diff --git a/.github/ignore-notebooks.txt b/.github/ignore-notebooks.txt
index 5505268..61ba17d 100644
--- a/.github/ignore-notebooks.txt
+++ b/.github/ignore-notebooks.txt
@@ -7,4 +7,6 @@
02_semantic_cache_optimization
spring_ai_redis_rag.ipynb
00_litellm_proxy_redis.ipynb
-04_redisvl_benchmarking_basics.ipynb
\ No newline at end of file
+04_redisvl_benchmarking_basics.ipynb
+06_hnsw_to_svs_vamana_migration.ipynb
+07_flat_to_svs_vamana_migration.ipynb
\ No newline at end of file
diff --git a/README.md b/README.md
index a01de17..ca5c739 100644
--- a/README.md
+++ b/README.md
@@ -69,6 +69,8 @@ Need quickstarts to begin your Redis AI journey?
| ๐ข **Data Type Support** - Shows how to convert a float32 index to float16 or integer dataypes | [](python-recipes/vector-search/03_dtype_support.ipynb) | [](https://colab.research.google.com/github/redis-developer/redis-ai-resources/blob/main/python-recipes/vector-search/03_dtype_support.ipynb) |
| ๐ **Benchmarking Basics** - Overview of search benchmarking basics with RedisVL and Python multiprocessing | [](python-recipes/vector-search/04_redisvl_benchmarking_basics.ipynb) | [](https://colab.research.google.com/github/redis-developer/redis-ai-resources/blob/main/python-recipes/vector-search/04_redisvl_benchmarking_basics.ipynb) |
| ๐ **Multi Vector Search** - Overview of multi vector queries with RedisVL | [](python-recipes/vector-search/05_multivector_search.ipynb) | [](https://colab.research.google.com/github/redis-developer/redis-ai-resources/blob/main/python-recipes/vector-search/05_multivector_search.ipynb) |
+| ๐๏ธ **HNSW to SVS-VAMANA Migration** - Showcase how to migrate HNSW indices to SVS-VAMANA | [](python-recipes/vector-search/06_hnsw_to_svs_vamana_migration.ipynb) | [](https://colab.research.google.com/github/redis-developer/redis-ai-resources/blob/main/python-recipes/vector-search/06_hnsw_to_svs_vamana_migration.ipynb) |
+| ๐๏ธ **FLAT to SVS-VAMANA Migration** - Showcase how to migrate FLAT indices to SVS-VAMANA | [](python-recipes/vector-search/07_flat_to_svs_vamana_migration.ipynb) | [](https://colab.research.google.com/github/redis-developer/redis-ai-resources/blob/main/python-recipes/vector-search/07_flat_to_svs_vamana_migration.ipynb) |
### Retrieval Augmented Generation (RAG)
diff --git a/python-recipes/vector-search/06_hnsw_to_svs_vamana_migration.ipynb b/python-recipes/vector-search/06_hnsw_to_svs_vamana_migration.ipynb
new file mode 100644
index 0000000..8b2cee7
--- /dev/null
+++ b/python-recipes/vector-search/06_hnsw_to_svs_vamana_migration.ipynb
@@ -0,0 +1,1201 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "\n",
+ "# Migrating from HNSW to SVS-VAMANA\n",
+ "\n",
+ "## Let's Begin!\n",
+ "
\n",
+ "\n",
+ "This notebook demonstrates how to migrate existing HNSW vector indices to SVS-VAMANA for improved memory efficiency while maintaining search quality.\n",
+ "\n",
+ "## What You'll Learn\n",
+ "\n",
+ "- How to assess your current HNSW index for migration\n",
+ "- Step-by-step migration from HNSW to SVS-VAMANA\n",
+ "- Memory usage comparison and cost analysis\n",
+ "- Search quality validation between HNSW and SVS-VAMANA\n",
+ "- Performance benchmarking and recall comparison\n",
+ "- Migration decision framework for production systems\n",
+ "\n",
+ "## Prerequisites\n",
+ "\n",
+ "- Redis Stack 8.2.0+ with RediSearch 2.8.10+\n",
+ "- Existing HNSW index with substantial data (1000+ documents recommended)\n",
+ "- High-dimensional vectors (768+ dimensions for best compression benefits)\n",
+ "\n",
+ "## HNSW vs SVS-VAMANA\n",
+ "\n",
+ "**HNSW (Hierarchical Navigable Small World):**\n",
+ "- Excellent search quality and recall\n",
+ "- Fast query performance\n",
+ "- Higher memory usage (stores full-precision vectors)\n",
+ "- Good for applications prioritizing search quality\n",
+ "\n",
+ "**SVS-VAMANA:**\n",
+ "- Competitive search quality with compression\n",
+ "- Significant memory savings (50-75% reduction)\n",
+ "- Built-in vector compression (LeanVec, quantization)\n",
+ "- Ideal for large-scale deployments with cost constraints"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## ๐ HNSW to SVS-VAMANA Migration Checklist\n",
+ "\n",
+ "**PRE-MIGRATION:**\n",
+ "- โ Backup existing HNSW index data\n",
+ "- โ Test migration on staging environment\n",
+ "- โ Validate search quality with real queries\n",
+ "- โ Measure baseline HNSW performance metrics\n",
+ "- โ Plan rollback strategy\n",
+ "- โ Document current HNSW parameters (M, EF_construction, EF_runtime)\n",
+ "\n",
+ "**MIGRATION:**\n",
+ "- โ Create SVS-VAMANA index with tested configuration\n",
+ "- โ Migrate data in batches during low-traffic periods\n",
+ "- โ Monitor memory usage and indexing progress\n",
+ "- โ Validate data integrity after migration\n",
+ "- โ Test search functionality thoroughly\n",
+ "- โ Compare recall metrics with baseline\n",
+ "\n",
+ "**POST-MIGRATION:**\n",
+ "- โ Monitor search performance and quality\n",
+ "- โ Track memory usage and cost savings\n",
+ "- โ Update application configuration\n",
+ "- โ Document new SVS-VAMANA settings\n",
+ "- โ Clean up old HNSW index after validation period\n",
+ "- โ Update monitoring and alerting thresholds\n",
+ "\n",
+ "**๐ก HNSW-SPECIFIC TIPS:**\n",
+ "- HNSW indices are more complex to rebuild than FLAT\n",
+ "- Consider the impact on applications using EF_runtime tuning\n",
+ "- SVS-VAMANA may have different optimal query parameters\n",
+ "- Test with your specific HNSW configuration (M, EF values)\n",
+ "- Monitor for 48-72 hours before removing HNSW index\n",
+ "- Keep compression settings documented for future reference"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## ๐ฆ Installation & Setup\n",
+ "\n",
+ "This notebook uses **RedisVL vectorizers** for generating embeddings and **Redis Stack** for vector search.\n",
+ "\n",
+ "**Requirements:**\n",
+ "- Redis Stack 8.2.0+ with RediSearch 2.8.10+ (for SVS-VAMANA support)\n",
+ "- redisvl>=0.11.0 (required for SVS-VAMANA migration features and vectorizers)\n",
+ "- redis-py>=6.4.0 (required for compatibility with RedisVL 0.11.0+)\n",
+ "- numpy (for vector operations)\n",
+ "\n",
+ "**โ ๏ธ Important:** If you encounter Redis connection errors, upgrade redis-py: `pip install -U \"redis>=6.4.0\"`"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Install Packages"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "/Users/nitin.kanukolanu/workspace/redis-vl-python/.venv/bin/python3: No module named pip\n",
+ "Note: you may need to restart the kernel to use updated packages.\n"
+ ]
+ }
+ ],
+ "source": [
+ "%pip install git+https://github.com/redis/redis-vl-python.git \"redis>=6.4.0\" \"numpy>=1.21.0\" \"sentence-transformers>=2.2.0\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Install Redis Stack\n",
+ "\n",
+ "Later in this tutorial, Redis will be used to store, index, and query vector\n",
+ "embeddings and full text fields. **We need to have a Redis\n",
+ "instance available.**\n",
+ "\n",
+ "#### Local Redis\n",
+ "Use the shell script below to download, extract, and install [Redis Stack](https://redis.io/docs/getting-started/install-stack/) directly from the Redis package archive."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# NBVAL_SKIP\n",
+ "%%sh\n",
+ "curl -fsSL https://packages.redis.io/gpg | sudo gpg --dearmor -o /usr/share/keyrings/redis-archive-keyring.gpg\n",
+ "echo \"deb [signed-by=/usr/share/keyrings/redis-archive-keyring.gpg] https://packages.redis.io/deb $(lsb_release -cs) main\" | sudo tee /etc/apt/sources.list.d/redis.list\n",
+ "sudo apt-get update > /dev/null 2>&1\n",
+ "sudo apt-get install redis-stack-server > /dev/null 2>&1\n",
+ "redis-stack-server --daemonize yes"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Alternative Redis Access (Cloud, Docker, other)\n",
+ "There are many ways to get the necessary redis-stack instance running\n",
+ "1. On cloud, deploy a [FREE instance of Redis in the cloud](https://redis.com/try-free/). Or, if you have your\n",
+ "own version of Redis Enterprise running, that works too!\n",
+ "2. Per OS, [see the docs](https://redis.io/docs/latest/operate/oss_and_stack/install/install-stack/)\n",
+ "3. With docker: `docker run -d --name redis-stack-server -p 6379:6379 redis/redis-stack-server:latest`"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Define the Redis Connection URL\n",
+ "\n",
+ "By default this notebook connects to the local instance of Redis Stack. **If you have your own Redis Enterprise instance** - replace REDIS_PASSWORD, REDIS_HOST and REDIS_PORT values with your own."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Libraries imported successfully!\n"
+ ]
+ }
+ ],
+ "source": [
+ "import os\n",
+ "import json\n",
+ "import numpy as np\n",
+ "import time\n",
