OpenSearch Vector Engine is now disk-optimized for low value, correct vector search

OpenSearch Vector Engine can now run vector search at a 3rd of the associated fee on OpenSearch 2.17+ domains. Now you can configure k-NN (vector) indexes to run on disk mode, optimizing it for memory-constrained environments, and allow low-cost, correct vector search that responds in low tons of of milliseconds. Disk mode gives a cheap various to reminiscence mode if you don’t want close to single-digit latency.

On this put up, you’ll find out about the advantages of this new characteristic, the underlying mechanics, buyer success tales, and getting began.

Overview of vector search and the OpenSearch Vector Engine

Vector search is a way that improves search high quality by enabling similarity matching on content material that has been encoded by machine studying (ML) fashions into vectors (numerical encodings). It permits use circumstances like semantic search, permitting you to think about context and intent together with key phrases to ship extra related searches.

OpenSearch Vector Engine permits real-time vector searches past billions of vectors by creating indexes on vectorized content material. You’ll be able to then run searches for the highest Okay paperwork in an index which are most much like a given question vector, which might be a query, key phrase, or content material (comparable to a picture, audio clip, or textual content) that has been encoded by the identical ML mannequin.

Tuning the OpenSearch Vector Engine

Search purposes have various necessities when it comes to pace, high quality, and price. As an illustration, ecommerce catalogs require the bottom doable response instances and high-quality search to ship a optimistic procuring expertise. Nevertheless, optimizing for search high quality and efficiency beneficial properties usually incurs value within the type of extra reminiscence and compute.

The fitting steadiness of pace, high quality, and price relies on your use circumstances and buyer expectations. OpenSearch Vector Engine gives complete tuning choices so you can also make good trade-offs to attain optimum outcomes tailor-made to your distinctive necessities.

You should utilize the next tuning controls:

• Algorithms and parameters – This consists of the next:
  • Hierarchical Navigable Small World (HNSW) algorithm and parameters like ef_search, ef_construct, and m
  • Inverted File Index (IVF) algorithm and parameters like nlist and nprobes
  • Precise k-nearest neighbors (k-NN), also referred to as brute-force k-NN (BFKNN) algorithm
• Engines – Fb AI Similarity Search (FAISS), Lucene, and Non-metric House Library (NMSLIB).
• Compression methods – Scalar (comparable to byte and half precision), binary, and product quantization
• Similarity (distance) metrics – Inside product, cosine, L1, L2, and hamming
• Vector embedding varieties – Dense and sparse with variable dimensionality
• Rating and scoring strategies – Vector, hybrid (mixture of vector and Finest Match 25 (BM25) scores), and multi-stage rating (comparable to cross-encoders and personalizers)

You’ll be able to regulate a mix of tuning controls to attain a various steadiness of pace, high quality, and price that’s optimized to your wants. The next diagram gives a tough efficiency profiling for pattern configurations.

Tuning for disk-optimization

With OpenSearch 2.17+, you possibly can configure your k-NN indexes to run on disk mode for high-quality, low-cost vector search by buying and selling in-memory efficiency for larger latency. In case your use case is glad with ninetieth percentile (P90) latency within the vary of 100–200 milliseconds, disk mode is a wonderful possibility so that you can obtain value financial savings whereas sustaining excessive search high quality. The next diagram illustrates disk mode’s efficiency profile amongst various engine configurations.

Disk mode was designed to expire of the field, lowering your reminiscence necessities by 97% in comparison with reminiscence mode whereas offering excessive search high quality. Nevertheless, you possibly can tune compression and sampling charges to regulate for pace, high quality, and price.

The next desk presents efficiency benchmarks for disk mode’s default settings. OpenSearch Benchmark (OSB) was used to run the primary three assessments, and VectorDBBench (VDBB) was used for the final two. Efficiency tuning finest practices had been utilized to attain optimum outcomes. The low scale assessments (Tasb-1M and Marco-1M) had been run on a single r7gd.massive knowledge node with one duplicate. The opposite assessments had been run on two r7gd.2xlarge knowledge nodes with one duplicate. The % value discount metric is calculated by evaluating an equal, right-sized in-memory deployment with the default settings.

These assessments are designed to reveal that disk mode can ship excessive search high quality with 32 instances compression throughout quite a lot of datasets and fashions whereas sustaining our goal latency (below P90 200 milliseconds). These benchmarks aren’t designed for evaluating ML fashions. A mannequin’s influence on search high quality varies with a number of components, together with the dataset.

