Update app.py

app.py

@@ -4,6 +4,7 @@ import PyPDF2
 from PIL import Image
 import pytesseract
 import speech_recognition as sr
+import docx
 import tempfile
 import os
 
@@ -42,18 +43,34 @@ def extract_text_from_video(video_file):
     return r.recognize_google(audio_data)
 
 
+# Function to extract text from a TXT file
+def extract_text_from_txt(txt_file):
+    return txt_file.read().decode("utf-8")
+
+
+# Function to extract text from a Word document
+def extract_text_from_word(docx_file):
+    doc = docx.Document(docx_file)
+    text = "\n".join([paragraph.text for paragraph in doc.paragraphs])
+    return text
+
+
 # Function to process files and generate embeddings
 def process_file(file):
-    file_type = file.type.split('/')[0]
+    file_type = file.type.split('/')[1]
     content = ""
 
     try:
-        if file_type == 'application':  # Documents like PDFs
+        if file.type == 'application/pdf':  # PDF files
             content = extract_text_from_pdf(file)
-        elif file_type == 'image':  # Images
+        elif file.type in ['image/png', 'image/jpeg']:  # Images
             content = extract_text_from_image(file)
-        elif file_type == 'video':  # Videos
+        elif file.type == 'video/mp4':  # Videos
             content = extract_text_from_video(file)
+        elif file.type == 'text/plain':  # TXT files
+            content = extract_text_from_txt(file)
+        elif file.name.endswith('.docx'):  # Word documents
+            content = extract_text_from_word(file)
     except Exception as e:
         st.error(f"Error processing file {file.name}: {e}")
 
@@ -70,7 +87,11 @@ st.title("AI-based Text Search for Files")
 st.write("Upload documents, images, or videos, and perform AI-powered text search.")
 
 # File upload section
-uploaded_files = st.file_uploader("Upload your files", type=['pdf', 'png', 'jpg', 'jpeg', 'mp4'], accept_multiple_files=True)
+uploaded_files = st.file_uploader(
+    "Upload your files", 
+    type=['pdf', 'png', 'jpg', 'jpeg', 'mp4', 'txt', 'docx'], 
+    accept_multiple_files=True
+)
 if uploaded_files:
     for file in uploaded_files:
         process_file(file)