+ "from typing import List, Dict, Any\n",
+ "\n",
+ "# Redis and RedisVL imports\n",
+ "import redis\n",
+ "from redisvl.index import SearchIndex\n",
+ "from redisvl.query import VectorQuery\n",
+ "from redisvl.redis.utils import array_to_buffer, buffer_to_array\n",
+ "from redisvl.utils import CompressionAdvisor\n",
+ "from redisvl.redis.connection import supports_svs\n",
+ "\n",
+ "# RedisVL Vectorizer imports\n",
+ "from redisvl.utils.vectorize import HFTextVectorizer\n",
+ "\n",
+ "# Replace values below with your own if using Redis Cloud instance\n",
+ "REDIS_HOST = os.getenv(\"REDIS_HOST\", \"localhost\") # ex: \"redis-18374.c253.us-central1-1.gce.cloud.redislabs.com\"\n",
+ "REDIS_PORT = os.getenv(\"REDIS_PORT\", \"6379\") # ex: 18374\n",
+ "REDIS_PASSWORD = os.getenv(\"REDIS_PASSWORD\", \"\") # ex: \"1TNxTEdYRDgIDKM2gDfasupCADXXXX\"\n",
+ "\n",
+ "# If SSL is enabled on the endpoint, use rediss:// as the URL prefix\n",
+ "REDIS_URL = f\"redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}\"\n",
+ "\n",
+ "print(\"๐ Libraries imported successfully!\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 1: Verify Redis and SVS Support\n",
+ "\n",
+ "First, let's ensure Redis Stack is running and supports SVS-VAMANA."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "โ
Redis connection successful\n",
+ "๐ Redis version: 8.2.2\n",
+ "โ
SVS-VAMANA supported\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Test Redis connection and SVS support\n",
+ "try:\n",
+ " client = redis.Redis.from_url(REDIS_URL)\n",
+ " client.ping()\n",
+ " print(\"โ
Redis connection successful\")\n",
+ " \n",
+ " # Check Redis version\n",
+ " redis_info = client.info()\n",
+ " redis_version = redis_info['redis_version']\n",
+ " print(f\"๐ Redis version: {redis_version}\")\n",
+ " \n",
+ " # Check SVS support\n",
+ " if supports_svs(client):\n",
+ " print(\"โ
SVS-VAMANA supported\")\n",
+ " else:\n",
+ " print(\"โ SVS-VAMANA not supported\")\n",
+ " print(\"Please ensure you're using Redis Stack 8.2.0+ with RediSearch 2.8.10+\")\n",
+ " \n",
+ "except Exception as e:\n",
+ " print(f\"โ Redis connection failed: {e}\")\n",
+ " print(\"Please ensure Redis Stack is running on localhost:6379\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 2: Load Sample Data\n",
+ "\n",
+ "We'll use the movie dataset to demonstrate the migration process."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ฝ๏ธ Loaded 20 movie records\n",
+ "Sample movie: Explosive Pursuit\n",
+ "Genres available: {'comedy', 'action'}\n",
+ "\n",
+ "๐ง Configuration:\n",
+ "Vector dimensions: 768\n",
+ "Dataset size: 20 movie documents\n",
+ "Vectorizer: RedisVL HFTextVectorizer\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Load the movies dataset\n",
+ "with open('resources/movies.json', 'r') as f:\n",
+ " movies_data = json.load(f)\n",
+ "\n",
+ "print(\n",
+ " f\"๐ฝ๏ธ Loaded {len(movies_data)} movie records\",\n",
+ " f\"Sample movie: {movies_data[0]['title']}\",\n",
+ " f\"Genres available: {set(movie['genre'] for movie in movies_data)}\",\n",
+ " sep=\"\\n\"\n",
+ ")\n",
+ "\n",
+ "# Configuration for demonstration \n",
+ "dims = 768 # Using all-mpnet-base-v2 model (768 dimensions)\n",
+ "num_docs = len(movies_data) # Use actual dataset size\n",
+ "\n",
+ "print(\n",
+ " f\"\\n๐ง Configuration:\",\n",
+ " f\"Vector dimensions: {dims}\",\n",
+ " f\"Dataset size: {num_docs} movie documents\",\n",
+ " f\"Vectorizer: RedisVL HFTextVectorizer\",\n",
+ " sep=\"\\n\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 3: Create HNSW Index\n",
+ "\n",
+ "First, we'll create an HNSW index with typical production settings."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Creating HNSW index with optimized settings...\n",
+ "โ
Created HNSW index: hnsw_demo_index\n",
+ "\n",
+ "๐ง HNSW Configuration:\n",
+ "M (connections per node): 16\n",
+ "EF Construction: 200\n",
+ "EF Runtime: 10\n",
+ "Distance metric: cosine\n",
+ "Data type: float32\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Create HNSW schema with production-like settings\n",
+ "hnsw_schema = {\n",
+ " \"index\": {\n",
+ " \"name\": \"hnsw_demo_index\",\n",
+ " \"prefix\": \"demo:hnsw:\",\n",
+ " },\n",
+ " \"fields\": [\n",
+ " {\"name\": \"movie_id\", \"type\": \"tag\"},\n",
+ " {\"name\": \"title\", \"type\": \"text\"},\n",
+ " {\"name\": \"genre\", \"type\": \"tag\"},\n",
+ " {\"name\": \"rating\", \"type\": \"numeric\"},\n",
+ " {\"name\": \"description\", \"type\": \"text\"},\n",
+ " {\n",
+ " \"name\": \"embedding\",\n",
+ " \"type\": \"vector\",\n",
+ " \"attrs\": {\n",
+ " \"dims\": dims,\n",
+ " \"algorithm\": \"hnsw\",\n",
+ " \"datatype\": \"float32\",\n",
+ " \"distance_metric\": \"cosine\",\n",
+ " \"m\": 16, # Number of bi-directional links for each node\n",
+ " \"ef_construction\": 200, # Size of dynamic candidate list\n",
+ " \"ef_runtime\": 10 # Size of dynamic candidate list during search\n",
+ " }\n",
+ " }\n",
+ " ]\n",
+ "}\n",
+ "\n",
+ "print(\"Creating HNSW index with optimized settings...\")\n",
+ "hnsw_index = SearchIndex.from_dict(hnsw_schema, redis_url=REDIS_URL)\n",
+ "hnsw_index.create(overwrite=True)\n",
+ "print(f\"โ
Created HNSW index: {hnsw_index.name}\")\n",
+ "\n",
+ "# Display HNSW configuration\n",
+ "print(\n",
+ " \"\\n๐ง HNSW Configuration:\",\n",
+ " f\"M (connections per node): 16\",\n",
+ " f\"EF Construction: 200\",\n",
+ " f\"EF Runtime: 10\",\n",
+ " f\"Distance metric: cosine\",\n",
+ " f\"Data type: float32\",\n",
+ " sep=\"\\n\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 4: Generate Embeddings and Load HNSW Index\n",
+ "\n",
+ "Generate embeddings for movie descriptions and populate the HNSW index."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Generating embeddings for movie descriptions...\n",
+ "๐ Using RedisVL HFTextVectorizer...\n",
+ "12:13:05 sentence_transformers.SentenceTransformer INFO Use pytorch device_name: mps\n",
+ "12:13:05 sentence_transformers.SentenceTransformer INFO Load pretrained SentenceTransformer: sentence-transformers/all-mpnet-base-v2\n",
+ "โ
Generated 20 real embeddings using RedisVL HFTextVectorizer\n",
+ "๐ Embedding shape: (20, 768)\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Generate embeddings using RedisVL vectorizers\n",
+ "print(\"๐ Generating embeddings for movie descriptions...\")\n",
+ "\n",
+ "descriptions = [movie['description'] for movie in movies_data]\n",
+ "\n",
+ "# Use RedisVL HFTextVectorizer\n",
+ "print(\"๐ Using RedisVL HFTextVectorizer...\")\n",
+ "vectorizer = HFTextVectorizer(\n",
+ " model=\"sentence-transformers/all-mpnet-base-v2\", # 768 dimensions\n",
+ ")\n",
+ "\n",
+ "# Generate embeddings using RedisVL vectorizer\n",
+ "embeddings = vectorizer.embed_many(descriptions)\n",
+ "embeddings = np.array(embeddings, dtype=np.float32)\n",
+ "\n",
+ "print(f\"โ
Generated {len(embeddings)} real embeddings using RedisVL HFTextVectorizer\")\n",
+ "print(f\"๐ Embedding shape: {embeddings.shape}\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ฆ Prepared 20 documents for indexing\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Prepare data for loading into HNSW index\n",
+ "sample_data = []\n",
+ "for i, movie in enumerate(movies_data):\n",
+ " sample_data.append({\n",
+ " 'movie_id': str(movie['id']),\n",
+ " 'title': movie['title'],\n",
+ " 'genre': movie['genre'],\n",
+ " 'rating': movie['rating'],\n",
+ " 'description': movie['description'],\n",
+ " 'embedding': array_to_buffer(embeddings[i].astype(np.float32), dtype='float32')\n",
+ " })\n",
+ "\n",
+ "print(f\"๐ฆ Prepared {len(sample_data)} documents for indexing\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ฅ Loading data into HNSW index...\n",
+ " Loaded 20/20 documents\n",
+ "โณ Waiting for HNSW indexing to complete...\n",
+ "\n",
+ "โ
HNSW index loaded with 20 documents\n",
+ "Index size: 3.2259750366210938 MB\n",
+ "Indexing time: ~5 seconds (HNSW graph construction)\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Load data into HNSW index\n",
+ "print(\"๐ฅ Loading data into HNSW index...\")\n",
+ "batch_size = 100 # Process in batches\n",
+ "\n",
+ "for i in range(0, len(sample_data), batch_size):\n",
+ " batch = sample_data[i:i+batch_size]\n",
+ " hnsw_index.load(batch)\n",
+ " print(f\" Loaded {min(i+batch_size, len(sample_data))}/{len(sample_data)} documents\")\n",
+ "\n",
+ "# Wait for indexing to complete\n",
+ "print(\"โณ Waiting for HNSW indexing to complete...\")\n",
+ "time.sleep(5) # HNSW indexing takes longer than FLAT\n",
+ "\n",
+ "hnsw_info = hnsw_index.info()\n",
+ "print(\n",
+ " f\"\\nโ
HNSW index loaded with {hnsw_info['num_docs']} documents\",\n",
+ " f\"Index size: {hnsw_info.get('vector_index_sz_mb', 'N/A')} MB\",\n",
+ " f\"Indexing time: ~5 seconds (HNSW graph construction)\",\n",
