cleanup

emb/api.py

@@ -66,15 +66,15 @@ async def embed_text(text: str) -> List[float]:
 #     "   data": [app.title for app in apps]
 #     }
 
-def my_periodic_task():
+def embed_periodically():
     print("Performing a periodic task every 5 minutes.")
 
 @app.on_event("startup")
 def start_scheduler():
     scheduler.add_job(
-        my_periodic_task,
-        trigger=IntervalTrigger(minutes=5),
-        id="my_periodic_task",  # ID for this job
+        embed_periodically,
+        trigger=IntervalTrigger(minutes=int(config("EMBED_FREQUENCY", default=5))),
+        id="embed_periodically", 
         replace_existing=True,
     )
     scheduler.start()

emb/db_model.py

@@ -117,7 +117,7 @@ def generate_data_in_auctions(data_file_path):
     # load extensions
     load_pg_extensions()
 
-    data_file_path = 'test_data.csv'
+    data_file_path = 'auctions_data.csv'
     logger.info(f"Going to load data from {data_file_path}")
     generate_data_in_auctions(data_file_path)
     logger.info("Done")

nb/sql.ipynb

@@ -9,10 +9,10 @@
    },
    "outputs": [],
    "source": [
-    "from sqlalchemy import create_engine\n",
+    "from sqlalchemy import create_engine, text\n",
     "import pandas as pd\n",
     "\n",
-    "db_con = create_engine('postgresql://postgres:argmax@pg:5432/postgres')\n"
+    "engine = create_engine('postgresql://postgres:argmax@pg:5432/postgres')\n"
    ]
   },
   {
@@ -82,14 +82,11 @@
     }
    ],
    "source": [
-    "\n",
-    "\n",
-    "# Define your SQL query\n",
     "sql_query = 'SELECT * FROM auctions;'\n",
+    "with engine.connect() as db_con:\n",
+    "    df = pd.read_sql(sql_query, con=db_con)\n",
     "\n",
-    "df = pd.read_sql(sql_query, con=db_con)\n",
-    "\n",
-    "print(df)\n"
+    "df\n"
    ]
   },
   {