MIME type handler proof-of-concept

notebooks/google_drive_web_vtt_vectorizer_and_storer.ipynb

@@ -11,31 +11,7 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:08:14.649\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.core.config\u001b[0m:\u001b[36m__init__\u001b[0m:\u001b[36m14\u001b[0m - \u001b[34m\u001b[1mCreated Settings\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:14.652\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.google_drive_service\u001b[0m:\u001b[36m__init__\u001b[0m:\u001b[36m44\u001b[0m - \u001b[34m\u001b[1mCreated GoogleDriveService\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:14.664\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.embeddings_model_service\u001b[0m:\u001b[36m__init__\u001b[0m:\u001b[36m22\u001b[0m - \u001b[34m\u001b[1mCreated EmbeddingsModelService\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:14.664\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vectorization_service\u001b[0m:\u001b[36m__init__\u001b[0m:\u001b[36m22\u001b[0m - \u001b[34m\u001b[1mCreated VectorizationService\u001b[0m\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:08:14.666\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36minit\u001b[0m:\u001b[36m175\u001b[0m - \u001b[1mInitializing MongoDB connection for database: ctp_slack_bot_dev\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:14.666\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36m__init__\u001b[0m:\u001b[36m26\u001b[0m - \u001b[34m\u001b[1mCreated MongoDB\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:14.667\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mconnect\u001b[0m:\u001b[36m32\u001b[0m - \u001b[34m\u001b[1mConnecting to MongoDB using URI: mongodb+srv://ctp-slack-bot.xkipuvm.mongodb.net/?retryWrites=true&w=majority&appName=ctp-slack-bot\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:14.667\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mconnect\u001b[0m:\u001b[36m49\u001b[0m - \u001b[34m\u001b[1mMongoDB client initialized for database: ctp_slack_bot_dev\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:15.043\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:15.044\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36m_test_connection\u001b[0m:\u001b[36m186\u001b[0m - \u001b[1mMongoDB connection test successful!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:15.044\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36m__init__\u001b[0m:\u001b[36m21\u001b[0m - \u001b[34m\u001b[1mCreated VectorDatabaseService\u001b[0m\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from datetime import datetime\n",
     "from functools import partial\n",
@@ -51,9 +27,10 @@
     "display_html = partial(display_html, raw=True)\n",
     "\n",
     "container = Container()\n",
+    "mongo_db = await container.mongo_db()\n",
     "google_drive_service = container.google_drive_service()\n",
     "vectorization_service = container.vectorization_service()\n",
-    "vector_database_service = container.vector_database_service()"
+    "vector_database_service = await container.vector_database_service()"
    ]
   },
   {
@@ -67,7 +44,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -85,64 +62,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<p>Found 11 files/folders.</p>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<ul><li>/Friday Building AI Applications Session</li><li>/Friday Building AI Applications Session/GMT20250411-223535_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250404-231749_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250328-223256_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250321-223330_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250314-223145_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250307-233135_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250228-233632_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250221-233332_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250214-234809_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250207-233258_Recording.transcript.vtt</li></ul>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<p>11 files/folders pass the modification time (<em>2024-08-30 00:00:00+00:00</em>) cut-off.</p>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<ul><li>/Friday Building AI Applications Session</li><li>/Friday Building AI Applications Session/GMT20250411-223535_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250404-231749_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250328-223256_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250321-223330_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250314-223145_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250307-233135_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250228-233632_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250221-233332_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250214-234809_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250207-233258_Recording.transcript.vtt</li></ul>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<p>11 files/folders pass the modification time (<em>2024-08-30 00:00:00+00:00</em>) cut-off and MIME type (<em>text/vtt</em>) criterion.</p>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<ul><li>/Friday Building AI Applications Session/GMT20250411-223535_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250404-231749_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250328-223256_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250321-223330_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250314-223145_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250307-233135_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250228-233632_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250221-233332_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250214-234809_Recording.transcript.vtt</li><li>/Friday Building AI Applications Session/GMT20250207-233258_Recording.transcript.vtt</li></ul>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "item_metadata = google_drive_service.list_directory(\"\", True)\n",
     "display_html(f\"<p>Found {len(item_metadata)} files/folders.</p>\")\n",
@@ -159,27 +81,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "web_vtt_parser = container.mime_type_handler_factory(MIME_TYPE)\n",
+    "display_html(f\"<p>{escape(str(type(web_vtt_parser)))}</p>\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "Processed 10 files."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "web_vtts = tuple(WebVTTContent.from_bytes(f\"googledrive:{metadata.folder_path}/{metadata.name}\",\n",
-    "                                          {\n",
-    "                                              \"filename\": metadata.name,\n",
-    "                                              \"mimeType\": metadata.mime_type,\n",
-    "                                              \"modificationTime\": metadata.modified_time\n",
-    "                                          },\n",
-    "                                          google_drive_service.read_file_by_id(metadata.id))\n",
+    "web_vtts = tuple(web_vtt_parser.from_bytes(f\"googledrive:{metadata.folder_path}/{metadata.name}\",\n",
+    "                                           {\n",