+ " sep=\"\\n\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 5: Get Compression Recommendation\n",
+ "\n",
+ "Use the CompressionAdvisor to get optimal SVS-VAMANA settings for our data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Analyzing data for optimal compression settings...\n",
+ "\n",
+ "๐ Compression Recommendations:\n",
+ "\n",
+ "๐๏ธ Memory Priority:\n",
+ " Algorithm: svs-vamana\n",
+ " Compression: LVQ4\n",
+ " Datatype: float32\n",
+ " Dimensions: 768 โ None\n",
+ "\n",
+ "โ๏ธ Balanced Priority:\n",
+ " Algorithm: svs-vamana\n",
+ " Compression: LVQ4x4\n",
+ " Datatype: float32\n",
+ " Dimensions: 768 โ None\n",
+ "\n",
+ "โก Performance Priority:\n",
+ " Algorithm: svs-vamana\n",
+ " Compression: LVQ4x4\n",
+ " Datatype: float32\n",
+ " Dimensions: 768 โ None\n",
+ "\n",
+ "โ
Selected configuration: Memory Priority\n",
+ "Expected memory reduction: ~0.0% from dimension reduction\n",
+ "Additional savings from float32 compression\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Get compression recommendation\n",
+ "print(\"๐ Analyzing data for optimal compression settings...\")\n",
+ "\n",
+ "# Get recommendations for different priorities\n",
+ "memory_config = CompressionAdvisor.recommend(dims=dims, priority=\"memory\")\n",
+ "balanced_config = CompressionAdvisor.recommend(dims=dims, priority=\"balanced\")\n",
+ "performance_config = CompressionAdvisor.recommend(dims=dims, priority=\"performance\")\n",
+ "\n",
+ "print(\n",
+ " \"\\n๐ Compression Recommendations:\",\n",
+ " \"\",\n",
+ " \"๐๏ธ Memory Priority:\",\n",
+ " f\" Algorithm: {memory_config.algorithm}\",\n",
+ " f\" Compression: {memory_config.compression if hasattr(memory_config, 'compression') else 'None'}\",\n",
+ " f\" Datatype: {memory_config.datatype}\",\n",
+ " f\" Dimensions: {dims} โ {memory_config.reduce if hasattr(memory_config, 'reduce') else dims}\",\n",
+ " \"\",\n",
+ " \"โ๏ธ Balanced Priority:\",\n",
+ " f\" Algorithm: {balanced_config.algorithm}\",\n",
+ " f\" Compression: {balanced_config.compression if hasattr(balanced_config, 'compression') else 'None'}\",\n",
+ " f\" Datatype: {balanced_config.datatype}\",\n",
+ " f\" Dimensions: {dims} โ {balanced_config.reduce if hasattr(balanced_config, 'reduce') else dims}\",\n",
+ " \"\",\n",
+ " \"โก Performance Priority:\",\n",
+ " f\" Algorithm: {performance_config.algorithm}\",\n",
+ " f\" Compression: {performance_config.compression if hasattr(performance_config, 'compression') else 'None'}\",\n",
+ " f\" Datatype: {performance_config.datatype}\",\n",
+ " f\" Dimensions: {dims} โ {performance_config.reduce if hasattr(performance_config, 'reduce') else dims}\",\n",
+ " sep=\"\\n\"\n",
+ ")\n",
+ "\n",
+ "# Select configuration (using memory priority for maximum savings)\n",
+ "selected_config = memory_config\n",
+ "# Use reduce if it exists and is not None, otherwise use original dims\n",
+ "target_dims = selected_config.reduce if (hasattr(selected_config, 'reduce') and selected_config.reduce is not None) else dims\n",
+ "target_dtype = selected_config.datatype\n",
+ "\n",
+ "print(\n",
+ " f\"\\nโ
Selected configuration: Memory Priority\",\n",
+ " f\"Expected memory reduction: ~{((dims - target_dims) / dims * 100):.1f}% from dimension reduction\",\n",
+ " f\"Additional savings from {selected_config.datatype} compression\",\n",
+ " sep=\"\\n\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 6: Create SVS-VAMANA Index\n",
+ "\n",
+ "Create the SVS-VAMANA index with the recommended compression settings."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Creating SVS-VAMANA index with compression...\n",
+ "โ
Created SVS-VAMANA index: svs_demo_index\n",
+ "Compression: LVQ4\n",
+ "Datatype: float32\n",
+ "Dimensions: 768 โ 768\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Create SVS-VAMANA schema with compression\n",
+ "svs_schema = {\n",
+ " \"index\": {\n",
+ " \"name\": \"svs_demo_index\",\n",
+ " \"prefix\": \"demo:svs:\",\n",
+ " },\n",
+ " \"fields\": [\n",
+ " {\"name\": \"movie_id\", \"type\": \"tag\"},\n",
+ " {\"name\": \"title\", \"type\": \"text\"},\n",
+ " {\"name\": \"genre\", \"type\": \"tag\"},\n",
+ " {\"name\": \"rating\", \"type\": \"numeric\"},\n",
+ " {\"name\": \"description\", \"type\": \"text\"},\n",
+ " {\n",
+ " \"name\": \"embedding\",\n",
+ " \"type\": \"vector\",\n",
+ " \"attrs\": {\n",
+ " \"dims\": target_dims, # Use reduced dimensions\n",
+ " \"algorithm\": \"svs-vamana\",\n",
+ " \"datatype\": selected_config.datatype,\n",
+ " \"distance_metric\": \"cosine\"\n",
+ " # Note: Don't include the full selected_config to avoid dims/reduce conflict\n",
+ " }\n",
+ " }\n",
+ " ]\n",
+ "}\n",
+ "\n",
+ "print(\"Creating SVS-VAMANA index with compression...\")\n",
+ "svs_index = SearchIndex.from_dict(svs_schema, redis_url=REDIS_URL)\n",
+ "svs_index.create(overwrite=True)\n",
+ "print(\n",
+ " f\"โ
Created SVS-VAMANA index: {svs_index.name}\",\n",
+ " f\"Compression: {selected_config.compression if hasattr(selected_config, 'compression') else 'None'}\",\n",
+ " f\"Datatype: {selected_config.datatype}\",\n",
+ " f\"Dimensions: {dims} โ {target_dims}\",\n",
+ " sep=\"\\n\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 7: Migrate Data from HNSW to SVS-VAMANA\n",
+ "\n",
+ "Extract data from the HNSW index and migrate it to SVS-VAMANA with compression."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Extracting data from HNSW index...\n",
+ "Found 20 documents to migrate\n",
+ "Prepared 20 documents for migration\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Extract data from HNSW index\n",
+ "print(\"๐ Extracting data from HNSW index...\")\n",
+ "\n",
+ "client = redis.Redis.from_url(REDIS_URL)\n",
+ "keys = client.keys(\"demo:hnsw:*\")\n",
+ "print(f\"Found {len(keys)} documents to migrate\")\n",
+ "\n",
+ "# Process and transform data for SVS index\n",
+ "svs_data = []\n",
+ "\n",
+ "for key in keys:\n",
+ " doc_data = client.hgetall(key)\n",
+ " \n",
+ " if b'embedding' in doc_data:\n",
+ " # Extract original vector from HNSW index\n",
+ " original_vector = np.array(buffer_to_array(doc_data[b'embedding'], dtype='float32'))\n",
+ " \n",
+ " # Apply dimensionality reduction if needed (LeanVec)\n",
+ " if target_dims < dims:\n",
+ " vector = original_vector[:target_dims]\n",
+ " else:\n",
+ " vector = original_vector\n",
+ " \n",
+ " # Convert to target datatype\n",
+ " if target_dtype == 'float16':\n",
+ " vector = vector.astype(np.float16)\n",
+ " \n",
+ " svs_data.append({\n",
+ " \"movie_id\": doc_data[b'movie_id'].decode(),\n",
+ " \"title\": doc_data[b'title'].decode(),\n",
+ " \"genre\": doc_data[b'genre'].decode(),\n",
+ " \"rating\": int(doc_data[b'rating'].decode()),\n",
+ " \"description\": doc_data[b'description'].decode(),\n",
+ " \"embedding\": array_to_buffer(vector, dtype=target_dtype)\n",
+ " })\n",
+ "\n",
+ "print(f\"Prepared {len(svs_data)} documents for migration\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ฅ Loading data into SVS-VAMANA index...\n",
+ " Migrated 20/20 documents\n",
+ "โณ Waiting for SVS-VAMANA indexing to complete...\n",
+ "\n",
+ "โ
Migration complete! SVS index has 20 documents\n",
+ "Index size: 3.017791748046875 MB\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Load data into SVS index\n",
+ "print(\"๐ฅ Loading data into SVS-VAMANA index...\")\n",
+ "batch_size = 100 # Define batch size for migration\n",
+ "\n",
+ "if len(svs_data) > 0:\n",
+ " for i in range(0, len(svs_data), batch_size):\n",
+ " batch = svs_data[i:i+batch_size]\n",
+ " svs_index.load(batch)\n",
+ " print(f\" Migrated {min(i+batch_size, len(svs_data))}/{len(svs_data)} documents\")\n",
+ "\n",
+ " # Wait for indexing to complete\n",
+ " print(\"โณ Waiting for SVS-VAMANA indexing to complete...\")\n",
+ " time.sleep(5)\n",
+ "\n",
+ " svs_info = svs_index.info()\n",
+ " print(\n",
+ " f\"\\nโ
Migration complete! SVS index has {svs_info['num_docs']} documents\",\n",
+ " f\"Index size: {svs_info.get('vector_index_sz_mb', 'N/A')} MB\",\n",
+ " sep=\"\\n\"\n",
+ " )\n",
+ "else:\n",
+ " print(\"โ ๏ธ No data to migrate. Make sure the HNSW index was populated first.\")\n",
+ " print(\" Run the previous cells to load data into the HNSW index.\")\n",
+ " svs_info = svs_index.info()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 8: Compare Memory Usage\n",
+ "\n",
+ "Analyze the memory savings achieved through the HNSW to SVS-VAMANA migration."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Memory Usage Comparison\n",
+ "========================================\n",
+ "Original HNSW index: 3.23 MB\n",
+ "SVS-VAMANA index: 3.02 MB\n",
+ "\n",
+ "๐ฐ Memory savings: 6.5%\n",
+ "Absolute reduction: 0.21 MB\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Helper function to extract memory info\n",
