diff --git a/alloydb/notebooks/columnar_engine_accelerated_hnsw_vector_search_benchmark.ipynb b/alloydb/notebooks/columnar_engine_accelerated_hnsw_vector_search_benchmark.ipynb new file mode 100644 index 0000000000..c43bfc3e28 --- /dev/null +++ b/alloydb/notebooks/columnar_engine_accelerated_hnsw_vector_search_benchmark.ipynb @@ -0,0 +1,2644 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "source": [ + "Copyright 2024 Google LLC\n", + "\n", + "Licensed under the Apache License, Version 2.0 (the \"License\");\n", + "you may not use this file except in compliance with the License.\n", + "You may obtain a copy of the License at\n", + "\n", + " https://www.apache.org/licenses/LICENSE-2.0\n", + "\n", + "Unless required by applicable law or agreed to in writing, software\n", + "distributed under the License is distributed on an \"AS IS\" BASIS,\n", + "WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", + "See the License for the specific language governing permissions and\n", + "limitations under the License." + ], + "metadata": { + "editable": false, + "id": "87m82ztIVg1L" + } + }, + { + "cell_type": "markdown", + "source": [ + "# ๐Ÿš€ Columnar Engine Accelerated Hnsw Vector Search Benchmark\n", + "\n", + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/GoogleCloudPlatform/python-docs-samples/blob/main/alloydb/notebooks/columnar_engine_accelerated_hnsw_vector_search_benchmark.ipynb)\n", + "\n", + "---\n", + "This interactive notebook measures the performance impact of **AlloyDB's Columnar Engine** on **pgvector HNSW** indexes. Visit [Get Started with AlloyDB](https://cloud.google.com/alloydb/docs/quickstart).\n", + "\n", + "*(Note: The performance metrics demonstrated in this notebook were captured using an **AlloyDB C4A 16-vCPU** instance. Your results may vary based on machine size).*\n", + "\n", + "๐Ÿšจ **IMPORTANT PREREQUISITES:**\n", + "\n", + "Ensure that **Public IP is enabled** on the instance *(Note: there is no need to authorize any networks!)* and the following database flags are set on your AlloyDB primary instance:\n", + "* `google_columnar_engine.enabled` = `on`\n", + "* `google_columnar_engine.enable_index_caching` = `on`\n", + "* `google_columnar_engine.memory_size_in_mb` = `1024` (or greater)\n", + "\n", + "๐Ÿ“š **Helpful Resources:**\n", + "\n", + "* [Get Started with AlloyDB](https://cloud.google.com/alloydb/docs/quickstart)\n", + "* [Accelerate vector search with the columnar engine](https://docs.cloud.google.com/alloydb/docs/ai/accelerate-with-ce)\n", + "* [pgvector](https://github.com/pgvector/pgvector)\n", + "---" + ], + "metadata": { + "id": "markdown-header" + } + }, + { + "cell_type": "code", + "source": [ + "# @title โš™๏ธ Benchmark Execution\n", + "# ==========================================\n", + "# 1. CONFIGURATION\n", + "# ==========================================\n", + "# @markdown ### **โš™๏ธ 1. Cluster Configuration**\n", + "project_id = \"\" # @param {type:\"string\", placeholder:\"Project ID\"}\n", + "region = \"\" # @param {type:\"string\", placeholder: \"Region (e.g. us-central1)\"}\n", + "cluster_name = \"\" # @param {type:\"string\", placeholder: \"Cluster name\"}\n", + "instance_name = \"\" # @param {type:\"string\", placeholder: \"Instance Name\"}\n", + "\n", + "# @markdown ### **๐Ÿ” 2. Database Credentials**\n", + "# @markdown *Note: Password will be requested securely when the benchmark is executed.*\n", + "db_user = \"\" # @param {type:\"string\", placeholder: \"DB User\"}\n", + "db_name = \"\" # @param {type:\"string\", placeholder: \"DB Name\"}\n", + "\n", + "# @markdown ### **โš™๏ธ 3. Benchmark Settings**\n", + "# @markdown *Note: Increasing these values will provide more intensive testing, but will slow down the benchmark runtime.*\n", + "# @markdown ### **โš™๏ธ 3. Benchmark Settings**\n", + "# @markdown *Note: Increasing these values will provide more intensive testing, but will slow down the benchmark runtime.*\n", + "# @markdown * `test_queries`: The total number of test queries to run during the benchmark. Increasing this value provides a more stable average but slows down the overall runtime.\n", + "# @markdown * `search_limit`: The number of nearest neighbors to retrieve per query (i.e., the `LIMIT` on the vector similarity search, equivalent to top-k).\n", + "\n", + "test_queries = 1000 # @param [100, 1000, 10000] {type:\"raw\"}\n", + "search_limit = 10 # @param [10, 100] {type:\"raw\"}\n", + "vector_dim = 100 # Fixed for GloVe-100 dataset\n", + "\n", + "import getpass\n", + "# Prompt for password upfront so user doesn't wait for the pip installation\n", + "db_pass = getpass.getpass(\"๐Ÿ”‘ Enter Database Password for AlloyDB: \")\n", + "\n", + "# ==========================================\n", + "# 2. SETUP & AUTHENTICATION\n", + "# ==========================================\n", + "import os\n", + "print(\"๐Ÿ“ฆ Installing dependencies silently... (This takes ~15 seconds)\")\n", + "os.system(\"pip install -q h5py matplotlib asyncpg google-cloud-alloydb-connector[asyncpg] tqdm rich pgvector\")\n", + "\n", + "print(\"๐Ÿ” Authenticating with Google Cloud...\")\n", + "from google.colab import auth\n", + "auth.authenticate_user()\n", + "\n", + "from IPython.display import clear_output\n", + "clear_output()\n", + "print(\"โœ… Output cleared. Colab Setup successful!