+    "                                               \"filename\": metadata.name,\n",
+    "                                               \"mimeType\": metadata.mime_type,\n",
+    "                                               \"modificationTime\": metadata.modified_time\n",
+    "                                           },\n",
+    "                                           google_drive_service.read_file_by_id(metadata.id))\n",
     "            for metadata\n",
     "            in metadata_to_process)\n",
     "\n",
@@ -188,528 +110,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "Chunked GMT20250411-223535_Recording.transcript.vtt into 86 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:08:52.269\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.embeddings_model_service\u001b[0m:\u001b[36mget_embeddings\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCreating embeddings for 86 text string(s)…\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Vectorized GMT20250411-223535_Recording.transcript.vtt’s 86 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:08:54.190\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m38\u001b[0m - \u001b[34m\u001b[1mGetting vectors collection for storing 86 chunks\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:54.216\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:54.217\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:54.240\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m110\u001b[0m - \u001b[1mCollection 'vectors' does not exist. Creating it…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:54.301\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m113\u001b[0m - \u001b[34m\u001b[1mSuccessfully created collection: vectors\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:54.302\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m42\u001b[0m - \u001b[34m\u001b[1mCreating vector search index for vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:54.320\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:54.321\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:54.341\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:54.491\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mcreate_indexes\u001b[0m:\u001b[36m153\u001b[0m - \u001b[1mVector search index 'vectors_vector_index' created for collection vectors.\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:54.494\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m62\u001b[0m - \u001b[34m\u001b[1mInserting 86 documents into vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:55.239\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m64\u001b[0m - \u001b[1mStored 86 vector chunks in database\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Stored GMT20250411-223535_Recording.transcript.vtt’s 86 vectorized chunks to the database."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "Chunked GMT20250404-231749_Recording.transcript.vtt into 56 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:08:55.241\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.embeddings_model_service\u001b[0m:\u001b[36mget_embeddings\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCreating embeddings for 56 text string(s)…\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Vectorized GMT20250404-231749_Recording.transcript.vtt’s 56 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:08:56.099\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m38\u001b[0m - \u001b[34m\u001b[1mGetting vectors collection for storing 56 chunks\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:56.119\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:56.120\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:56.151\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:56.151\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m42\u001b[0m - \u001b[34m\u001b[1mCreating vector search index for vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:56.170\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:56.170\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:56.199\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:56.341\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mcreate_indexes\u001b[0m:\u001b[36m153\u001b[0m - \u001b[1mVector search index 'vectors_vector_index' created for collection vectors.\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:56.341\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m62\u001b[0m - \u001b[34m\u001b[1mInserting 56 documents into vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:08:56.732\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m64\u001b[0m - \u001b[1mStored 56 vector chunks in database\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Stored GMT20250404-231749_Recording.transcript.vtt’s 56 vectorized chunks to the database."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "Chunked GMT20250328-223256_Recording.transcript.vtt into 359 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:08:56.735\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.embeddings_model_service\u001b[0m:\u001b[36mget_embeddings\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCreating embeddings for 359 text string(s)…\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Vectorized GMT20250328-223256_Recording.transcript.vtt’s 359 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:00.360\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m38\u001b[0m - \u001b[34m\u001b[1mGetting vectors collection for storing 359 chunks\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:00.384\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:00.384\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:00.404\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:00.404\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m42\u001b[0m - \u001b[34m\u001b[1mCreating vector search index for vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:00.424\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:00.424\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:00.445\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:00.588\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mcreate_indexes\u001b[0m:\u001b[36m153\u001b[0m - \u001b[1mVector search index 'vectors_vector_index' created for collection vectors.\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:00.590\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m62\u001b[0m - \u001b[34m\u001b[1mInserting 359 documents into vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:04.394\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m64\u001b[0m - \u001b[1mStored 359 vector chunks in database\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Stored GMT20250328-223256_Recording.transcript.vtt’s 359 vectorized chunks to the database."