Update app.py

app.py

@@ -1,25 +1,15 @@
 import streamlit as st
 import os
-from PIL import Image
-import numpy as np
 import pickle
+import numpy as np
 import tensorflow
 from tensorflow.keras.preprocessing import image
 from tensorflow.keras.layers import GlobalMaxPooling2D
 from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input
 from sklearn.neighbors import NearestNeighbors
 from numpy.linalg import norm
+from PIL import Image
 from chatbot import Chatbot  # Assuming you have a chatbot module
-import zipfile
-
-# Define the path to the zip file and the directory to extract to
-zip_file_path = 'images.zip'
-extract_to = 'images'
-
-# Check if the images directory already exists to avoid re-extracting
-if not os.path.exists(extract_to):
-    with zipfile.ZipFile(zip_file_path, 'r') as zip_ref:
-        zip_ref.extractall(extract_to)
 
 # Define function for feature extraction
 def feature_extraction(img_path, model):
@@ -57,7 +47,8 @@ def save_uploaded_file(uploaded_file):
 # Function to show dashboard content
 def show_dashboard():
     st.header("Fashion Recommender System")
-    chatbot = Chatbot()
+    chatbot = Chatbot()  # Load the chatbot, which will also load the dataset
+
     # Load ResNet model for image feature extraction
     model = ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
     model.trainable = False
@@ -66,16 +57,9 @@ def show_dashboard():
         GlobalMaxPooling2D()
     ])
 
-    try:
-        feature_list = np.array(pickle.load(open('embeddings.pkl', 'rb')))
-        filenames = pickle.load(open('filenames.pkl', 'rb'))
-    except Exception as e:
-        st.error(f"Error loading pickle files: {e}")
-        return
-
-    # Print the filenames to verify
-    st.write("List of filenames loaded:")
-    st.write(filenames)
+    # Feature list and filenames should be loaded from the same source as the chatbot
+    feature_list = np.array(chatbot.image_embeddings)  # Assuming you have embeddings loaded in the chatbot
+    filenames = chatbot.product_frame['productImageURL'].tolist()  # Adjust according to your dataset
 
     # File upload section
     uploaded_file = st.file_uploader("Choose an image")
@@ -109,16 +93,15 @@ def show_dashboard():
 
             for col, idx in zip(columns, indices[0]):
                 file_path = filenames[idx]
-                full_path = os.path.join(extract_to, os.path.basename(file_path))
-                st.write(f"Trying to open file: {full_path}")  # Add debug info
+                st.write(f"Trying to open file: {file_path}")  # Add debug info
                 try:
-                    if os.path.exists(full_path):
+                    if os.path.exists(file_path):
                         with col:
-                            st.image(full_path)
+                            st.image(file_path)
                     else:
-                        st.error(f"File does not exist: {full_path}")
+                        st.error(f"File does not exist: {file_path}")
                 except Exception as e:
-                    st.error(f"Error opening file {full_path}: {e}")
+                    st.error(f"Error opening file {file_path}: {e}")
         else:
             st.error("Some error occurred in file upload")