\")\n", + "\n", + "# ==========================================\n", + "# 3. LATE IMPORTS (Post-Installation)\n", + "# ==========================================\n", + "import asyncio\n", + "import urllib.request\n", + "import shutil\n", + "import h5py\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "import matplotlib.ticker as ticker\n", + "from tqdm.notebook import tqdm\n", + "from rich.console import Console\n", + "from rich.panel import Panel\n", + "from google.cloud.alloydb.connector import AsyncConnector\n", + "import pgvector.asyncpg\n", + "from pgvector.asyncpg import register_vector\n", + "\n", + "console = Console()\n", + "\n", + "# ==========================================\n", + "# 4. SQL DEFINITIONS (Optimized with Array Intersection)\n", + "# ==========================================\n", + "SQL_MEASURE_RECALL = \"\"\"\n", + "CREATE OR REPLACE FUNCTION measure_recall(ef INT, num_q INT) RETURNS FLOAT AS $func$\n", + "DECLARE\n", + " q_rec record; total_recall FLOAT := 0; retrieved_ids INT[]; intersect_count INT;\n", + "BEGIN\n", + " PERFORM set_config('hnsw.ef_search', ef::text, false);\n", + "\n", + " FOR q_rec IN SELECT embedding, ground_truth FROM glove_test ORDER BY id LIMIT num_q LOOP\n", + " SELECT array_agg(sub.id) INTO retrieved_ids FROM (\n", + " SELECT id FROM glove ORDER BY embedding <=> q_rec.embedding LIMIT __SEARCH_LIMIT__\n", + " ) sub;\n", + "\n", + " -- Instant Intersection of retrieved array and ground_truth[1:search_limit]\n", + " SELECT count(*) INTO intersect_count\n", + " FROM unnest(retrieved_ids) as r\n", + " JOIN unnest(q_rec.ground_truth[1:__SEARCH_LIMIT__]) as g ON r = g;\n", + "\n", + " total_recall := total_recall + (intersect_count::FLOAT / __SEARCH_LIMIT__);\n", + " END LOOP;\n", + "\n", + " RETURN total_recall / num_q;\n", + "END;\n", + "$func$ LANGUAGE plpgsql;\n", + "\"\"\".replace(\"__SEARCH_LIMIT__\", str(search_limit))\n", + "\n", + "SQL_MEASURE_QPS = \"\"\"\n", + "CREATE OR REPLACE FUNCTION measure_qps(ef INT, num_q INT) RETURNS FLOAT AS $func$\n", + "DECLARE\n", + " start_time timestamp; end_time timestamp; q_vec halfvec;\n", + "BEGIN\n", + " PERFORM set_config('hnsw.ef_search', ef::text, false);\n", + "\n", + " start_time := clock_timestamp();\n", + " FOR q_vec IN SELECT embedding FROM glove_test LIMIT num_q LOOP\n", + " PERFORM id FROM glove ORDER BY embedding <=> q_vec LIMIT __SEARCH_LIMIT__;\n", + " END LOOP;\n", + " end_time := clock_timestamp();\n", + "\n", + " RETURN num_q / (extract(epoch from end_time) - extract(epoch from start_time));\n", + "END;\n", + "$func$ LANGUAGE plpgsql;\n", + "\"\"\".replace(\"__SEARCH_LIMIT__\", str(search_limit))\n", + "\n", + "# ==========================================\n", + "# 5. CORE FUNCTIONS\n", + "# ==========================================\n", + "async def verify_columnar_flags(conn):\n", + " console.print(\"\\n[bold blue]Step 2/9:[/bold blue] ๐Ÿ” Verifying Columnar Engine Flags...\")\n", + " enabled = await conn.fetchval(\"SELECT current_setting('google_columnar_engine.enabled', true);\")\n", + " caching = await conn.fetchval(\"SELECT current_setting('google_columnar_engine.enable_index_caching', true);\")\n", + " mem_size = await conn.fetchval(\"SELECT current_setting('google_columnar_engine.memory_size_in_mb', true);\")\n", + "\n", + " warnings = []\n", + " if enabled != 'on': warnings.append(\"โŒ google_columnar_engine.enabled is NOT 'on'\")\n", + " if caching != 'on': warnings.append(\"โŒ google_columnar_engine.enable_index_caching is NOT 'on'\")\n", + " try:\n", + " if not mem_size or int(mem_size) < 1024:\n", + " warnings.append(f\"โŒ memory_size_in_mb is '{mem_size}' (Must be at least 1024)\")\n", + " except ValueError:\n", + " warnings.append(f\"โŒ Could not parse memory_size_in_mb: {mem_size}\")\n", + "\n", + " if warnings:\n", + " for w in warnings: console.print(f\"[bold red]{w}[/bold red]\")\n", + " raise RuntimeError(\"Missing required Database Flags. Please update your cluster settings and restart.\")\n", + " else:\n", + " console.print(\" [bold green]โœ… All strict Columnar Engine flags are properly configured![/bold green]\")\n", + "\n", + "async def fast_bulk_insert_train(conn, data_array, batch_size=10000, desc=\"\"):\n", + " for i in tqdm(range(0, len(data_array), batch_size), desc=desc, leave=True, colour='#1f77b4'):\n", + " batch = data_array[i:i + batch_size]\n", + " records = [(i + j + 1, emb.tolist()) for j, emb in enumerate(batch)]\n", + " await conn.copy_records_to_table(\"glove\", columns=[\"id\", \"embedding\"], records=records)\n", + "\n", + "async def fast_bulk_insert_test(conn, data_array, neighbors_array, batch_size=10000, desc=\"\"):\n", + " for i in tqdm(range(0, len(data_array), batch_size), desc=desc, leave=True, colour='#1f77b4'):\n", + " batch_d = data_array[i:i + batch_size]\n", + " batch_n = neighbors_array[i:i + batch_size]\n", + " records = [(i + j + 1, emb.tolist(), [int(x+1) for x in nbr]) for j, (emb, nbr) in enumerate(zip(batch_d, batch_n))]\n", + " await conn.copy_records_to_table(\"glove_test\", columns=[\"id\", \"embedding\", \"ground_truth\"], records=records)\n", + "\n", + "async def prepare_dataset(conn):\n", + " console.print(\"[bold blue]Step 4/9:[/bold blue] ๐Ÿ“ฅ Preparing GloVe Dataset...\")\n", + " if not os.path.exists(\"glove-100-angular.hdf5\"):\n", + " console.print(\" [dim]Downloading dataset (1.2GB) from ann-benchmarks.com...[/dim]\")\n", + " url = \"http://ann-benchmarks.com/glove-100-angular.hdf5\"\n", + " req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0'})\n", + " with urllib.request.urlopen(req) as response, open(\"glove-100-angular.hdf5\", \"wb\") as out_file:\n", + " shutil.copyfileobj(response, out_file)\n", + "\n", + " console.print(\"[bold blue]Step 5/9:[/bold blue] ๐Ÿ“‚ Loading dataset and inserting via COPY...