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "Chunked GMT20250321-223330_Recording.transcript.vtt into 314 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:04.397\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.embeddings_model_service\u001b[0m:\u001b[36mget_embeddings\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCreating embeddings for 314 text string(s)…\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Vectorized GMT20250321-223330_Recording.transcript.vtt’s 314 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:07.348\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m38\u001b[0m - \u001b[34m\u001b[1mGetting vectors collection for storing 314 chunks\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:07.369\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:07.370\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:07.389\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:07.389\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m42\u001b[0m - \u001b[34m\u001b[1mCreating vector search index for vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:07.410\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:07.410\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:07.430\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:07.566\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mcreate_indexes\u001b[0m:\u001b[36m153\u001b[0m - \u001b[1mVector search index 'vectors_vector_index' created for collection vectors.\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:07.568\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m62\u001b[0m - \u001b[34m\u001b[1mInserting 314 documents into vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:11.153\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m64\u001b[0m - \u001b[1mStored 314 vector chunks in database\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Stored GMT20250321-223330_Recording.transcript.vtt’s 314 vectorized chunks to the database."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "Chunked GMT20250314-223145_Recording.transcript.vtt into 331 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:11.157\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.embeddings_model_service\u001b[0m:\u001b[36mget_embeddings\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCreating embeddings for 331 text string(s)…\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Vectorized GMT20250314-223145_Recording.transcript.vtt’s 331 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:14.751\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m38\u001b[0m - \u001b[34m\u001b[1mGetting vectors collection for storing 331 chunks\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:14.774\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:14.774\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:14.794\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:14.794\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m42\u001b[0m - \u001b[34m\u001b[1mCreating vector search index for vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:14.813\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:14.813\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:14.834\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:14.948\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mcreate_indexes\u001b[0m:\u001b[36m153\u001b[0m - \u001b[1mVector search index 'vectors_vector_index' created for collection vectors.\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:14.950\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m62\u001b[0m - \u001b[34m\u001b[1mInserting 331 documents into vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:18.640\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m64\u001b[0m - \u001b[1mStored 331 vector chunks in database\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Stored GMT20250314-223145_Recording.transcript.vtt’s 331 vectorized chunks to the database."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "Chunked GMT20250307-233135_Recording.transcript.vtt into 280 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:18.643\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.embeddings_model_service\u001b[0m:\u001b[36mget_embeddings\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCreating embeddings for 280 text string(s)…\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Vectorized GMT20250307-233135_Recording.transcript.vtt’s 280 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:22.256\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m38\u001b[0m - \u001b[34m\u001b[1mGetting vectors collection for storing 280 chunks\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:22.278\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:22.279\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:22.297\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:22.297\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m42\u001b[0m - \u001b[34m\u001b[1mCreating vector search index for vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:22.344\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:22.345\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:22.368\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:22.505\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mcreate_indexes\u001b[0m:\u001b[36m153\u001b[0m - \u001b[1mVector search index 'vectors_vector_index' created for collection vectors.\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:22.507\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m62\u001b[0m - \u001b[34m\u001b[1mInserting 280 documents into vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:24.988\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m64\u001b[0m - \u001b[1mStored 280 vector chunks in database\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Stored GMT20250307-233135_Recording.transcript.vtt’s 280 vectorized chunks to the database."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "Chunked GMT20250228-233632_Recording.transcript.vtt into 233 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:24.991\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.embeddings_model_service\u001b[0m:\u001b[36mget_embeddings\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCreating embeddings for 233 text string(s)…\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Vectorized GMT20250228-233632_Recording.transcript.vtt’s 233 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:28.628\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m38\u001b[0m - \u001b[34m\u001b[1mGetting vectors collection for storing 233 chunks\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:28.648\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:28.649\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:28.669\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:28.669\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m42\u001b[0m - \u001b[34m\u001b[1mCreating vector search index for vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:28.688\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:28.688\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:28.709\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:28.836\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mcreate_indexes\u001b[0m:\u001b[36m153\u001b[0m - \u001b[1mVector search index 'vectors_vector_index' created for collection vectors.\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:28.838\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m62\u001b[0m - \u001b[34m\u001b[1mInserting 233 documents into vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:31.039\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m64\u001b[0m - \u001b[1mStored 233 vector chunks in database\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Stored GMT20250228-233632_Recording.transcript.vtt’s 233 vectorized chunks to the database."