created app.py

app.py

@@ -0,0 +1,58 @@
+import streamlit as st
+from helper import load_hf_datasets, search, get_file_paths, get_images_from_s3_to_display
+import os
+
+
+#Load environment variables
+AWS_ACCESS_KEY_ID = os.getenv("AWS_ACCESS_KEY_ID")
+AWS_SECRET_ACCESS_KEY = os.getenv("AWS_SECRET_ACCESS_KEY")
+# Predefined list of datasets
+datasets = ["WayveScenes", "StopSign_test"]  # Example dataset names
+
+# AWS S3 bucket name
+bucket_name = "datasets-quasara-io"
+
+# Streamlit App
+def main():
+    st.title("Semantic Search and Image Display")
+
+    # Select dataset from dropdown
+    dataset_name = st.selectbox("Select Dataset", datasets)
+    if dataset_name == 'WayveScenes':
+        folder_path = 'WayveScenes/'
+    else:
+        folder_path = ''
+    # Input search query
+    query = st.text_input("Enter your search query")
+
+    # Number of results to display
+    limit = st.number_input("Number of results to display", min_value=1, max_value=10, value=10)
+
+    # Search button
+    if st.button("Search"):
+        # Validate input
+        if not query:
+            st.warning("Please enter a search query.")
+        else:
+            # Load the selected dataset
+            df = load_hf_datasets(dataset_name)
+
+            # Perform the search
+            results = search(query, df, limit, 0, "cosine", search_in_images=True, search_in_small_objects=False)
+
+            # Get the S3 file paths of the top results
+            top_k_paths = get_file_paths(df, results)
+
+            # Display images from S3
+            if top_k_paths:
+                st.write(f"Displaying top {len(top_k_paths)} results for query '{query}':")
+
+                get_images_from_s3_to_display(bucket_name, top_k_paths,AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, folder_path)
+            else:
+                st.write("No results found.")
+
+if __name__ == "__main__":
+    main()
+
+
+#the query and the stuff is not really correlating