\")\n", + " with h5py.File(\"glove-100-angular.hdf5\", \"r\") as f:\n", + " train_data = f['train'][:]\n", + " test_data = f['test'][:]\n", + " neighbors_data = f['neighbors'][:]\n", + "\n", + " await fast_bulk_insert_train(conn, train_data, desc=\"COPY Training Data\")\n", + " await fast_bulk_insert_test(conn, test_data, neighbors_data, desc=\"COPY Test Queries & Ground Truth\")\n", + "\n", + "async def monitor_index_progress(connector):\n", + " try:\n", + " poll_conn = await connector.connect(\n", + " f\"projects/{project_id}/locations/{region}/clusters/{cluster_name}/instances/{instance_name}\",\n", + " \"asyncpg\", user=db_user, password=db_pass, db=db_name, ip_type=\"PUBLIC\"\n", + " )\n", + " except Exception:\n", + " return\n", + "\n", + " try:\n", + " with tqdm(total=100, desc=\"Building HNSW Index\", colour='#00ff00') as pbar:\n", + " while True:\n", + " try:\n", + " progress = await poll_conn.fetchrow(\"\"\"\n", + " SELECT blocks_done, blocks_total, phase\n", + " FROM pg_stat_progress_create_index\n", + " WHERE relid = 'glove'::regclass\n", + " \"\"\")\n", + " if progress and progress['blocks_total'] > 0:\n", + " percent = (progress['blocks_done'] / progress['blocks_total']) * 100\n", + " pbar.n = round(percent, 1)\n", + " pbar.set_postfix_str(f\"Phase: {progress['phase']}\")\n", + " pbar.refresh()\n", + " except Exception:\n", + " pass\n", + " await asyncio.sleep(1)\n", + " except asyncio.CancelledError:\n", + " pass\n", + " finally:\n", + " try:\n", + " await poll_conn.close()\n", + " except Exception:\n", + " pass\n", + "\n", + "async def build_index(conn, connector):\n", + " console.print(\"[bold blue]Step 6/9:[/bold blue] ๐Ÿงน Updating database planner statistics...\")\n", + " await conn.execute(\"VACUUM (DISABLE_PAGE_SKIPPING, ANALYZE) glove;\")\n", + " await conn.execute(\"VACUUM (DISABLE_PAGE_SKIPPING, ANALYZE) glove_test;\")\n", + "\n", + " console.print(\"[bold blue]Step 7/9:[/bold blue] ๐Ÿ—๏ธ Building HNSW Index...\")\n", + " await conn.execute(\"DROP INDEX IF EXISTS my_hnsw_idx;\")\n", + " await conn.execute(\"SET max_parallel_maintenance_workers = 16;\")\n", + " await conn.execute(\"SET maintenance_work_mem = '3GB';\")\n", + "\n", + " monitor_task = asyncio.create_task(monitor_index_progress(connector))\n", + " try:\n", + " await conn.execute(\"CREATE INDEX my_hnsw_idx ON glove USING hnsw (embedding halfvec_cosine_ops) WITH (m = 24, ef_construction = 256);\")\n", + " finally:\n", + " monitor_task.cancel()\n", + "\n", + "async def run_evaluations(conn, ef_values, test_queries):\n", + " console.print(\"[bold blue]Step 8/9:[/bold blue] โš™๏ธ Deploying Benchmark PL/pgSQL Functions...\")\n", + " await conn.execute(SQL_MEASURE_RECALL)\n", + " await conn.execute(SQL_MEASURE_QPS)\n", + "\n", + " console.print(\"\\n[bold blue]Step 9/9:[/bold blue] โฑ๏ธ Running Benchmarks...\")\n", + " results_without_ce = []\n", + " results_with_ce = []\n", + "\n", + " # Run WITHOUT Columnar Engine\n", + " await conn.execute(\"SELECT google_columnar_engine_drop_index('my_hnsw_idx');\")\n", + " for ef in tqdm(ef_values, desc=\"Without Columnar Engine\", leave=True, colour='#1f77b4'):\n", + " recall = await conn.fetchval(f\"SELECT measure_recall({ef}, {test_queries});\")\n", + " qps = await conn.fetchval(f\"SELECT measure_qps({ef}, {test_queries});\")\n", + " console.log(\"ef: %d | qps: %d | recall: %.3f\" % (ef, qps, recall))\n", + " results_without_ce.append((ef, recall, qps))\n", + "\n", + " # Run WITH Columnar Engine\n", + " await conn.execute(\"SELECT google_columnar_engine_add_index('my_hnsw_idx');\")\n", + " for ef in tqdm(ef_values, desc=\"WITH Columnar Engine\", leave=True, colour='#ff7f0e'):\n", + " recall = await conn.fetchval(f\"SELECT measure_recall({ef}, {test_queries});\")\n", + " qps = await conn.fetchval(f\"SELECT measure_qps({ef}, {test_queries});\")\n", + " console.log(\"ef: %d | qps: %d | recall: %.3f\" % (ef, qps, recall))\n", + " results_with_ce.append((ef, recall, qps))\n", + "\n", + " return results_without_ce, results_with_ce\n", + "\n", + "def plot_results(results_without_ce, results_with_ce):\n", + " \"\"\"Renders the final performance plot outside the async block.\"\"\"\n", + " console.print(\"\\n[bold green]๐Ÿ“Š Generating Final Plot & Summary...[/bold green]\")\n", + " import numpy as np\n", + " import matplotlib.patheffects as patheffects\n", + "\n", + " ef_wo = [p[0] for p in results_without_ce]\n", + " recalls_wo = [p[1] for p in results_without_ce]\n", + " qps_wo = [p[2] for p in results_without_ce]\n", + "\n", + " ef_wi = [p[0] for p in results_with_ce]\n", + " recalls_wi = [p[1] for p in results_with_ce]\n", + " qps_wi = [p[2] for p in results_with_ce]\n", + "\n", + " plt.rc('font', size=14)\n", + " plt.rc('axes', titlesize=18)\n", + " plt.rc('axes', labelsize=16)\n", + " plt.rc('xtick', labelsize=14)\n", + " plt.rc('ytick', labelsize=14)\n", + " plt.rc('legend', fontsize=14)\n", + " plt.figure(figsize=(12, 7))\n", + "\n", + " # Google brand colors\n", + " color_wi = '#ff7f0e' # Orange\n", + " color_wo = '#1f77b4' # Blue\n", + " color_ar = '#2ca02c' # Green\n", + "\n", + " plt.plot(recalls_wi, qps_wi, marker='D', linewidth=3, markersize=10,\n", + " color=color_wi, label='With Columnar Engine')\n", + " plt.plot(recalls_wo, qps_wo, marker='o', linewidth=3, markersize=10,\n", + " color=color_wo, label='Without Columnar Engine')\n", + "\n", + " plt.xlabel('Recall (Accuracy)')\n", + " plt.ylabel('Queries Per Second (QPS)')\n", + " plt.title(f'HNSW Recall vs QPS\\n(GloVe 100, LIMIT {search_limit}, {test_queries} Tests)', pad=20, fontweight='bold')\n", + "\n", + " max_qps = max(max(qps_wi, default=0), max(qps_wo, default=0))\n", + " min_recall = min(min(recalls_wi, default=1), min(recalls_wo, default=1))\n", + "\n", + " plt.ylim(0, max_qps + 500)\n", + " plt.xlim(min_recall - 0.015, 