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "Chunked GMT20250221-233332_Recording.transcript.vtt into 278 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:31.042\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.embeddings_model_service\u001b[0m:\u001b[36mget_embeddings\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCreating embeddings for 278 text string(s)…\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Vectorized GMT20250221-233332_Recording.transcript.vtt’s 278 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:36.119\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m38\u001b[0m - \u001b[34m\u001b[1mGetting vectors collection for storing 278 chunks\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:36.138\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:36.138\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:36.157\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:36.158\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m42\u001b[0m - \u001b[34m\u001b[1mCreating vector search index for vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:36.177\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:36.177\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:36.198\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:36.314\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mcreate_indexes\u001b[0m:\u001b[36m153\u001b[0m - \u001b[1mVector search index 'vectors_vector_index' created for collection vectors.\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:36.316\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m62\u001b[0m - \u001b[34m\u001b[1mInserting 278 documents into vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:38.707\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m64\u001b[0m - \u001b[1mStored 278 vector chunks in database\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Stored GMT20250221-233332_Recording.transcript.vtt’s 278 vectorized chunks to the database."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "Chunked GMT20250214-234809_Recording.transcript.vtt into 97 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:38.710\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.embeddings_model_service\u001b[0m:\u001b[36mget_embeddings\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCreating embeddings for 97 text string(s)…\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Vectorized GMT20250214-234809_Recording.transcript.vtt’s 97 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:40.479\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m38\u001b[0m - \u001b[34m\u001b[1mGetting vectors collection for storing 97 chunks\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:40.499\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:40.499\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:40.529\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:40.529\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m42\u001b[0m - \u001b[34m\u001b[1mCreating vector search index for vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:40.548\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:40.548\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:40.568\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:40.678\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mcreate_indexes\u001b[0m:\u001b[36m153\u001b[0m - \u001b[1mVector search index 'vectors_vector_index' created for collection vectors.\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:40.679\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m62\u001b[0m - \u001b[34m\u001b[1mInserting 97 documents into vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:41.562\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m64\u001b[0m - \u001b[1mStored 97 vector chunks in database\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Stored GMT20250214-234809_Recording.transcript.vtt’s 97 vectorized chunks to the database."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "Chunked GMT20250207-233258_Recording.transcript.vtt into 209 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:41.565\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.embeddings_model_service\u001b[0m:\u001b[36mget_embeddings\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCreating embeddings for 209 text string(s)…\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Vectorized GMT20250207-233258_Recording.transcript.vtt’s 209 chunks."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-04-20 00:09:44.152\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m38\u001b[0m - \u001b[34m\u001b[1mGetting vectors collection for storing 209 chunks\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:44.178\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:44.178\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:44.197\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:44.198\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m42\u001b[0m - \u001b[34m\u001b[1mCreating vector search index for vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:44.221\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mping\u001b[0m:\u001b[36m85\u001b[0m - \u001b[34m\u001b[1mMongoDB connection is active!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:44.222\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m106\u001b[0m - \u001b[34m\u001b[1mChecking if collection 'vectors' exists…\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:44.247\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mget_collection\u001b[0m:\u001b[36m115\u001b[0m - \u001b[34m\u001b[1mCollection 'vectors' already exists!\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:44.390\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.db.mongo_db\u001b[0m:\u001b[36mcreate_indexes\u001b[0m:\u001b[36m153\u001b[0m - \u001b[1mVector search index 'vectors_vector_index' created for collection vectors.\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:44.391\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m62\u001b[0m - \u001b[34m\u001b[1mInserting 209 documents into vectors collection\u001b[0m\n",
-      "\u001b[32m2025-04-20 00:09:46.410\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mctp_slack_bot.services.vector_database_service\u001b[0m:\u001b[36mstore\u001b[0m:\u001b[36m64\u001b[0m - \u001b[1mStored 209 vector chunks in database\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "Stored GMT20250207-233258_Recording.transcript.vtt’s 209 vectorized chunks to the database."
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "for web_vtt in web_vtts:\n",
     "    chunks = web_vtt.get_chunks()\n",
     "    display_html(f\"Chunked {web_vtt.get_metadata().get(\"filename\")} into {len(chunks)} chunks.\")\n",
     "    vectorized_chunks = vectorization_service.vectorize(chunks)\n",
     "    display_html(f\"Vectorized {web_vtt.get_metadata().get(\"filename\")}’s {len(vectorized_chunks)} chunks.\")\n",
-    "    await (await vector_database_service).store(vectorized_chunks)\n",
+    "    await vector_database_service.store(vectorized_chunks)\n",
     "    display_html(f\"Stored {web_vtt.get_metadata().get(\"filename\")}’s {len(vectorized_chunks)} vectorized chunks to the database.\")"
    ]
   }