Disk mode’s optimizations below the hood

While you configure a k-NN index to run on disk mode, OpenSearch mechanically applies a quantization approach, compressing vectors as they’re loaded to construct a compressed index. By default, disk mode converts every full-precision vector—a sequence of tons of to hundreds of dimensions, every saved as 32-bit numbers—into binary vectors, which symbolize every dimension as a single-bit. This conversion ends in a 32 instances compression fee, enabling the engine to construct an index that’s 97% smaller than one composed of full-precision vectors. A right-sized cluster will maintain this compressed index in reminiscence.

Compression lowers value by lowering the reminiscence required by the vector engine, nevertheless it sacrifices accuracy in return. Disk mode recovers accuracy, and subsequently search high quality, utilizing a two-step search course of. The primary section of the question execution begins by effectively traversing the compressed index in reminiscence for candidate matches. The second section makes use of these candidates to oversample corresponding full-precision vectors. These full-precision vectors are saved on disk in a format designed to scale back I/O and optimize disk retrieval pace and effectivity. The pattern of full-precision vectors is then used to reinforce and re-score matches from section one (utilizing precise k-NN), thereby recovering the search high quality loss attributed to compression. Disk mode’s larger latency relative to reminiscence mode is attributed to this re-scoring course of, which requires disk entry and extra computation.

Early buyer successes

Prospects are already working the vector engine in disk mode. On this part, we share testimonials from early adopters.

Asana is bettering search high quality for patrons on their work administration platform by phasing in semantic search capabilities via OpenSearch’s vector engine. They initially optimized the deployment through the use of product quantization to compress indexes by 16 instances. By switching over to the disk-optimized configurations, they had been capable of doubtlessly scale back value by one other 33% whereas sustaining their search high quality and latency targets. These economics make it viable for Asana to scale to billions of vectors and democratize semantic search all through their platform.

DevRev bridges the elemental hole in software program firms by immediately connecting customer-facing groups with builders. As an AI-centered platform, it creates direct pathways from buyer suggestions to product improvement, serving to over 1,000 firms speed up progress with correct search, quick analytics, and customizable workflows. Constructed on massive language fashions (LLMs) and Retrieval Augmented Era (RAG) flows working on OpenSearch’s vector engine, DevRev permits clever conversational experiences.

“With OpenSearch’s disk-optimized vector engine, we achieved our search high quality and latency targets with 16x compression. OpenSearch affords scalable economics for our multi-billion vector search journey.”

– Anshu Avinash, Head of AI and Search at DevRev.

Get began with disk mode on the OpenSearch Vector Engine

First, you must decide the sources required to host your index. Begin by estimating the reminiscence required to help your disk-optimized k-NN index (with the default 32 instances compression fee) utilizing the next components:

Required reminiscence (bytes) = 1.1 x ((vector dimension rely)/8 + 8 x m) x (vector rely)

As an illustration, for those who use the defaults for Amazon Titan Textual content V2, your vector dimension rely is 1024. Disk mode makes use of the HNSW algorithm to construct indexes, so “m” is without doubt one of the algorithm parameters, and it defaults to 16. When you construct an index for a 1-billion vector corpus encoded by Amazon Titan Textual content, your reminiscence necessities are 282 GB.

When you have a throughput-heavy workload, you must be sure that your area has enough IOPs and CPUs as nicely. When you observe deployment finest practices, you should utilize occasion retailer and storage efficiency optimized occasion varieties, which is able to usually give you enough IOPs. You need to all the time carry out load testing for high-throughput workloads, and regulate the unique estimates to accommodate for larger IOPs and CPU necessities.

Now you possibly can deploy an OpenSearch 2.17+ area that has been right-sized to your wants. Create your k-NN index with the mode parameter set to on_disk, after which ingest your knowledge. If you have already got a k-NN index working on the default in_memory mode, you possibly can convert it by switching the mode to on_disk adopted by a reindex job. After the index is rebuilt, you possibly can downsize your area accordingly.

Conclusion

On this put up, we mentioned how one can profit from working the OpenSearch Vector Engine on disk mode, shared buyer success tales, and supplied you recommendations on getting began. You’re now set to run the OpenSearch Vector Engine at as little as a 3rd of the associated fee.

To be taught extra, seek advice from the documentation.

In regards to the Authors

Dylan Tong is a Senior Product Supervisor at Amazon Net Companies. He leads the product initiatives for AI and machine studying (ML) on OpenSearch together with OpenSearch’s vector database capabilities. Dylan has a long time of expertise working immediately with prospects and creating merchandise and options within the database, analytics and AI/ML area. Dylan holds a BSc and MEng diploma in Pc Science from Cornell College.

Vamshi Vijay Nakkirtha is a software program engineering supervisor engaged on the OpenSearch Venture and Amazon OpenSearch Service. His main pursuits embody distributed techniques.