1.015)\n", + "\n", + " plt.gca().yaxis.set_major_locator(ticker.MultipleLocator(1000))\n", + " plt.gca().xaxis.set_major_locator(ticker.MultipleLocator(0.05))\n", + "\n", + " # Clean up spines (borders)\n", + " plt.gca().spines['top'].set_visible(False)\n", + " plt.gca().spines['right'].set_visible(False)\n", + " plt.gca().spines['left'].set_color('#cccccc')\n", + " plt.gca().spines['bottom'].set_color('#cccccc')\n", + "\n", + " pe = [patheffects.withStroke(linewidth=3, foreground='white', alpha=0.9)]\n", + "\n", + " # --- 1. Annotate QPS improvement at the same Recall (Vertical Gap) ---\n", + " for r_wi, q_wi, q_wo in zip(recalls_wi, qps_wi, qps_wo):\n", + " multiplier = q_wi / q_wo if q_wo > 0 else 0\n", + " if multiplier > 0:\n", + " plt.text(r_wi * 1.001, q_wi + (max_qps * 0.04), f'{multiplier:.1f}x QPS', color=color_wi,\n", + " fontsize=12, fontweight='bold', ha='center', va='bottom', path_effects=pe)\n", + "\n", + " # --- 2. Annotate Recall improvement at the same QPS (Horizontal Gap) ---\n", + " if len(qps_wo) > 0 and len(qps_wi) > 0:\n", + " idx_min_recall_wo = np.argmin(recalls_wo)\n", + " r_wo_min = recalls_wo[idx_min_recall_wo]\n", + " q_target = qps_wo[idx_min_recall_wo]\n", + "\n", + " # Check if q_target is within the range of orange line's QPS\n", + " if min(qps_wi) <= q_target <= max(qps_wi):\n", + " wi_sort = np.argsort(qps_wi)\n", + " r_wi_interp = np.interp(q_target, np.array(qps_wi)[wi_sort], np.array(recalls_wi)[wi_sort])\n", + "\n", + " if (r_wi_interp - r_wo_min) > 0.005:\n", + " plt.annotate('', xy=(r_wi_interp, q_target), xytext=(r_wo_min, q_target),\n", + " arrowprops=dict(arrowstyle=\"<->\", color=color_ar, lw=1.5, linestyle='--'))\n", + " plt.text((r_wo_min + r_wi_interp) / 2, q_target + (max_qps * 0.015), f'+{r_wi_interp - r_wo_min:.3f} Recall',\n", + " color=color_ar, fontsize=11, fontweight='bold', ha='center', va='bottom', path_effects=pe)\n", + "\n", + " plt.legend(loc='upper right', frameon=True, edgecolor='#cccccc')\n", + " plt.grid(True, which='both', color='#f0f0f0', linestyle='-', linewidth=1.5)\n", + " plt.tight_layout()\n", + " plt.show()\n", + "\n", + "# ==========================================\n", + "# 6. MAIN EXECUTION PIPELINE\n", + "# ==========================================\n", + "async def run_benchmark():\n", + " connector = None\n", + " conn = None\n", + " try:\n", + " console.print(Panel(\n", + " \"[bold green]โœ… GCP Authentication Successful![/bold green]\\n\"\n", + " \"[bold default]๐Ÿš€ Starting AlloyDB Benchmark Pipeline (Asyncpg + COPY)...[/bold default]\",\n", + " border_style=\"green\", expand=False\n", + " ))\n", + "\n", + " console.print(\"\\n[bold blue]Step 1/9:[/bold blue] ๐Ÿ”Œ Initializing AlloyDB AsyncConnector...\")\n", + " connector = AsyncConnector()\n", + " conn = await connector.connect(\n", + " f\"projects/{project_id}/locations/{region}/clusters/{cluster_name}/instances/{instance_name}\",\n", + " \"asyncpg\", user=db_user, password=db_pass, db=db_name, ip_type=\"PUBLIC\"\n", + " )\n", + "\n", + " await verify_columnar_flags(conn)\n", + "\n", + " console.print(\"[bold blue]Step 3/9:[/bold blue] ๐Ÿ› ๏ธ Setting up extensions & tables...\")\n", + " await conn.execute(\"CREATE EXTENSION IF NOT EXISTS vector;\")\n", + " await conn.execute(\"CREATE EXTENSION IF NOT EXISTS google_columnar_engine;\")\n", + " await conn.execute(\"DROP TABLE IF EXISTS glove CASCADE;\")\n", + " await conn.execute(\"DROP TABLE IF EXISTS glove_test CASCADE;\")\n", + " await conn.execute(f\"CREATE TABLE glove (id BIGINT PRIMARY KEY, embedding halfvec({vector_dim}));\")\n", + " await conn.execute(f\"CREATE TABLE glove_test (id BIGINT PRIMARY KEY, embedding halfvec({vector_dim}), ground_truth INT[]);\")\n", + "\n", + " await register_vector(conn)\n", + "\n", + " await prepare_dataset(conn)\n", + " await build_index(conn, connector)\n", + "\n", + " ef_values = [40, 100, 200, 400, 800]\n", + " # Return results to pass into synchronous plotter\n", + " return await run_evaluations(conn, ef_values, test_queries)\n", + "\n", + " except Exception as e:\n", + " console.print(f\"\\n[bold red]โŒ ERROR:[/bold red] {str(e)}\")\n", + " return None, None\n", + " finally:\n", + " if conn: await conn.close()\n", + " if connector: await connector.close()\n", + "\n", + "# Evaluate the benchmark (Async Loop)\n", + "results_wo, results_wi = await run_benchmark()\n", + "\n", + "# Guarantee Plot renders perfectly (Sync Thread)\n", + "if results_wo and results_wi:\n", + " plot_results(results_wo, results_wi)\n" + ], + "metadata": { + "cellView": "form", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000, + "referenced_widgets": [ + "cf4de0a14cfa41e6a93bd982280ba1ee", + "ab2ff9be5ea241be8868da4016951923", + "50d4ea5f8e544e90a72cb1f5013ae12b", + "4a4ce6b301f6459fa232c3c04a306803", + "9de057f9662d4329b6f55ba565284796", + "ecb08db623b34d718f2cc69b21184a83", + "b92f09c2f1c1440dac59f24bda55ec6e", + "09b7085e58f845569efae068f23af495", + "71a5e33f4d6040d08b8299a2d2963781", + "c049ad9053664469ab3063565710cf75", + "ba29e67d84f5425bb319305575cd0051", + "1853184b6aff4be08ea1d71dd7b02491", + "7ef308f4cd0f46f48338cba96ce75592", + "e8be41159b794f3bbcc672be23c36f30", + "57fa825a1fb04e7a98256792e7dd6687", + "56c15a9737ed476289f0d6da8c7c2b2a", + "28896967211a428aa91596e4374125b7", + "4611f99bbf444b76b48c183a1c596a3e", + "7c247c04219b4ad8a002e6f5c3707a0b", + "a0c4cde888d941aaba264ea631b0b8df", + "73704dba4a934f609bf4d70f2b653d97", + "cff12405e60348718b3fbf4609cf9676", + "29aa6d294ccd4e9d82074f3a959c7d68", + "a3f14ae9a5834bb6ba1639ae93184856", + "4790b78abdd34fbda65ed82c50596d44", + "7ce2dfe5974c49f3aa09caee53e15be1", + "e3a2d37130344675b75dadcb4944efab", + "56baa1312