Update app.py

app.py

@@ -5,7 +5,7 @@ import os
 import json
 import io
 import subprocess  # To call process_hf_dataset.py
-from database import init_chromadb, populate_sample_db, store_program, query_programs, load_chromadb_from_hf, DB_NAME
+from database import init_chromadb, store_program, query_programs, load_chromadb_from_hf, DB_NAME
 
 # User-configurable variables
 UPLOAD_DIR = "./uploads"  # Directory for uploads
@@ -99,8 +99,23 @@ def index():
                 )
             except subprocess.CalledProcessError as e:
                 return f"Error processing Hugging Face dataset: {e}", 500
+        elif 'load_dataset' in request.form:
+            # Trigger loading of Hugging Face dataset without resetting
+            try:
+                subprocess.run(['python', 'process_hf_dataset.py'], check=True)
+                return render_template(
+                    'results_partial.html',
+                    parts=None,
+                    filename="Hugging Face Dataset Loaded",
+                    reconstructed_code=None,
+                    code_input=None,
+                    query_results=None,
+                    message="Hugging Face dataset loaded and stored successfully."
+                )
+            except subprocess.CalledProcessError as e:
+                return f"Error loading Hugging Face dataset: {e}", 500
         elif 'reset_db' in request.form:
-            # Reset ChromaDB collection
+            # Reset ChromaDB collection (no repopulation with samples)
             try:
                 client = init_chromadb()
                 try:
@@ -108,7 +123,6 @@ def index():
                 except:
                     pass  # Collection may not exist
                 client.create_collection(DB_NAME)
-                populate_sample_db(client)  # Optionally repopulate with samples
                 return render_template(
                     'results_partial.html',
                     parts=None,
@@ -116,7 +130,7 @@ def index():
                     reconstructed_code=None,
                     code_input=None,
                     query_results=None,
-                    message="Database reset and repopulated with samples successfully."
+                    message="Database reset successfully."
                 )
             except Exception as e:
                 return f"Error resetting database: {e}", 500
@@ -134,14 +148,7 @@ def index():
             )
         return 'No file, code, or query provided', 400
 
-    # Initial page load
-    client = load_chromadb_from_hf()
-    # If no dataset exists locally, populate with samples
-    try:
-        if not client.list_collections()[0].name == DB_NAME:
-            populate_sample_db(client)
-    except:
-        populate_sample_db(client)
+    # Initial page load (do not populate with samples automatically)
     return render_template('index.html', parts=None, filename=None, reconstructed_code=None, code_input=None, query_results=None)
 
 @app.route('/export_json', methods=['POST'])