src/ctp_slack_bot/mime_type_handlers/text/vtt.py

@@ -1,6 +1,7 @@
 from datetime import datetime
 from io import BytesIO
 from re import compile as compile_re
+from types import MappingProxyType
 from typing import Any, Mapping, Optional, Self
 from webvtt import WebVTT
 
@@ -28,7 +29,7 @@ class WebVTTMimeTypeHandler(BaseMimeTypeHandler):
                         for result
                         in map(ISO_DATE_TIME_PATTERN.findall, web_vtt.header_comments)
                         if result)
-        except ValueError:
+        except (StopIteration, ValueError):
             return None
 
     def from_bytes(self: Self, id: str, metadata: Mapping[str, Any], buffer: bytes) -> WebVTTContent:
@@ -36,4 +37,4 @@ class WebVTTMimeTypeHandler(BaseMimeTypeHandler):
         frames = tuple(WebVTTFrame.from_webvtt_caption(caption, index)
                        for index, caption
                        in enumerate(web_vtt.captions, 1))
-        return WebVTTContent(id=id, metadata=metadata, start_time=WebVTTMimeTypeHandler.__get_start_time(web_vtt), frames=frames)
+        return WebVTTContent(id=id, metadata=MappingProxyType(metadata), start_time=WebVTTMimeTypeHandler.__get_start_time(web_vtt), frames=frames)

src/ctp_slack_bot/models/webvtt.py

@@ -69,21 +69,3 @@ class WebVTTContent(Content):
 
     def get_metadata(self: Self) -> Mapping[str, Any]:
         return MappingProxyType(self.metadata)
-
-    @classmethod
-    def __get_start_time(cls, web_vtt: WebVTT) -> Optional[datetime]:
-        try:
-            return next(datetime.fromisoformat(result[0])
-                        for result
-                        in map(ISO_DATE_TIME_PATTERN.findall, web_vtt.header_comments)
-                        if result)
-        except (StopIteration, ValueError):
-            return None
-
-    @classmethod
-    def from_bytes(cls, id: str, metadata: Mapping[str, Any], buffer: bytes) -> Self:
-        web_vtt = WebVTT.from_buffer(BytesIO(buffer))
-        frames = tuple(WebVTTFrame.from_webvtt_caption(caption, index)
-                       for index, caption
-                       in enumerate(web_vtt.captions, 1))
-        return WebVTTContent(id=id, metadata=MappingProxyType(metadata), start_time=cls.__get_start_time(web_vtt), frames=frames)