f5b459791b51ed157f9360b", + "0e70564d7eea473da5222fdab901a8ad", + "f188e4492f6a492f94b17968a11eae52", + "9862e497828944209b3e1e65e82e303d", + "a754e70e7ce147b4a11c3cb62b2de16b", + "64fcbd33baac4f79ba9d096016863cdc", + "de83ddc45f61463d9ee52d4518098f7d", + "5a7a3a47d582418fa1964e60e840dac2", + "ce25a37cfa6a4d90b12e1faba4a8aa41", + "dda6bc7cb73b440d8d6c8bb654ad7028", + "613d852a41fe42f687d82731bd8d352d", + "c046a084bdcc4547bbbd96754d17407b", + "7fab4fd2de94460f86bfc877b7e2681c", + "fb938822fdb5439aaaa3880727235047", + "1ffc1bbb1ff84ba19129ee1b70552172", + "79dbcbb8f4ff43aabf7602e38b2e7e47", + "4f8b0b36c4fc4adba19f590e43388abb", + "ce330eae985b41a6a906370759e815a3", + "3ab232d8cd764d2b884769c99fa20672", + "f7e90b34cc004df8b35304733abeb134", + "6ce0f50e19e54a8d80bcde0eca4ef47c", + "5af25d01af84452fbde4130c2d4ed594", + "eaa4ecad8fa543059189c99aacc579ee", + "fc6fd35ed88347b5b96c226eda84fbac", + "e153160c7f3043e380c950d1c04beba1", + "6e7df11bbef04f3fb72174f0f41329a9", + "f9b1b218af2a4946bb3502fbe36e0375", + "922b9b7ea4744ac18076e54c914a5546" + ] + }, + "id": "KOs-ppVTCKTu", + "jupyter": { + "source_hidden": true + }, + "outputId": "c373fdbf-1cb2-4bcf-c0f3-447ea11a3f8a", + "tags": [ + "hide-input" + ] + }, + "execution_count": null, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "โœ… Output cleared. Colab Setup successful!\n" + ] + }, + { + "data": { + "text/html": [ + "
โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ\n",
+              "โ”‚ โœ… GCP Authentication Successful!                          โ”‚\n",
+              "โ”‚ ๐Ÿš€ Starting AlloyDB Benchmark Pipeline (Asyncpg + COPY)... โ”‚\n",
+              "โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[32mโ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ\u001b[0m\n", + "\u001b[32mโ”‚\u001b[0m \u001b[1;32mโœ… GCP Authentication Successful!\u001b[0m \u001b[32mโ”‚\u001b[0m\n", + "\u001b[32mโ”‚\u001b[0m \u001b[1;39m๐Ÿš€ Starting AlloyDB Benchmark Pipeline (Asyncpg + COPY)...\u001b[0m \u001b[32mโ”‚\u001b[0m\n", + "\u001b[32mโ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
\n",
+              "Step 1/9: ๐Ÿ”Œ Initializing AlloyDB AsyncConnector...\n",
+              "
\n" + ], + "text/plain": [ + "\n", + "\u001b[1;34mStep \u001b[0m\u001b[1;34m1\u001b[0m\u001b[1;34m/\u001b[0m\u001b[1;34m9\u001b[0m\u001b[1;34m:\u001b[0m ๐Ÿ”Œ Initializing AlloyDB AsyncConnector\u001b[33m...\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
\n",
+              "Step 2/9: ๐Ÿ” Verifying Columnar Engine Flags...\n",
+              "
\n" + ], + "text/plain": [ + "\n", + "\u001b[1;34mStep \u001b[0m\u001b[1;34m2\u001b[0m\u001b[1;34m/\u001b[0m\u001b[1;34m9\u001b[0m\u001b[1;34m:\u001b[0m ๐Ÿ” Verifying Columnar Engine Flags\u001b[33m...\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
         โœ… All strict Columnar Engine flags are properly configured!\n",
+              "
\n" + ], + "text/plain": [ + " \u001b[1;32mโœ… All strict Columnar Engine flags are properly configured!\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
Step 3/9: ๐Ÿ› ๏ธ Setting up extensions & tables...\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1;34mStep \u001b[0m\u001b[1;34m3\u001b[0m\u001b[1;34m/\u001b[0m\u001b[1;34m9\u001b[0m\u001b[1;34m:\u001b[0m ๐Ÿ› ๏ธ Setting up extensions & tables\u001b[33m...\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
Step 4/9: ๐Ÿ“ฅ Preparing GloVe Dataset...\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1;34mStep \u001b[0m\u001b[1;34m4\u001b[0m\u001b[1;34m/\u001b[0m\u001b[1;34m9\u001b[0m\u001b[1;34m:\u001b[0m ๐Ÿ“ฅ Preparing GloVe Dataset\u001b[33m...\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
         Downloading dataset (1.2GB) from ann-benchmarks.com...\n",
+              "
\n" + ], + "text/plain": [ + " \u001b[2mDownloading dataset \u001b[0m\u001b[1;2m(\u001b[0m\u001b[1;2;36m1.\u001b[0m\u001b[2m2GB\u001b[0m\u001b[1;2m)\u001b[0m\u001b[2m from ann-benchmarks.com\u001b[0m\u001b[2;33m...\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
Step 5/9: ๐Ÿ“‚ Loading dataset and inserting via COPY...\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1;34mStep \u001b[0m\u001b[1;34m5\u001b[0m\u001b[1;34m/\u001b[0m\u001b[1;34m9\u001b[0m\u001b[1;34m:\u001b[0m ๐Ÿ“‚ Loading dataset and inserting via COPY\u001b[33m...\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "cf4de0a14cfa41e6a93bd982280ba1ee", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "COPY Training Data: 0%| | 0/119 [00:00Step 6/9: ๐Ÿงน Updating database planner statistics...\n", + "\n" + ], + "text/plain": [ + "\u001b[1;34mStep \u001b[0m\u001b[1;34m6\u001b[0m\u001b[1;34m/\u001b[0m\u001b[1;34m9\u001b[0m\u001b[1;34m:\u001b[0m ๐Ÿงน Updating database planner statistics\u001b[33m...\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
Step 7/9: ๐Ÿ—๏ธ Building HNSW Index...\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1;34mStep \u001b[0m\u001b[1;34m7\u001b[0m\u001b[1;34m/\u001b[0m\u001b[1;34m9\u001b[0m\u001b[1;34m:\u001b[0m ๐Ÿ—๏ธ Building HNSW Index\u001b[33m...\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "29aa6d294ccd4e9d82074f3a959c7d68", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Building HNSW Index: 0%| | 0/100 [00:00Step 8/9: โš™๏ธ Deploying Benchmark PL/pgSQL Functions...\n", + "\n" + ], + "text/plain": [ + "\u001b[1;34mStep \u001b[0m\u001b[1;34m8\u001b[0m\u001b[1;34m/\u001b[0m\u001b[1;34m9\u001b[0m\u001b[1;34m:\u001b[0m โš™๏ธ Deploying Benchmark PL/pgSQL Functions\u001b[33m...\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
\n",
+              "Step 9/9: โฑ๏ธ Running Benchmarks...\n",
+              "