+ "def get_memory_mb(index_info):\n",
+ " \"\"\"Extract memory usage in MB from index info\"\"\"\n",
+ " memory = index_info.get('vector_index_sz_mb', 0)\n",
+ " if isinstance(memory, str):\n",
+ " try:\n",
+ " return float(memory)\n",
+ " except ValueError:\n",
+ " return 0.0\n",
+ " return float(memory)\n",
+ "\n",
+ "# Get memory usage\n",
+ "hnsw_memory = get_memory_mb(hnsw_info)\n",
+ "svs_memory = get_memory_mb(svs_info)\n",
+ "\n",
+ "print(\n",
+ " \"๐ Memory Usage Comparison\",\n",
+ " \"=\" * 40,\n",
+ " f\"Original HNSW index: {hnsw_memory:.2f} MB\",\n",
+ " f\"SVS-VAMANA index: {svs_memory:.2f} MB\",\n",
+ " \"\",\n",
+ " sep=\"\\n\"\n",
+ ")\n",
+ "\n",
+ "if hnsw_memory > 0:\n",
+ " if svs_memory > 0:\n",
+ " savings = ((hnsw_memory - svs_memory) / hnsw_memory) * 100\n",
+ " print(\n",
+ " f\"๐ฐ Memory savings: {savings:.1f}%\",\n",
+ " f\"Absolute reduction: {hnsw_memory - svs_memory:.2f} MB\",\n",
+ " sep=\"\\n\"\n",
+ " )\n",
+ " else:\n",
+ " print(\"โณ SVS index still indexing - memory comparison pending\")\n",
+ "else:\n",
+ " print(\"โ ๏ธ Memory information not available\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 9: Validate Search Quality\n",
+ "\n",
+ "Compare search quality between HNSW and SVS-VAMANA to ensure the migration maintains acceptable recall."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Generating test queries for quality validation...\n",
+ "Generated 10 test queries\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Generate test queries\n",
+ "print(\"๐ Generating test queries for quality validation...\")\n",
+ "\n",
+ "np.random.seed(123) # For reproducible test queries\n",
+ "num_test_queries = 10\n",
+ "test_queries = []\n",
+ "\n",
+ "for i in range(num_test_queries):\n",
+ " # Create test query vectors\n",
+ " query_vec = np.random.random(dims).astype(np.float32)\n",
+ " query_vec = query_vec / np.linalg.norm(query_vec) # Normalize\n",
+ " test_queries.append(query_vec)\n",
+ "\n",
+ "print(f\"Generated {len(test_queries)} test queries\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Testing HNSW search quality...\n",
+ "HNSW search completed in 0.010 seconds\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Test HNSW search quality\n",
+ "print(\"๐ Testing HNSW search quality...\")\n",
+ "\n",
+ "hnsw_results = []\n",
+ "hnsw_start = time.time()\n",
+ "\n",
+ "for query_vec in test_queries:\n",
+ " query = VectorQuery(\n",
+ " vector=query_vec,\n",
+ " vector_field_name=\"embedding\",\n",
+ " return_fields=[\"movie_id\", \"title\", \"genre\"],\n",
+ " dtype=\"float32\",\n",
+ " num_results=10\n",
+ " )\n",
+ " results = hnsw_index.query(query)\n",
+ " hnsw_results.append([doc[\"movie_id\"] for doc in results])\n",
+ "\n",
+ "hnsw_time = time.time() - hnsw_start\n",
+ "print(f\"HNSW search completed in {hnsw_time:.3f} seconds\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Testing SVS-VAMANA search quality...\n",
+ "SVS-VAMANA search completed in 0.009 seconds\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Test SVS-VAMANA search quality\n",
+ "print(\"๐ Testing SVS-VAMANA search quality...\")\n",
+ "\n",
+ "svs_results = []\n",
+ "svs_start = time.time()\n",
+ "\n",
+ "for i, query_vec in enumerate(test_queries):\n",
+ " # Adjust query vector for SVS index (handle dimensionality reduction)\n",
+ " if target_dims < dims:\n",
+ " svs_query_vec = query_vec[:target_dims]\n",
+ " else:\n",
+ " svs_query_vec = query_vec\n",
+ " \n",
+ " if target_dtype == 'float16':\n",
+ " svs_query_vec = svs_query_vec.astype(np.float16)\n",
+ " \n",
+ " query = VectorQuery(\n",
+ " vector=svs_query_vec,\n",
+ " vector_field_name=\"embedding\",\n",
+ " return_fields=[\"movie_id\", \"title\", \"genre\"],\n",
+ " dtype=target_dtype,\n",
+ " num_results=10\n",
+ " )\n",
+ " results = svs_index.query(query)\n",
+ " svs_results.append([doc[\"movie_id\"] for doc in results])\n",
+ "\n",
+ "svs_time = time.time() - svs_start\n",
+ "print(f\"SVS-VAMANA search completed in {svs_time:.3f} seconds\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Search Quality Comparison\n",
+ "========================================\n",
+ "HNSW (baseline): 100% recall (exact graph-based search)\n",
+ "SVS-VAMANA Recall@5: 100.0% (vs HNSW baseline)\n",
+ "SVS-VAMANA Recall@10: 100.0% (vs HNSW baseline)\n",
+ "\n",
+ "โฑ๏ธ Performance Comparison:\n",
+ "HNSW query time: 0.010s (1.0ms per query)\n",
+ "SVS-VAMANA query time: 0.009s (0.9ms per query)\n",
+ "Speed difference: +5.9%\n",
+ "\n",
+ "๐ฏ Quality Assessment: ๐ข Excellent - Minimal quality loss\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Calculate recall and performance metrics\n",
+ "def calculate_recall(reference_results, test_results, k=10):\n",
+ " \"\"\"Calculate recall@k between two result sets\"\"\"\n",
+ " if not reference_results or not test_results:\n",
+ " return 0.0\n",
+ " \n",
+ " total_recall = 0.0\n",
+ " for ref, test in zip(reference_results, test_results):\n",
+ " ref_set = set(ref[:k])\n",
+ " test_set = set(test[:k])\n",
+ " if len(ref_set) > 0:\n",
+ " recall = len(ref_set.intersection(test_set)) / len(ref_set)\n",
+ " total_recall += recall\n",
+ " \n",
+ " return total_recall / len(reference_results)\n",
+ "\n",
+ "# Calculate metrics\n",
+ "recall_at_5 = calculate_recall(hnsw_results, svs_results, k=5)\n",
+ "recall_at_10 = calculate_recall(hnsw_results, svs_results, k=10)\n",
+ "\n",
+ "print(\n",
+ " \"๐ Search Quality Comparison\",\n",
+ " \"=\" * 40,\n",
+ " \"HNSW (baseline): 100% recall (exact graph-based search)\",\n",
+ " f\"SVS-VAMANA Recall@5: {recall_at_5*100:.1f}% (vs HNSW baseline)\",\n",
+ " f\"SVS-VAMANA Recall@10: {recall_at_10*100:.1f}% (vs HNSW baseline)\",\n",
+ " \"\",\n",
+ " \"โฑ๏ธ Performance Comparison:\",\n",
+ " f\"HNSW query time: {hnsw_time:.3f}s ({hnsw_time/num_test_queries*1000:.1f}ms per query)\",\n",
+ " f\"SVS-VAMANA query time: {svs_time:.3f}s ({svs_time/num_test_queries*1000:.1f}ms per query)\",\n",
+ " f\"Speed difference: {((hnsw_time - svs_time) / hnsw_time * 100):+.1f}%\",\n",
+ " sep=\"\\n\"\n",
+ ")\n",
+ "\n",
+ "# Quality assessment\n",
+ "if recall_at_10 >= 0.95:\n",
+ " quality_assessment = \"๐ข Excellent - Minimal quality loss\"\n",
+ "elif recall_at_10 >= 0.90:\n",
+ " quality_assessment = \"๐ก Good - Acceptable quality for most applications\"\n",
+ "elif recall_at_10 >= 0.80:\n",
+ " quality_assessment = \"๐ Fair - Consider if quality requirements are flexible\"\n",
+ "else:\n",
+ " quality_assessment = \"๐ด Poor - Migration not recommended\"\n",
+ "\n",
+ "print(f\"\\n๐ฏ Quality Assessment: {quality_assessment}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 10: Migration Decision Framework\n",
+ "\n",
+ "Based on the analysis, determine if migration is recommended."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ค Migration Decision Analysis\n",
+ "========================================\n",
+ "\n",
+ "๐ Criteria Evaluation:\n",
+ "Memory savings: 6.5% โ
(threshold: 5%)\n",
+ "Search quality: 1.000 โ
(threshold: 0.85)\n",
+ "\n",
+ "๐ฏ Migration Recommendation: ๐ข RECOMMENDED\n",
+ "๐ญ Reasoning: Migration provides significant memory savings while maintaining good search quality.\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Migration decision logic\n",
+ "memory_savings_threshold = 5 # Minimum % memory savings\n",
+ "recall_threshold = 0.85 # Minimum 85% recall@10\n",
+ "\n",
+ "memory_savings_pct = ((hnsw_memory - svs_memory) / hnsw_memory * 100) if hnsw_memory > 0 and svs_memory > 0 else 0\n",
+ "meets_memory_threshold = memory_savings_pct >= memory_savings_threshold\n",
+ "meets_quality_threshold = recall_at_10 >= recall_threshold\n",
+ "\n",
+ "print(\n",
+ " \"๐ค Migration Decision Analysis\",\n",
+ " \"=\" * 40,\n",
+ " \"\",\n",
+ " \"๐ Criteria Evaluation:\",\n",
+ " f\"Memory savings: {memory_savings_pct:.1f}% {'โ
' if meets_memory_threshold else 'โ'} (threshold: {memory_savings_threshold}%)\",\n",
+ " f\"Search quality: {recall_at_10:.3f} {'โ
' if meets_quality_threshold else 'โ'} (threshold: {recall_threshold})\",\n",
+ " \"\",\n",
+ " sep=\"\\n\"\n",
+ ")\n",
+ "\n",
+ "if meets_memory_threshold and meets_quality_threshold:\n",
+ " recommendation = \"๐ข RECOMMENDED\"\n",
+ " reasoning = \"Migration provides significant memory savings while maintaining good search quality.\"\n",
+ "elif meets_memory_threshold and not meets_quality_threshold:\n",
+ " recommendation = \"๐ก CONDITIONAL\"\n",
+ " reasoning = \"Good memory savings but reduced search quality. Consider if your application can tolerate lower recall.\"\n",
+ "elif not meets_memory_threshold and meets_quality_threshold:\n",
+ " recommendation = \"๐ LIMITED BENEFIT\"\n",
