-st.write("System PATH:", os.environ["PATH"])
-if shutil.which("pdfinfo") is None:
-    st.error("pdfinfo is not found in the current environment. Please check your PATH.")
-else:
-    st.success("pdfinfo found and accessible.")
-
-# Initialize Streamlit app
-st.title("PDF Image to Text/Word Converter with Search Capability")
-st.write("Upload your PDF to extract text or Word document and search content within it.")
 
-# Create a temporary directory
-temp_dir = tempfile.mkdtemp()
+# Ensure Poppler is in the PATH (you might need to adjust this for your server)
+os.environ["PATH"] += ":/usr/local/bin"  # Update this with the correct Poppler path if needed
 
-# Upload PDF file
-uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
-
-if uploaded_file:
-    pdf_path = Path(temp_dir) / uploaded_file.name
-    with open(pdf_path, "wb") as f:
-        f.write(uploaded_file.read())
-
-    st.write("File uploaded successfully!")
-
-    # Convert PDF pages to images
-    st.write("Converting PDF to images...")
+def pdf_to_text(pdf_path):
     try:
-        images = convert_from_path(pdf_path, output_folder=temp_dir, poppler_path="/usr/bin")  # Update path as needed
+        # Convert PDF to images
+        images = convert_from_path(pdf_path)
+        text = ""
+        
+        for image in images:
+            text += pytesseract.image_to_string(image)
+        
+        return text
     except Exception as e:
         st.error(f"Error during PDF to image conversion: {e}")
-        st.stop()
-
-    # Extract text from images
-    st.write("Extracting text from images...")
-    extracted_text = ""
-    for idx, image in enumerate(images):
-        st.image(image, caption=f"Page {idx + 1}", use_column_width=True)
-        text = pytesseract.image_to_string(image)
-        extracted_text += text + "\n"
-
-    # Save extracted text to a .txt file
-    text_file_path = Path(temp_dir) / "extracted_text.txt"
-    with open(text_file_path, "w", encoding="utf-8") as text_file:
-        text_file.write(extracted_text)
-
-    st.success("Text extraction complete!")
-
-    # Option to download text file
-    st.download_button(
-        label="Download Extracted Text",
-        data=extracted_text,
-        file_name="extracted_text.txt",
-        mime="text/plain",
-    )
-
-    # Initialize vector model and Pinecone
-    st.write("Initializing vector search...")
-    model = SentenceTransformer('all-MiniLM-L6-v2')
-    pinecone.init(api_key="YOUR_PINECONE_API_KEY", environment="us-west1-gcp")  # Replace with your Pinecone details
-
-    # Create Pinecone index if it doesn't exist
-    index_name = "pdf-text-index"
-    if index_name not in pinecone.list_indexes():
-        pinecone.create_index(index_name, dimension=384)
-    index = pinecone.Index(index_name)
-
-    # Generate vector embeddings and upload to Pinecone
-    st.write("Generating vector embeddings...")
-    sentences = extracted_text.split("\n")
-    embeddings = model.encode(sentences)
-    for i, embedding in enumerate(embeddings):
-        index.upsert([(f"sentence-{i}", embedding, {"sentence": sentences[i]})])
-
-    # Search functionality
-    st.write("Search within the extracted text")
-    query = st.text_input("Enter your query:")
-    if query:
-        query_vector = model.encode([query])[0]
-        results = index.query(query_vector, top_k=5, include_metadata=True)
-        st.write("Top results:")
-        for match in results["matches"]:
-            st.write(f"Score: {match['score']}, Text: {match['metadata']['sentence']}")
-
-# Cleanup temporary files
-if st.button("Clean Temporary Files"):
-    shutil.rmtree(temp_dir)
-    st.success("Temporary files cleaned!")
+        return None
+
+def main():
+    st.title("PDF to Text Converter")
+    
+    # Upload PDF file
+    uploaded_file = st.file_uploader("Upload a PDF", type="pdf")
+    
+    if uploaded_file is not None:
+        # Save uploaded file temporarily
+        with open("uploaded_file.pdf", "wb") as f:
+            f.write(uploaded_file.getbuffer())
+        
+        st.text("Converting PDF to text...")
+        
+        text = pdf_to_text("uploaded_file.pdf")
+        
+        if text:
+            st.text_area("Extracted Text", text, height=300)
+            
+            # Create downloadable Word file
+            word_file = "output.docx"
+            with open(word_file, "w") as f:
+                f.write(text)
+                
+            st.download_button("Download Word File", word_file)
+    
+if __name__ == "__main__":
+    main()