\n" + ], + "text/plain": [ + "\n", + "\u001b[1;34mStep \u001b[0m\u001b[1;34m9\u001b[0m\u001b[1;34m/\u001b[0m\u001b[1;34m9\u001b[0m\u001b[1;34m:\u001b[0m โฑ๏ธ Running Benchmarks\u001b[33m...\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "de83ddc45f61463d9ee52d4518098f7d", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Without Columnar Engine: 0%| | 0/5 [00:00[04:46:36] ef: 40 | qps: 905 | recall: 0.795 2526329112.py:224\n", + "\n" + ], + "text/plain": [ + "\u001b[2;36m[04:46:36]\u001b[0m\u001b[2;36m \u001b[0mef: \u001b[1;36m40\u001b[0m | qps: \u001b[1;36m905\u001b[0m | recall: \u001b[1;36m0.795\u001b[0m \u001b]8;id=560467;file:///tmp/ipykernel_666/2526329112.py\u001b\\\u001b[2m2526329112.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=307767;file:///tmp/ipykernel_666/2526329112.py#224\u001b\\\u001b[2m224\u001b[0m\u001b]8;;\u001b\\\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
[04:46:41] ef: 100 | qps: 446 | recall: 0.881                                                     2526329112.py:224\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[2;36m[04:46:41]\u001b[0m\u001b[2;36m \u001b[0mef: \u001b[1;36m100\u001b[0m | qps: \u001b[1;36m446\u001b[0m | recall: \u001b[1;36m0.881\u001b[0m \u001b]8;id=764489;file:///tmp/ipykernel_666/2526329112.py\u001b\\\u001b[2m2526329112.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=105719;file:///tmp/ipykernel_666/2526329112.py#224\u001b\\\u001b[2m224\u001b[0m\u001b]8;;\u001b\\\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
[04:46:49] ef: 200 | qps: 249 | recall: 0.924                                                     2526329112.py:224\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[2;36m[04:46:49]\u001b[0m\u001b[2;36m \u001b[0mef: \u001b[1;36m200\u001b[0m | qps: \u001b[1;36m249\u001b[0m | recall: \u001b[1;36m0.924\u001b[0m \u001b]8;id=621825;file:///tmp/ipykernel_666/2526329112.py\u001b\\\u001b[2m2526329112.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=485598;file:///tmp/ipykernel_666/2526329112.py#224\u001b\\\u001b[2m224\u001b[0m\u001b]8;;\u001b\\\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
[04:47:04] ef: 400 | qps: 132 | recall: 0.958                                                     2526329112.py:224\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[2;36m[04:47:04]\u001b[0m\u001b[2;36m \u001b[0mef: \u001b[1;36m400\u001b[0m | qps: \u001b[1;36m132\u001b[0m | recall: \u001b[1;36m0.958\u001b[0m \u001b]8;id=182954;file:///tmp/ipykernel_666/2526329112.py\u001b\\\u001b[2m2526329112.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=645822;file:///tmp/ipykernel_666/2526329112.py#224\u001b\\\u001b[2m224\u001b[0m\u001b]8;;\u001b\\\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
[04:47:32] ef: 800 | qps: 71 | recall: 0.979                                                      2526329112.py:224\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[2;36m[04:47:32]\u001b[0m\u001b[2;36m \u001b[0mef: \u001b[1;36m800\u001b[0m | qps: \u001b[1;36m71\u001b[0m | recall: \u001b[1;36m0.979\u001b[0m \u001b]8;id=859044;file:///tmp/ipykernel_666/2526329112.py\u001b\\\u001b[2m2526329112.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=741180;file:///tmp/ipykernel_666/2526329112.py#224\u001b\\\u001b[2m224\u001b[0m\u001b]8;;\u001b\\\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "ce330eae985b41a6a906370759e815a3", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "WITH Columnar Engine: 0%| | 0/5 [00:00[04:47:34] ef: 40 | qps: 6989 | recall: 0.795 2526329112.py:232\n", + "\n" + ], + "text/plain": [ + "\u001b[2;36m[04:47:34]\u001b[0m\u001b[2;36m \u001b[0mef: \u001b[1;36m40\u001b[0m | qps: \u001b[1;36m6989\u001b[0m | recall: \u001b[1;36m0.795\u001b[0m \u001b]8;id=245333;file:///tmp/ipykernel_666/2526329112.py\u001b\\\u001b[2m2526329112.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=448784;file:///tmp/ipykernel_666/2526329112.py#232\u001b\\\u001b[2m232\u001b[0m\u001b]8;;\u001b\\\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
[04:47:35] ef: 100 | qps: 3452 | recall: 0.881                                                    2526329112.py:232\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[2;36m[04:47:35]\u001b[0m\u001b[2;36m \u001b[0mef: \u001b[1;36m100\u001b[0m | qps: \u001b[1;36m3452\u001b[0m | recall: \u001b[1;36m0.881\u001b[0m \u001b]8;id=765500;file:///tmp/ipykernel_666/2526329112.py\u001b\\\u001b[2m2526329112.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=592606;file:///tmp/ipykernel_666/2526329112.py#232\u001b\\\u001b[2m232\u001b[0m\u001b]8;;\u001b\\\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
[04:47:36] ef: 200 | qps: 1903 | recall: 0.924                                                    2526329112.py:232\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[2;36m[04:47:36]\u001b[0m\u001b[2;36m \u001b[0mef: \u001b[1;36m200\u001b[0m | qps: \u001b[1;36m1903\u001b[0m | recall: \u001b[1;36m0.924\u001b[0m \u001b]8;id=446412;file:///tmp/ipykernel_666/2526329112.py\u001b\\\u001b[2m2526329112.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=642407;file:///tmp/ipykernel_666/2526329112.py#232\u001b\\\u001b[2m232\u001b[0m\u001b]8;;\u001b\\\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
[04:47:38] ef: 400 | qps: 1020 | recall: 0.958                                                    2526329112.py:232\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[2;36m[04:47:38]\u001b[0m\u001b[2;36m \u001b[0mef: \u001b[1;36m400\u001b[0m | qps: \u001b[1;36m1020\u001b[0m | recall: \u001b[1;36m0.958\u001b[0m \u001b]8;id=885242;file:///tmp/ipykernel_666/2526329112.py\u001b\\\u001b[2m2526329112.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=936632;file:///tmp/ipykernel_666/2526329112.py#232\u001b\\\u001b[2m232\u001b[0m\u001b]8;;\u001b\\\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