+ " reasoning = \"Search quality is maintained but memory savings are minimal. Migration may not be worth the effort.\"\n",
+ "else:\n",
+ " recommendation = \"๐ด NOT RECOMMENDED\"\n",
+ " reasoning = \"Insufficient memory savings and/or poor search quality. Consider alternative optimization strategies.\"\n",
+ "\n",
+ "print(\n",
+ " f\"๐ฏ Migration Recommendation: {recommendation}\",\n",
+ " f\"๐ญ Reasoning: {reasoning}\",\n",
+ " sep=\"\\n\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 12: Cleanup\n",
+ "\n",
+ "Clean up the demonstration indices."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐งน Cleaning up demonstration indices...\n",
+ "โ
Deleted HNSW demonstration index\n",
+ "โ
Deleted SVS-VAMANA demonstration index\n",
+ "\n",
+ "๐ HNSW to SVS-VAMANA migration demonstration complete!\n",
+ "\n",
+ "Next steps:\n",
+ "1. Apply learnings to your production HNSW indices\n",
+ "2. Test with your actual query patterns and data\n",
+ "3. Monitor performance in your environment\n",
+ "4. Consider gradual rollout strategy\n",
+ "5. Evaluate impact on applications using HNSW-specific features\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(\"๐งน Cleaning up demonstration indices...\")\n",
+ "\n",
+ "# Clean up HNSW index\n",
+ "try:\n",
+ " hnsw_index.delete(drop=True)\n",
+ " print(\"โ
Deleted HNSW demonstration index\")\n",
+ "except Exception as e:\n",
+ " print(f\"โ ๏ธ Failed to delete HNSW index: {e}\")\n",
+ "\n",
+ "# Clean up SVS index\n",
+ "try:\n",
+ " svs_index.delete(drop=True)\n",
+ " print(\"โ
Deleted SVS-VAMANA demonstration index\")\n",
+ "except Exception as e:\n",
+ " print(f\"โ ๏ธ Failed to delete SVS index: {e}\")\n",
+ "\n",
+ "print(\n",
+ " \"\\n๐ HNSW to SVS-VAMANA migration demonstration complete!\",\n",
+ " \"\\nNext steps:\",\n",
+ " \"1. Apply learnings to your production HNSW indices\",\n",
+ " \"2. Test with your actual query patterns and data\",\n",
+ " \"3. Monitor performance in your environment\",\n",
+ " \"4. Consider gradual rollout strategy\",\n",
+ " \"5. Evaluate impact on applications using HNSW-specific features\",\n",
+ " sep=\"\\n\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.12.6"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/python-recipes/vector-search/07_flat_to_svs_vamana_migration.ipynb b/python-recipes/vector-search/07_flat_to_svs_vamana_migration.ipynb
new file mode 100644
index 0000000..6b7789f
--- /dev/null
+++ b/python-recipes/vector-search/07_flat_to_svs_vamana_migration.ipynb
@@ -0,0 +1,1090 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "\n",
+ "# Migrating from FLAT to SVS-VAMANA\n",
+ "\n",
+ "## Let's Begin!\n",
+ "
\n",
+ "\n",
+ "This notebook demonstrates how to migrate existing FLAT vector indices to SVS-VAMANA for improved memory efficiency and cost savings.\n",
+ "\n",
+ "## What You'll Learn\n",
+ "\n",
+ "- How to assess your current FLAT index for migration\n",
+ "- Step-by-step migration from FLAT to SVS-VAMANA\n",
+ "- Memory usage comparison and cost analysis\n",
+ "- Search quality validation\n",
+ "- Performance benchmarking\n",
+ "- Migration decision framework\n",
+ "\n",
+ "## Prerequisites\n",
+ "\n",
+ "- Redis Stack 8.2.0+ with RediSearch 2.8.10+\n",
+ "- Existing vector index with substantial data (1000+ documents recommended)\n",
+ "- Vector embeddings (768 dimensions using sentence-transformers/all-mpnet-base-v2)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## ๐ FLAT to SVS-VAMANA Migration Checklist\n",
+ "\n",
+ "**PRE-MIGRATION:**\n",
+ "- โ Backup existing FLAT index data\n",
+ "- โ Test migration on staging environment\n",
+ "- โ Validate search quality with real queries\n",
+ "- โ Measure baseline FLAT performance metrics\n",
+ "- โ Plan rollback strategy\n",
+ "- โ Document current FLAT index configuration\n",
+ "\n",
+ "**MIGRATION:**\n",
+ "- โ Create SVS-VAMANA index with tested configuration\n",
+ "- โ Migrate data in batches during low-traffic periods\n",
+ "- โ Monitor memory usage and indexing progress\n",
+ "- โ Validate data integrity after migration\n",
+ "- โ Test search functionality thoroughly\n",
+ "- โ Compare recall metrics with baseline\n",
+ "\n",
+ "**POST-MIGRATION:**\n",
+ "- โ Monitor search performance and quality\n",
+ "- โ Track memory usage and cost savings\n",
+ "- โ Update application configuration\n",
+ "- โ Document new SVS-VAMANA settings\n",
+ "- โ Clean up old FLAT index after validation period\n",
+ "- โ Update monitoring and alerting thresholds\n",
+ "\n",
+ "**๐ก FLAT-SPECIFIC TIPS:**\n",
+ "- FLAT indices are simpler to migrate than HNSW (no graph structure)\n",
+ "- FLAT provides 100% recall, so focus on acceptable recall threshold for SVS-VAMANA\n",
+ "- SVS-VAMANA will be faster than FLAT for large datasets\n",
+ "- Memory savings are most significant with FLAT migrations\n",
+ "- Consider using compression for maximum memory reduction\n",
+ "- Test query performance improvements with your dataset size"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## ๐ฆ Installation & Setup\n",
+ "\n",
+ "This notebook uses **RedisVL vectorizers** for generating embeddings and **Redis Stack** for vector search.\n",
+ "\n",
+ "**Requirements:**\n",
+ "- Redis Stack 8.2.0+ with RediSearch 2.8.10+ (for SVS-VAMANA support)\n",
+ "- redisvl>=0.11.0 (required for SVS-VAMANA migration features and vectorizers)\n",
+ "- redis-py>=6.4.0 (required for compatibility with RedisVL 0.11.0+)\n",
+ "- numpy (for vector operations)\n",
+ "\n",
+ "**โ ๏ธ Important:** If you encounter Redis connection errors, upgrade redis-py: `pip install -U \"redis>=6.4.0\"`"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Install Packages"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "%pip install git+https://github.com/redis/redis-vl-python.git \"redis>=6.4.0\" \"numpy>=1.21.0\" \"sentence-transformers>=2.2.0\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Install Redis Stack\n",
+ "\n",
+ "Later in this tutorial, Redis will be used to store, index, and query vector\n",
+ "embeddings and full text fields. **We need to have a Redis\n",
+ "instance available.**\n",
+ "\n",
+ "#### Local Redis\n",
+ "Use the shell script below to download, extract, and install [Redis Stack](https://redis.io/docs/getting-started/install-stack/) directly from the Redis package archive."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# NBVAL_SKIP\n",
+ "%%sh\n",
+ "curl -fsSL https://packages.redis.io/gpg | sudo gpg --dearmor -o /usr/share/keyrings/redis-archive-keyring.gpg\n",
+ "echo \"deb [signed-by=/usr/share/keyrings/redis-archive-keyring.gpg] https://packages.redis.io/deb $(lsb_release -cs) main\" | sudo tee /etc/apt/sources.list.d/redis.list\n",
+ "sudo apt-get update > /dev/null 2>&1\n",
+ "sudo apt-get install redis-stack-server > /dev/null 2>&1\n",
+ "redis-stack-server --daemonize yes"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Alternative Redis Access (Cloud, Docker, other)\n",
+ "There are many ways to get the necessary redis-stack instance running\n",
+ "1. On cloud, deploy a [FREE instance of Redis in the cloud](https://redis.com/try-free/). Or, if you have your\n",
+ "own version of Redis Enterprise running, that works too!\n",
+ "2. Per OS, [see the docs](https://redis.io/docs/latest/operate/oss_and_stack/install/install-stack/)\n",
+ "3. With docker: `docker run -d --name redis-stack-server -p 6379:6379 redis/redis-stack-server:latest`"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Define the Redis Connection URL\n",
+ "\n",
+ "By default this notebook connects to the local instance of Redis Stack. **If you have your own Redis Enterprise instance** - replace REDIS_PASSWORD, REDIS_HOST and REDIS_PORT values with your own."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "import sys\n",
+ "import subprocess\n",
+ "# Required imports from redis-vl\n",
+ "import numpy as np\n",
+ "import time\n",
+ "from redisvl.index import SearchIndex\n",
+ "from redisvl.query import VectorQuery\n",
+ "from redisvl.redis.utils import array_to_buffer, buffer_to_array\n",
+ "from redisvl.utils import CompressionAdvisor\n",
+ "from redisvl.redis.connection import supports_svs\n",
+ "import redis\n",
+ "\n",
+ "# RedisVL Vectorizer imports\n",
+ "from redisvl.utils.vectorize import HFTextVectorizer\n",
+ "\n",
+ "# Replace values below with your own if using Redis Cloud instance\n",
+ "REDIS_HOST = os.getenv(\"REDIS_HOST\", \"localhost\") # ex: \"redis-18374.c253.us-central1-1.gce.cloud.redislabs.com\"\n",
+ "REDIS_PORT = os.getenv(\"REDIS_PORT\", \"6379\") # ex: 18374\n",
+ "REDIS_PASSWORD = os.getenv(\"REDIS_PASSWORD\", \"\") # ex: \"1TNxTEdYRDgIDKM2gDfasupCADXXXX\"\n",
+ "\n",
+ "# If SSL is enabled on the endpoint, use rediss:// as the URL prefix\n",
+ "REDIS_URL = f\"redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 1: Verify SVS-VAMANA Support\n",