[04:47:42] ef: 800 | qps: 522 | recall: 0.979                                                     2526329112.py:232\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[2;36m[04:47:42]\u001b[0m\u001b[2;36m \u001b[0mef: \u001b[1;36m800\u001b[0m | qps: \u001b[1;36m522\u001b[0m | recall: \u001b[1;36m0.979\u001b[0m \u001b]8;id=694553;file:///tmp/ipykernel_666/2526329112.py\u001b\\\u001b[2m2526329112.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=590858;file:///tmp/ipykernel_666/2526329112.py#232\u001b\\\u001b[2m232\u001b[0m\u001b]8;;\u001b\\\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
\n",
+              "๐Ÿ“Š Generating Final Plot & Summary...\n",
+              "
\n" + ], + "text/plain": [ + "\n", + "\u001b[1;32m๐Ÿ“Š Generating Final Plot & Summary\u001b[0m\u001b[1;32m...\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + }, + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "version_major": 2, + "version_minor": 0, + "state": { + "cf4de0a14cfa41e6a93bd982280ba1ee": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_ab2ff9be5ea241be8868da4016951923", + "IPY_MODEL_50d4ea5f8e544e90a72cb1f5013ae12b", + "IPY_MODEL_4a4ce6b301f6459fa232c3c04a306803" + ], + "layout": "IPY_MODEL_9de057f9662d4329b6f55ba565284796" + } + }, + "ab2ff9be5ea241be8868da4016951923": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_ecb08db623b34d718f2cc69b21184a83", + "placeholder": "โ€‹", + "style": "IPY_MODEL_b92f09c2f1c1440dac59f24bda55ec6e", + "value": "COPYโ€‡Trainingโ€‡Data:โ€‡100%" + } + }, + "50d4ea5f8e544e90a72cb1f5013ae12b": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_09b7085e58f845569efae068f23af495", + "max": 119, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_71a5e33f4d6040d08b8299a2d2963781", + "value": 119 + } + }, + "4a4ce6b301f6459fa232c3c04a306803": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_c049ad9053664469ab3063565710cf75", + "placeholder": "โ€‹", + "style": "IPY_MODEL_ba29e67d84f5425bb319305575cd0051", + "value": "โ€‡119/119โ€‡[00:35<00:00,โ€‡โ€‡4.20it/s]" + } + }, + "9de057f9662d4329b6f55ba565284796": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ecb08db623b34d718f2cc69b21184a83": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "b92f09c2f1c1440dac59f24bda55ec6e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "09b7085e58f845569efae068f23af495": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "71a5e33f4d6040d08b8299a2d2963781": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": "#1f77b4", + "description_width": "" + } + }, + "c049ad9053664469ab3063565710cf75": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ba29e67d84f5425bb319305575cd0051": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "1853184b6aff4be08ea1d71dd7b02491": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_7ef308f4cd0f46f48338cba96ce75592", + "IPY_MODEL_e8be41159b794f3bbcc672be23c36f30", + "IPY_MODEL_57fa825a1fb04e7a98256792e7dd6687" + ], + "layout": "IPY_MODEL_56c15a9737ed476289f0d6da8c7c2b2a" + } + }, + "7ef308f4cd0f46f48338cba96ce75592": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_28896967211a428aa91596e4374125b7", + "placeholder": "โ€‹", + "style": "IPY_MODEL_4611f99bbf444b76b48c183a1c596a3e", + "value": "COPYโ€‡Testโ€‡Queriesโ€‡&โ€‡Groundโ€‡Truth:โ€‡100%" + } + }, + "e8be41159b794f3bbcc672be23c36f30": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_7c247c04219b4ad8a002e6f5c3707a0b", + "max": 1, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_a0c4cde888d941aaba264ea631b0b8df", + "value": 1 + } + }, + "57fa825a1fb04e7a98256792e7dd6687": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_73704dba4a934f609bf4d70f2b653d97", + "placeholder": "โ€‹", + "style": "IPY_MODEL_cff12405e60348718b3fbf4609cf9676", + "value": "โ€‡1/1โ€‡[00:01<00:00,โ€‡โ€‡1.27s/it]" + } + }, + "56c15a9737ed476289f0d6da8c7c2b2a": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "28896967211a428aa91596e4374125b7": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "4611f99bbf444b76b48c183a1c596a3e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "7c247c04219b4ad8a002e6f5c3707a0b": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "a0c4cde888d941aaba264ea631b0b8df": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": "#1f77b4", + "description_width": "" + } + }, + "73704dba4a934f609bf4d70f2b653d97": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "cff12405e60348718b3fbf4609cf9676": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "29aa6d294ccd4e9d82074f3a959c7d68": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_a3f14ae9a5834bb6ba1639ae93184856", + "IPY_MODEL_4790b78abdd34fbda65ed82c50596d44", + "IPY_MODEL_7ce2dfe5974c49f3aa09caee53e15be1" + ], + "layout": "IPY_MODEL_e3a2d37130344675b75dadcb4944efab" + } + }, + "a3f14ae9a5834bb6ba1639ae93184856": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_56baa1312f5b459791b51ed157f9360b", + "placeholder": "โ€‹", + "style": "IPY_MODEL_0e70564d7eea473da5222fdab901a8ad", + "value": "Buildingโ€‡HNSWโ€‡Index:โ€‡100%" + } + }, + "4790b78abdd34fbda65ed82c50596d44": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_f188e4492f6a492f94b17968a11eae52", + "max": 100, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_9862e497828944209b3e1e65e82e303d", + "value": 100 + } + }, + "7ce2dfe5974c49f3aa09caee53e15be1": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_a754e70e7ce147b4a11c3cb62b2de16b", + "placeholder": "โ€‹", + "style": "IPY_MODEL_64fcbd33baac4f79ba9d096016863cdc", + "value": "โ€‡100.0/100โ€‡[02:15<00:00,โ€‡โ€‡1.35s/it,โ€‡Phase:โ€‡buildingโ€‡index:โ€‡loadingโ€‡tuples]" + } + }, + "e3a2d37130344675b75dadcb4944efab": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "56baa1312f5b459791b51ed157f9360b": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "0e70564d7eea473da5222fdab901a8ad": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "f188e4492f6a492f94b17968a11eae52": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "9862e497828944209b3e1e65e82e303d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": "#00ff00", + "description_width": "" + } + }, + "a754e70e7ce147b4a11c3cb62b2de16b": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "64fcbd33baac4f79ba9d096016863cdc": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "de83ddc45f61463d9ee52d4518098f7d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_5a7a3a47d582418fa1964e60e840dac2", + "IPY_MODEL_ce25a37cfa6a4d90b12e1faba4a8aa41", + "IPY_MODEL_dda6bc7cb73b440d8d6c8bb654ad7028" + ], + "layout": "IPY_MODEL_613d852a41fe42f687d82731bd8d352d" + } + }, + "5a7a3a47d582418fa1964e60e840dac2": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_c046a084bdcc4547bbbd96754d17407b", + "placeholder": "โ€‹", + "style": "IPY_MODEL_7fab4fd2de94460f86bfc877b7e2681c", + "value": "Withoutโ€‡Columnarโ€‡Engine:โ€‡100%" + } + }, + "ce25a37cfa6a4d90b12e1faba4a8aa41": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_fb938822fdb5439aaaa3880727235047", + "max": 5, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_1ffc1bbb1ff84ba19129ee1b70552172", + "value": 5 + } + }, + "dda6bc7cb73b440d8d6c8bb654ad7028": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_79dbcbb8f4ff43aabf7602e38b2e7e47", + "placeholder": "โ€‹", + "style": "IPY_MODEL_4f8b0b36c4fc4adba19f590e43388abb", + "value": "โ€‡5/5โ€‡[00:58<00:00,โ€‡16.08s/it]" + } + }, + "613d852a41fe42f687d82731bd8d352d": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "c046a084bdcc4547bbbd96754d17407b": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "7fab4fd2de94460f86bfc877b7e2681c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "fb938822fdb5439aaaa3880727235047": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "1ffc1bbb1ff84ba19129ee1b70552172": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": "#1f77b4", + "description_width": "" + } + }, + "79dbcbb8f4ff43aabf7602e38b2e7e47": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "4f8b0b36c4fc4adba19f590e43388abb": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "ce330eae985b41a6a906370759e815a3": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_3ab232d8cd764d2b884769c99fa20672", + "IPY_MODEL_f7e90b34cc004df8b35304733abeb134", + "IPY_MODEL_6ce0f50e19e54a8d80bcde0eca4ef47c" + ], + "layout": "IPY_MODEL_5af25d01af84452fbde4130c2d4ed594" + } + }, + "3ab232d8cd764d2b884769c99fa20672": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_eaa4ecad8fa543059189c99aacc579ee", + "placeholder": "โ€‹", + "style": "IPY_MODEL_fc6fd35ed88347b5b96c226eda84fbac", + "value": "WITHโ€‡Columnarโ€‡Engine:โ€‡100%" + } + }, + "f7e90b34cc004df8b35304733abeb134": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_e153160c7f3043e380c950d1c04beba1", + "max": 5, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_6e7df11bbef04f3fb72174f0f41329a9", + "value": 5 + } + }, + "6ce0f50e19e54a8d80bcde0eca4ef47c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_f9b1b218af2a4946bb3502fbe36e0375", + "placeholder": "โ€‹", + "style": "IPY_MODEL_922b9b7ea4744ac18076e54c914a5546", + "value": "โ€‡5/5โ€‡[00:08<00:00,โ€‡โ€‡2.27s/it]" + } + }, + "5af25d01af84452fbde4130c2d4ed594": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "eaa4ecad8fa543059189c99aacc579ee": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "fc6fd35ed88347b5b96c226eda84fbac": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "e153160c7f3043e380c950d1c04beba1": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "6e7df11bbef04f3fb72174f0f41329a9": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": "#ff7f0e", + "description_width": "" + } + }, + "f9b1b218af2a4946bb3502fbe36e0375": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "922b9b7ea4744ac18076e54c914a5546": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + } + } + } + } + }, + "nbformat_minor": 0, + "nbformat": 4 +} \ No newline at end of file diff --git a/alloydb/notebooks/e2e_test.py b/alloydb/notebooks/e2e_test.py index 34516188c4..36a122fd6f 100644 --- a/alloydb/notebooks/e2e_test.py +++ b/alloydb/notebooks/e2e_test.py @@ -153,3 +153,43 @@ async def test_embeddings_batch_processing( ) await conn.commit() await pool.dispose() + + +@pytest.mark.asyncio +async def test_alloydb_vector_search_benchmark( + project_id: str, + cluster_name: str, + instance_name: str, + region: str, + database_name: str, + password: str, +) -> None: + # Run the benchmark notebook with significantly reduced parameters + # to allow CI to complete quickly without OOMs or timeouts + conftest.run_notebook( + "alloydb_vector_search_benchmark.ipynb", + variables={ + "project_id": project_id, + "region": region, + "cluster_id": cluster_name, + "instance_id": instance_name, + "db_name": database_name, + "db_user": "postgres", + "test_queries": 10, + }, + preprocess=preprocess, + skip_shell_commands=True, + replace={ + ( + "db_pass = getpass.getpass(" + '"๐Ÿ”‘ Enter Database Password for AlloyDB: ")' + ): f"db_pass = '{password}'", + "train_data = f['train'][:]": "train_data = f['train'][:1000]", + "test_data = f['test'][:]": "test_data = f['test'][:100]", + "neighbors_data = f['neighbors'][:]": ( + "neighbors_data = f['neighbors'][:100]" + ), + "ef_values = [40, 100, 200, 400, 800]": "ef_values = [40]", + }, + until_end=True, + )