+ "\n",
+ "First, let's ensure your Redis environment supports SVS-VAMANA."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "โ
Redis connection successful\n",
+ "โ
SVS-VAMANA supported\n",
+ " Ready for migration!\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Check Redis connection and SVS support\n",
+ "REDIS_URL = \"redis://localhost:6379\"\n",
+ "\n",
+ "try:\n",
+ " client = redis.Redis.from_url(REDIS_URL)\n",
+ " client.ping()\n",
+ " print(\"โ
Redis connection successful\")\n",
+ " \n",
+ " if supports_svs(client):\n",
+ " print(\"โ
SVS-VAMANA supported\")\n",
+ " print(\" Ready for migration!\")\n",
+ " else:\n",
+ " print(\"โ SVS-VAMANA not supported\")\n",
+ " print(\" Requires Redis >= 8.2.0 with RediSearch >= 2.8.10\")\n",
+ " print(\" Please upgrade Redis Stack before proceeding\")\n",
+ " \n",
+ "except Exception as e:\n",
+ " print(f\"โ Redis connection failed: {e}\")\n",
+ " print(\" Please ensure Redis is running and accessible\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 2: Assess Your Current Index\n",
+ "\n",
+ "For this demonstration, we'll create a sample FLAT index. In practice, you would analyze your existing index."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ฅ Loading sample movie data...\n",
+ "Loaded 20 movie records\n",
+ "Sample movie: Explosive Pursuit - A daring cop chases a notorious criminal across the city in a high-stakes game of cat and mouse.\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Download sample data from redis-ai-resources\n",
+ "print(\"๐ฅ Loading sample movie data...\")\n",
+ "import os\n",
+ "import json\n",
+ "\n",
+ "# Load the movies dataset\n",
+ "url = \"resources/movies.json\"\n",
+ "with open(\"resources/movies.json\", \"r\") as f:\n",
+ " movies_data = json.load(f)\n",
+ "\n",
+ "print(f\"Loaded {len(movies_data)} movie records\")\n",
+ "print(f\"Sample movie: {movies_data[0]['title']} - {movies_data[0]['description']}\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Migration Assessment\n",
+ "Vector dimensions: 768\n",
+ "Dataset size: 20 movie documents\n",
+ "Data includes: title, genre, rating, description\n",
+ "Vectorizer: RedisVL HFTextVectorizer\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Configuration for demonstration \n",
+ "dims = 768 # Using all-mpnet-base-v2 model (768 dimensions)\n",
+ "\n",
+ "num_docs = len(movies_data) # Use actual dataset size\n",
+ "\n",
+ "print(\n",
+ " \"๐ Migration Assessment\",\n",
+ " f\"Vector dimensions: {dims}\",\n",
+ " f\"Dataset size: {num_docs} movie documents\",\n",
+ " \"Data includes: title, genre, rating, description\",\n",
+ " f\"Vectorizer: RedisVL HFTextVectorizer\",\n",
+ " sep=\"\\n\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "---\n",
+ "Next, let's configure a smaple FLAT index. Notice the algorithm value, dims value, and datatype value under fields."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Creating sample FLAT index...\n",
+ "12:00:03 redisvl.index.index INFO Index already exists, overwriting.\n",
+ "โ
Created FLAT index: migration_demo_flat\n"
+ ]
+ }
+ ],
+ "source": [
+ "flat_schema = {\n",
+ " \"index\": {\n",
+ " \"name\": \"migration_demo_flat\",\n",
+ " \"prefix\": \"demo:flat:\",\n",
+ " },\n",
+ " \"fields\": [\n",
+ " {\"name\": \"movie_id\", \"type\": \"tag\"},\n",
+ " {\"name\": \"title\", \"type\": \"text\"},\n",
+ " {\"name\": \"genre\", \"type\": \"tag\"},\n",
+ " {\"name\": \"rating\", \"type\": \"numeric\"},\n",
+ " {\"name\": \"description\", \"type\": \"text\"},\n",
+ " {\n",
+ " \"name\": \"embedding\",\n",
+ " \"type\": \"vector\",\n",
+ " \"attrs\": {\n",
+ " \"dims\": dims,\n",
+ " \"algorithm\": \"flat\",\n",
+ " \"datatype\": \"float32\",\n",
+ " \"distance_metric\": \"cosine\"\n",
+ " }\n",
+ " }\n",
+ " ]\n",
+ "}\n",
+ "\n",
+ "# Create and populate FLAT index\n",
+ "print(\"Creating sample FLAT index...\")\n",
+ "flat_index = SearchIndex.from_dict(flat_schema, redis_url=REDIS_URL)\n",
+ "flat_index.create(overwrite=True)\n",
+ "print(f\"โ
Created FLAT index: {flat_index.name}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "---\n",
+ "Generate embeddings for movie descriptions\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Generating embeddings for movie descriptions...\n",
+ "๐ Using RedisVL HFTextVectorizer...\n",
+ "12:00:07 sentence_transformers.SentenceTransformer INFO Use pytorch device_name: mps\n",
+ "12:00:07 sentence_transformers.SentenceTransformer INFO Load pretrained SentenceTransformer: sentence-transformers/all-mpnet-base-v2\n",
+ "โ
Generated 20 real embeddings using RedisVL HFTextVectorizer\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Generate embeddings using RedisVL vectorizers\n",
+ "print(\"๐ Generating embeddings for movie descriptions...\")\n",
+ "embedding_model=\"sentence-transformers/all-mpnet-base-v2\"\n",
+ "descriptions = [movie['description'] for movie in movies_data]\n",
+ "\n",
+ "# Use RedisVL HFTextVectorizer\n",
+ "print(\"๐ Using RedisVL HFTextVectorizer...\")\n",
+ "vectorizer = HFTextVectorizer(\n",
+ " model=embedding_model # 768 dimensions\n",
+ ")\n",
+ "\n",
+ "# Generate embeddings using RedisVL vectorizer\n",
+ "embeddings = vectorizer.embed_many(descriptions)\n",
+ "embeddings = np.array(embeddings, dtype=np.float32)\n",
+ "\n",
+ "print(f\"โ
Generated {len(embeddings)} real embeddings using RedisVL HFTextVectorizer\")\n",
+ "\n",
+ "# Prepare data for loading\n",
+ "sample_data = []\n",
+ "for i, movie in enumerate(movies_data):\n",
+ " sample_data.append({\n",
+ " 'movie_id': str(movie['id']),\n",
+ " 'title': movie['title'],\n",
+ " 'genre': movie['genre'],\n",
+ " 'rating': movie['rating'],\n",
+ " 'description': movie['description'],\n",
+ " 'embedding': array_to_buffer(embeddings[i].astype(np.float32), dtype='float32')\n",
+ " })"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ฅ Loading data into FLAT index...\n",
+ " Loaded 20/20 documents\n",
+ "Waiting for indexing to complete...\n",
+ "\n",
+ "โ
FLAT index loaded with 40 documents\n",
+ "Index size: 3.0174942016601563 MB\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Load data into FLAT index\n",
+ "print(\"๐ฅ Loading data into FLAT index...\")\n",
+ "batch_size = 100 # Process in batches\n",
+ "\n",
+ "for i in range(0, len(sample_data), batch_size):\n",
+ " batch = sample_data[i:i+batch_size]\n",
+ " flat_index.load(batch)\n",
+ " print(f\" Loaded {min(i+batch_size, len(sample_data))}/{len(sample_data)} documents\")\n",
+ "\n",
+ "# Wait for indexing to complete\n",
+ "print(\"Waiting for indexing to complete...\")\n",
+ "time.sleep(3)\n",
+ "\n",
+ "flat_info = flat_index.info()\n",
+ "print(f\"\\nโ
FLAT index loaded with {flat_info['num_docs']} documents\")\n",
+ "print(f\"Index size: {flat_info.get('vector_index_sz_mb', 'N/A')} MB\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 3: Get Compression Recommendation\n",
+ "\n",
+ "The CompressionAdvisor analyzes your vector dimensions and provides optimal compression settings for SVS-VAMANA vector indices. It eliminates the guesswork from parameter tuning by providing intelligent recommendations based on your vector characteristics and performance priorities.\n",
+ "\n",
+ "## Configuration Strategy\n",
+ "**High-Dimensional Vectors (โฅ1024 dims)**: Uses **LeanVec4x8** compression with dimensionality reduction. Memory priority reduces dimensions by 50%, speed priority by\n",
+ "25%, balanced by 50%. Achieves 60-80% memory savings.\n",
+ "\n",
+ "**Lower-Dimensional Vectors (<1024 dims)**: Uses **LVQ compression** without dimensionality reduction. Memory priority uses LVQ4 (4 bits), speed uses LVQ4x8 (12 bits),\n",
+ "balanced uses LVQ4x4 (8 bits). Achieves 60-87% memory savings.\n",
+ "\n",
+ "**Our Configuration (768 dims)**: Will use **LVQ compression** as we're below the 1024 dimension threshold. This provides excellent compression without dimensionality reduction.\n",
+ "\n",
+ "## Available Compression Types\n",
+ "- **LVQ4/LVQ4x4/LVQ4x8**: 4/8/12 bits per dimension\n",
+ "- **LeanVec4x8/LeanVec8x8**: 12/16 bits + dimensionality reduction for high-dim vectors\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Analyzing compression options...\n",
+ "\n",
+ "MEMORY priority:\n",
+ " Algorithm: svs-vamana\n",
+ " Compression: LVQ4\n",
+ " Datatype: float32\n",
+ "\n",
+ "BALANCED priority:\n",
+ " Algorithm: svs-vamana\n",
+ " Compression: LVQ4x4\n",
+ " Datatype: float32\n",
+ "\n",
+ "PERFORMANCE priority:\n",
+ " Algorithm: svs-vamana\n",
+ " Compression: LVQ4x4\n",
+ " Datatype: float32\n",
+ "\n",
+ "๐ Selected configuration: LVQ4 with float32\n",
+ "Expected memory savings: Significant for 768-dimensional vectors\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Get compression recommendation\n",
+ "print(\"๐ Analyzing compression options...\")\n",
+ "print()\n",
+ "\n",
+ "# Try different priorities to show options\n",
+ "priorities = [\"memory\", \"balanced\", \"performance\"]\n",
+ "configs = {}\n",
+ "\n",
+ "for priority in priorities:\n",
+ " config = CompressionAdvisor.recommend(dims=dims, priority=priority)\n",
+ " configs[priority] = config\n",
+ " print(f\"{priority.upper()} priority:\")\n",
+ " print(f\" Algorithm: {config.algorithm}\")\n",
+ " print(f\" Compression: {config.compression if hasattr(config, 'compression') else 'None'}\")\n",
+ " print(f\" Datatype: {config.datatype}\")\n",
+ " if hasattr(config, 'reduce') and config.reduce:\n",
+ " reduction = ((dims - config.reduce) / dims) * 100\n",
+ " print(f\" Dimensionality: {dims} โ {config.reduce} ({reduction:.1f}% reduction)\")\n",
+ " print()\n",
+ "\n",
+ "# Select memory-optimized configuration for migration\n",
+ "selected_config = configs[\"memory\"]\n",
+ "print(f\"๐ Selected configuration: {selected_config.compression if hasattr(selected_config, 'compression') else 'None'} with {selected_config.datatype}\")\n",
+ "print(f\"Expected memory savings: Significant for {dims}-dimensional vectors\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 4: Create SVS-VAMANA Index\n",
+ "\n",
+ "Now we'll create the new SVS-VAMANA index with the recommended compression settings."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Creating SVS-VAMANA index with compression...\n",
+ "12:01:03 redisvl.index.index INFO Index already exists, overwriting.\n",
+ "โ
Created SVS-VAMANA index: migration_demo_svs\n",
+ "Compression: LVQ4\n",
+ "Datatype: float32\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Fallback configuration if not defined (for CI/CD compatibility)\n",
+ "if 'selected_config' not in locals():\n",
+ " from redisvl.utils import CompressionAdvisor\n",
+ " selected_config = CompressionAdvisor.recommend(dims=dims, priority=\"memory\")\n",
+ "\n",
+ "# Create SVS-VAMANA schema with compression\n",
+ "svs_schema = {\n",
+ " \"index\": {\n",
+ " \"name\": \"migration_demo_svs\",\n",
+ " \"prefix\": \"demo:svs:\",\n",
+ " },\n",
+ " \"fields\": [\n",
+ " {\"name\": \"movie_id\", \"type\": \"tag\"},\n",
+ " {\"name\": \"title\", \"type\": \"text\"},\n",
+ " {\"name\": \"genre\", \"type\": \"tag\"},\n",
+ " {\"name\": \"rating\", \"type\": \"numeric\"},\n",
+ " {\"name\": \"description\", \"type\": \"text\"},\n",
+ " {\n",
+ " \"name\": \"embedding\",\n",
+ " \"type\": \"vector\",\n",
+ " \"attrs\": {\n",
+ " \"dims\": selected_config.reduce if (hasattr(selected_config, 'reduce') and selected_config.reduce is not None) else dims,\n",
+ " \"algorithm\": \"svs-vamana\",\n",
+ " \"datatype\": selected_config.datatype,\n",
+ " \"distance_metric\": \"cosine\"\n",
+ " # Note: Don't include the full selected_config to avoid dims/reduce conflict\n",
+ " }\n",
+ " }\n",
+ " ]\n",
+ "}\n",
+ "\n",
+ "print(\"Creating SVS-VAMANA index with compression...\")\n",
+ "svs_index = SearchIndex.from_dict(svs_schema, redis_url=REDIS_URL)\n",
+ "svs_index.create(overwrite=True)\n",
+ "print(f\"โ
Created SVS-VAMANA index: {svs_index.name}\")\n",
+ "print(f\"Compression: {selected_config.compression if hasattr(selected_config, 'compression') else 'None'}\")\n",
+ "print(f\"Datatype: {selected_config.datatype}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 5: Migrate Data\n",
+ "\n",
+ "Extract data from the original index and load it into the SVS-VAMANA index with compression applied."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Migrating data to SVS-VAMANA...\n",
+ "Target dimensions: 768 (from 768)\n",
+ "Target datatype: float32\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(\"๐ Migrating data to SVS-VAMANA...\")\n",
+ "\n",
+ "# Fallback configuration if not defined (for CI/CD compatibility)\n",
+ "if 'selected_config' not in locals():\n",
+ " from redisvl.utils import CompressionAdvisor\n",
+ " selected_config = CompressionAdvisor.recommend(dims=dims, priority=\"memory\")\n",
+ "\n",
+ "# Determine target vector dimensions (may be reduced by LeanVec)\n",
+ "# Use reduce if it exists and is not None, otherwise use original dims\n",
+ "target_dims = selected_config.reduce if (hasattr(selected_config, 'reduce') and selected_config.reduce is not None) else dims\n",
+ "target_dtype = selected_config.datatype\n",
+ "\n",
+ "print(f\"Target dimensions: {target_dims} (from {dims})\")\n",
+ "print(f\"Target datatype: {target_dtype}\")\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Extracting data from original index...\n",
+ "Found 40 documents to migrate\n",
+ "Prepared 40 documents for migration\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Extract data from FLAT index\n",
+ "print(\"Extracting data from original index...\")\n",
+ "keys = client.keys(\"demo:flat:*\")\n",
+ "print(f\"Found {len(keys)} documents to migrate\")\n",
+ "\n",
+ "# Process and transform data for SVS index\n",
+ "svs_data = []\n",
+ "for i, key in enumerate(keys):\n",
+ " doc_data = client.hgetall(key)\n",
+ " \n",
+ " if b'embedding' in doc_data:\n",
+ " # Extract original vector\n",
+ " original_vector = np.array(buffer_to_array(doc_data[b'embedding'], dtype='float32'))\n",
+ " \n",
+ " # Apply dimensionality reduction if needed (LeanVec)\n",
+ " if target_dims < dims:\n",
+ " vector = original_vector[:target_dims]\n",
+ " else:\n",
+ " vector = original_vector\n",
+ " \n",
+ " # Convert to target datatype\n",
+ " if target_dtype == 'float16':\n",
+ " vector = vector.astype(np.float16)\n",
+ " \n",
+ " svs_data.append({\n",
+ " \"movie_id\": doc_data[b'movie_id'].decode(),\n",
+ " \"title\": doc_data[b'title'].decode(),\n",
+ " \"genre\": doc_data[b'genre'].decode(),\n",
+ " \"rating\": int(doc_data[b'rating'].decode()),\n",
+ " \"description\": doc_data[b'description'].decode(),\n",
+ " \"embedding\": array_to_buffer(vector, dtype=target_dtype)\n",
+ " })\n",
+ " \n",
+ " if (i + 1) % 500 == 0:\n",
+ " print(f\" Processed {i + 1}/{len(keys)} documents\")\n",
+ "\n",
+ "print(f\"Prepared {len(svs_data)} documents for migration\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Loading data into SVS-VAMANA index...\n",
+ " Migrated 40/40 documents\n",
+ "Waiting for indexing to complete...\n",
+ "\n",
+ "โ
Migration complete! SVS index has 60 documents\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Load data into SVS index\n",
+ "print(\"Loading data into SVS-VAMANA index...\")\n",
+ "batch_size = 100 # Define batch size for migration\n",
+ "\n",
+ "if len(svs_data) > 0:\n",
+ " for i in range(0, len(svs_data), batch_size):\n",
+ " batch = svs_data[i:i+batch_size]\n",
+ " svs_index.load(batch)\n",
+ " print(f\" Migrated {min(i+batch_size, len(svs_data))}/{len(svs_data)} documents\")\n",
+ "\n",
+ " # Wait for indexing to complete\n",
+ " print(\"Waiting for indexing to complete...\")\n",
+ " time.sleep(5)\n",
+ "\n",
+ " svs_info = svs_index.info()\n",
+ " print(f\"\\nโ
Migration complete! SVS index has {svs_info['num_docs']} documents\")\n",
+ "else:\n",
+ " print(\"โ ๏ธ No data to migrate. Make sure the FLAT index was populated first.\")\n",
+ " print(\" Run the previous cells to load data into the FLAT index.\")\n",
+ " svs_info = svs_index.info()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 6: Compare Memory Usage\n",
+ "\n",
+ "Let's analyze the memory savings achieved through compression. This is just an example on the small sample data. Use a larger dataset before deciding."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Memory Usage Comparison\n",
+ "========================================\n",
+ "Original FLAT index: 3.02 MB\n",
+ "SVS-VAMANA index: 3.02 MB\n",
+ "\n",
+ "๐ฐ Memory savings: -0.1%\n",
+ "Absolute reduction: -0.00 MB\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Helper function to extract memory info\n",
+ "def get_memory_mb(index_info):\n",
+ " \"\"\"Extract memory usage in MB from index info\"\"\"\n",
+ " memory = index_info.get('vector_index_sz_mb', 0)\n",
+ " if isinstance(memory, str):\n",
+ " try:\n",
+ " return float(memory)\n",
+ " except ValueError:\n",
+ " return 0.0\n",
+ " return float(memory)\n",
+ "\n",
+ "# Get memory usage\n",
+ "flat_memory = get_memory_mb(flat_info)\n",
+ "svs_memory = get_memory_mb(svs_info)\n",
+ "\n",
+ "print(\n",
+ " \"๐ Memory Usage Comparison\",\n",
+ " \"=\" * 40,\n",
+ " f\"Original FLAT index: {flat_memory:.2f} MB\",\n",
+ " f\"SVS-VAMANA index: {svs_memory:.2f} MB\",\n",
+ " \"\",\n",
+ " sep=\"\\n\"\n",
+ ")\n",
+ "\n",
+ "if flat_memory > 0:\n",
+ " if svs_memory > 0:\n",
+ " savings = ((flat_memory - svs_memory) / flat_memory) * 100\n",
+ " print(\n",
+ " f\"๐ฐ Memory savings: {savings:.1f}%\",\n",
+ " f\"Absolute reduction: {flat_memory - svs_memory:.2f} MB\",\n",
+ " sep=\"\\n\"\n",
+ " )\n",
+ " else:\n",
+ " print(\"โณ SVS index still indexing - memory comparison pending\")\n",
+ "else:\n",
+ " print(\"โ ๏ธ Memory information not available\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 7: Validate Search Quality\n",
+ "\n",
+ "Compare search quality and performance between FLAT and SVS-VAMANA indices."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ Search Quality Comparison\n",
+ "========================================\n",
+ "Recall@5: 0.667 (66.7%)\n",
+ "Recall@10: 0.800 (80.0%)\n",
+ "\n",
+ "โฑ๏ธ Performance Comparison:\n",
+ "FLAT query time: 0.018s (1.8ms per query)\n",
+ "SVS-VAMANA query time: 0.013s (1.3ms per query)\n",
+ "Speed difference: +28.3%\n",
+ "\n",
+ "๐ฏ Quality Assessment: ๐ Fair - Consider if quality requirements are flexible\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Calculate recall and performance metrics\n",
+ "def calculate_recall(reference_results, test_results, k=10):\n",
+ " \"\"\"Calculate recall@k between two result sets\"\"\"\n",
+ " if not reference_results or not test_results:\n",
+ " return 0.0\n",
+ " \n",
+ " ref_ids = set([doc['movie_id'] for doc in reference_results[:k]])\n",
+ " test_ids = set([doc['movie_id'] for doc in test_results[:k]])\n",
+ " \n",
+ " if not ref_ids:\n",
+ " return 0.0\n",
+ " \n",
+ " return len(ref_ids.intersection(test_ids)) / len(ref_ids)\n",
+ "\n",
+ "# Create test queries\n",
+ "num_test_queries = 10\n",
+ "test_queries = []\n",
+ "\n",
+ "for i in range(num_test_queries):\n",
+ " query_vec = np.random.random(dims).astype(np.float32)\n",
+ " query_vec = query_vec / np.linalg.norm(query_vec)\n",
+ " test_queries.append(query_vec)\n",
+ "\n",
+ "# Test FLAT index (ground truth)\n",
+ "flat_results_list = []\n",
+ "flat_start = time.time()\n",
+ "\n",
+ "for query_vec in test_queries:\n",
+ " query = VectorQuery(\n",
+ " vector=query_vec,\n",
+ " vector_field_name=\"embedding\",\n",
+ " return_fields=[\"movie_id\", \"title\", \"genre\"],\n",
+ " dtype=\"float32\",\n",
+ " num_results=10\n",
+ " )\n",
+ " results = flat_index.query(query)\n",
+ " flat_results_list.append(results)\n",
+ "\n",
+ "flat_time = time.time() - flat_start\n",
+ "\n",
+ "# Test SVS-VAMANA index\n",
+ "svs_results_list = []\n",
+ "svs_start = time.time()\n",
+ "\n",
+ "for query_vec in test_queries:\n",
+ " # Adjust query vector for SVS index (handle dimensionality reduction)\n",
+ " if target_dims < dims:\n",
+ " svs_query_vec = query_vec[:target_dims]\n",
+ " else:\n",
+ " svs_query_vec = query_vec\n",
+ " \n",
+ " if target_dtype == 'float16':\n",
+ " svs_query_vec = svs_query_vec.astype(np.float16)\n",
+ " \n",
+ " query = VectorQuery(\n",
+ " vector=svs_query_vec,\n",
+ " vector_field_name=\"embedding\",\n",
+ " return_fields=[\"movie_id\", \"title\", \"genre\"],\n",
+ " dtype=target_dtype,\n",
+ " num_results=10\n",
+ " )\n",
+ " results = svs_index.query(query)\n",
+ " svs_results_list.append(results)\n",
+ "\n",
+ "svs_time = time.time() - svs_start\n",
+ "\n",
+ "# Calculate recall metrics\n",
+ "recall_at_5 = np.mean([calculate_recall(flat_res, svs_res, k=5) \n",
+ " for flat_res, svs_res in zip(flat_results_list, svs_results_list)])\n",
+ "recall_at_10 = np.mean([calculate_recall(flat_res, svs_res, k=10) \n",
+ " for flat_res, svs_res in zip(flat_results_list, svs_results_list)])\n",
+ "\n",
+ "print(\n",
+ " \"๐ Search Quality Comparison\",\n",
+ " \"=\" * 40,\n",
+ " \"FLAT (baseline): 100% recall (brute-force exact search)\",\n",
+ " f\"SVS-VAMANA Recall@5: {recall_at_5*100:.1f}% (vs FLAT baseline)\",\n",
+ " f\"SVS-VAMANA Recall@10: {recall_at_10*100:.1f}% (vs FLAT baseline)\",\n",
+ " \"\",\n",
+ " \"โฑ๏ธ Performance Comparison:\",\n",
+ " f\"FLAT query time: {flat_time:.3f}s ({flat_time/num_test_queries*1000:.1f}ms per query)\",\n",
+ " f\"SVS-VAMANA query time: {svs_time:.3f}s ({svs_time/num_test_queries*1000:.1f}ms per query)\",\n",
+ " f\"Speed difference: {((flat_time - svs_time) / flat_time * 100):+.1f}%\",\n",
+ " sep=\"\\n\"\n",
+ ")\n",
+ "\n",
+ "# Quality assessment\n",
+ "if recall_at_10 >= 0.95:\n",
+ " quality_assessment = \"๐ข Excellent - Minimal quality loss\"\n",
+ "elif recall_at_10 >= 0.90:\n",
+ " quality_assessment = \"๐ก Good - Acceptable quality for most applications\"\n",
+ "elif recall_at_10 >= 0.80:\n",
+ " quality_assessment = \"๐ Fair - Consider if quality requirements are flexible\"\n",
+ "else:\n",
+ " quality_assessment = \"๐ด Poor - Migration not recommended\"\n",
+ "\n",
+ "print(f\"\\n๐ฏ Quality Assessment: {quality_assessment}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 8: Migration Decision Framework\n",
+ "\n",
+ "Analyze the migration results and provide a recommendation based on memory savings and search quality."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐ค Migration Decision Analysis\n",
+ "========================================\n",
+ "\n",
+ "๐ Criteria Evaluation:\n",
+ "Memory savings: -0.1% โ (threshold: 5%)\n",
+ "Search quality: 0.800 โ (threshold: 0.85)\n",
+ "\n",
+ "๐ฏ Migration Recommendation: ๐ด NOT RECOMMENDED\n",
+ "๐ญ Reasoning: Insufficient memory savings and/or poor search quality. Consider alternative optimization strategies.\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Migration decision logic\n",
+ "memory_savings_threshold = 5 # Minimum % memory savings\n",
+ "recall_threshold = 0.85 # Minimum 85% recall@10\n",
+ "\n",
+ "memory_savings_pct = ((flat_memory - svs_memory) / flat_memory * 100) if flat_memory > 0 and svs_memory > 0 else 0\n",
+ "meets_memory_threshold = memory_savings_pct >= memory_savings_threshold\n",
+ "meets_quality_threshold = recall_at_10 >= recall_threshold\n",
+ "\n",
+ "print(\n",
+ " \"๐ค Migration Decision Analysis\",\n",
+ " \"=\" * 40,\n",
+ " \"\",\n",
+ " \"๐ Criteria Evaluation:\",\n",
+ " f\"Memory savings: {memory_savings_pct:.1f}% {'โ
' if meets_memory_threshold else 'โ'} (threshold: {memory_savings_threshold}%)\",\n",
+ " f\"Search quality: {recall_at_10:.3f} {'โ
' if meets_quality_threshold else 'โ'} (threshold: {recall_threshold})\",\n",
+ " \"\",\n",
+ " sep=\"\\n\"\n",
+ ")\n",
+ "\n",
+ "if meets_memory_threshold and meets_quality_threshold:\n",
+ " recommendation = \"๐ข RECOMMENDED\"\n",
+ " reasoning = \"Migration provides significant memory savings while maintaining good search quality.\"\n",
+ "elif meets_memory_threshold and not meets_quality_threshold:\n",
+ " recommendation = \"๐ก CONDITIONAL\"\n",
+ " reasoning = \"Good memory savings but reduced search quality. Consider if your application can tolerate lower recall.\"\n",
+ "elif not meets_memory_threshold and meets_quality_threshold:\n",
+ " recommendation = \"๐ LIMITED BENEFIT\"\n",
+ " reasoning = \"Search quality is maintained but memory savings are minimal. Migration may not be worth the effort.\"\n",
+ "else:\n",
+ " recommendation = \"๐ด NOT RECOMMENDED\"\n",
+ " reasoning = \"Insufficient memory savings and/or poor search quality. Consider alternative optimization strategies.\"\n",
+ "\n",
+ "print(\n",
+ " f\"๐ฏ Migration Recommendation: {recommendation}\",\n",
+ " f\"๐ญ Reasoning: {reasoning}\",\n",
+ " sep=\"\\n\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 9: Cleanup\n",
+ "\n",
+ "Clean up the demonstration indices."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "๐งน Cleaning up demonstration indices...\n",
+ "โ
Deleted FLAT demonstration index\n",
+ "โ
Deleted SVS-VAMANA demonstration index\n",
+ "\n",
+ "๐ Migration demonstration complete!\n",
+ "\n",
+ "Next steps:\n",
+ "1. Apply learnings to your production data\n",
+ "2. Test with your actual query patterns\n",
+ "3. Monitor performance in your environment\n",
+ "4. Consider gradual rollout strategy\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(\"๐งน Cleaning up demonstration indices...\")\n",
+ "\n",
+ "# Clean up FLAT index\n",
+ "try:\n",
+ " flat_index.delete(drop=True)\n",
+ " print(\"โ
Deleted FLAT demonstration index\")\n",
+ "except Exception as e:\n",
+ " print(f\"โ ๏ธ Failed to delete FLAT index: {e}\")\n",
+ "\n",
+ "# Clean up SVS index\n",
+ "try:\n",
+ " svs_index.delete(drop=True)\n",
+ " print(\"โ
Deleted SVS-VAMANA demonstration index\")\n",
+ "except Exception as e:\n",
+ " print(f\"โ ๏ธ Failed to delete SVS index: {e}\")\n",
+ "\n",
+ "print(\n",
+ " \"\\n๐ Migration demonstration complete!\",\n",
+ " \"\\nNext steps:\",\n",
+ " \"1. Apply learnings to your production data\",\n",
+ " \"2. Test with your actual query patterns\",\n",
+ " \"3. Monitor performance in your environment\",\n",
+ " \"4. Consider gradual rollout strategy\",\n",
+ " sep=\"\\n\"\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.12.6"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}