Many machine learning (ML) use cases, like fraud detection, ad targeting, and recommendation engines, require near real-time predictions. The performance of these predictions is heavily dependent on access to the most up-to-date data, with delays of even a few seconds making all the difference. But it’s difficult to set up the infrastructure needed to support high-throughput updates and low-latency retrieval of data.

Starting this month, Vertex AI Matching Engine and Feature Store will support real-time Streaming Ingestion as Preview features. With Streaming Ingestion for Matching Engine, a fully managed vector database for vector similarity search, items in an index are updated continuously and reflected in similarity search results immediately. With Streaming Ingestion for Feature Store, you can retrieve the latest feature values with low latency for highly accurate predictions, and extract real-time datasets for training.

For example, Digits is taking advantage of Vertex AI Matching Engine Streaming Ingestion to help power their product, Boost, a tool that saves accountants time by automating manual quality control work.“Vertex AI Matching Engine Streaming Ingestion has been key to Digits Boost being able to deliver features and analysis in real-time. Before Matching Engine, transactions were classified on a 24 hour batch schedule, but now with Matching Engine Streaming Ingestion, we can perform near real time incremental indexing – activities like inserting, updating or deleting embeddings on an existing index, which helped us speed up the process. Now feedback to customers is immediate, and we can handle more transactions, more quickly,” said Hannes Hapke, Machine Learning Engineer at Digits.

This blog post covers how these new features can improve predictions and enable near real-time use cases, such as recommendations, content personalization, and cybersecurity monitoring.

Streaming Ingestion enables real-time AI

As organizations recognize the potential business impact of better predictions based on up-to-date data, more real-time AI use cases are being implemented. Here are some examples:

• Real-time recommendations and a real-time marketplace: By adding Streaming Ingestion to their existing Matching Engine-based product recommendations, Mercari is creating a real-time marketplace where users can browse products based on their specific interests, and where results are updated instantly when sellers add new products. Once it’s fully implemented, the experience will be like visiting an early-morning farmer’s market, with fresh food being brought in as you shop. By combining Streaming Ingestion with Matching Engine’s filtering capability, Mercari can specify whether or not an item should be included in the search results, based on tags such as “online/offline” or “instock/nostock.”

• Large-scale personalized content streaming: For any stream of content representable with feature vectors (including text, images, or documents), you can design pub-sub channels to pick up valuable content for each subscriber’s specific interests. Because Matching Engine is scalable (i.e., it can process millions of queries each second), you can support millions of online subscribers for content streaming, serving a wide variety of topics that are changing dynamically. With Matching Engine’s filtering capability, you also have real-time control over what content should be included, by assigning tags such as “explicit” or “spam” to each object. You can use Feature Store as a central repository for storing and serving the feature vectors of the contents in near real time.

• Monitoring: Content streaming can also be used for monitoring events or signals from IT infrastructure, IoT devices, manufacturing production lines, and security systems, among other commercial use cases. For example, you can extract signals from millions of sensors and devices and represent them as feature vectors. Matching Engine can be used to continuously update a list of “the top 100 devices with possible defective signals,” or “top 100 sensor events with outliers,” all in near real time.

• Threat/spam detection: If you are monitoring signals from security threat signatures or spam activity patterns, you can use Matching Engine to instantly identify possible attacks from millions of monitoring points. In contrast, security threat identification based on batch processing often involves potentially significant lag, leaving the company vulnerable. With real-time data, your models are better able to catch threats or spams as they happen in your enterprise network, web services, online games, etc.

Implementing streaming use cases

Let’s take a closer look at how you can implement some of these use cases.

Real-time recommendations for retail

Mercari built a feature extraction pipeline with Streaming Ingestion.

The feature extraction pipeline is defined with Vertex AI Pipelines, and is periodically invoked by Cloud Scheduler and Cloud Functions to initiate the following process:

1. Get item data: The pipeline issues a query to fetch the updated item data from BigQuery.
2. Extract feature vector: The pipeline runs predictions on the data with the word2vec model to extract feature vectors.
3. Update index: The pipeline calls Matching Engine APIs to add the feature vectors to the vector index. The vectors are also saved to Cloud Bigtable (and can be replaced with Feature Store in the future).

“We have been evaluating the Matching Engine Streaming Ingestion and couldn’t believe the super short latency of the index update for the first time. We would like to introduce the functionality to our production service as soon as it becomes GA, ” said Nogami Wakana, Software Engineer at Souzoh (a Mercari group company).

This architecture design can be also applied to any retail businesses that need real-time updates for product recommendations.

Ad targeting

Ad recommender systems benefit significantly from real-time features and item matching with the most up-to-date information. Let’s see how Vertex AI can help build a real-time ad targeting system.

The first step is generating a set of candidates from the ad corpus. This is challenging because you must generate relevant candidates in milliseconds and ensure they are up to date. Here you can use Vertex AI Matching Engine to perform low-latency vector similarity matching, generate suitable candidates, and use Streaming Ingestion to ensure that your index is up-to-date with the latest ads.

Next is reranking the candidate selection using a machine learning model to ensure that you have a relevant order of ad candidates. For the model to use the latest data, you can use Feature Store Streaming Ingestion to import the latest features and use online serving to serve feature values at low latency to improve accuracy.

After reranking the ads candidates, you can apply final optimizations, such as applying the latest business logic. You can implement the optimization step using a Cloud Function or Cloud Run.

What’s Next?

Interested? The documents for Streaming Ingestion are available and you can try it out now. Using the new feature is easy: For example, when you create an index on Matching Engine with the REST API, you can specify the indexUpdateMethod attribute as STREAM_UPDATE.

{
    displayName: "'${DISPLAY_NAME}'", 
    description: "'${DISPLAY_NAME}'",
    metadata: {
       contentsDeltaUri: "'${INPUT_GCS_DIR}'", 
       config: {
          dimensions: "'${DIMENSIONS}'",
          approximateNeighborsCount: 150,
          distanceMeasureType: "DOT_PRODUCT_DISTANCE",
          algorithmConfig: {treeAhConfig: {leafNodeEmbeddingCount: 10000, leafNodesToSearchPercent: 20}}
       },
    },
    indexUpdateMethod: "STREAM_UPDATE"
}

After deploying the index, you can update or rebuild the index (feature vectors) with the following format. If the data point ID exists in the index, the data point is updated, otherwise, a new data point is inserted.

{
    
datapoints: [
        
{datapoint_id: "'${DATAPOINT_ID_1}'", feature_vector: [...]}, 
        {datapoint_id: "'${DATAPOINT_ID_2}'", feature_vector: [...]}
    
]
}

It can handle the data point insertion/update at high throughput with low latency. The new data point values will be applied in any new queries within a few seconds or milliseconds (the latency varies depending on the various conditions).

The Streaming Ingestion is a powerful functionality and very easy to use. No need to build and operate your own streaming data pipeline for real-time indexing and storage. Yet, it adds significant value to your business with its real-time responsiveness.

To learn more, take a look at the following blog posts for learning Matching Engine and Feature Store concepts and use cases:

• Vertex Matching Engine: Blazing fast and massively scalable nearest neighbor search
• Find anything blazingly fast with Google’s vector search technology
• Kickstart your organization’s ML application development flywheel with the Vertex Feature Store
• Meet AI’s multitool: Vector embeddings

This week, the Vera C. Rubin Observatory is launching the first preview of its new Rubin Science Platform (RSP) for an initial cohort of astronomers. The observatory, which is located in Chile but managed by the U.S. National Science Foundation’s NOIRLab in Tucson, AZ and SLAC in California, is jointly funded by the NSF and the U.S. Department of Energy. The platform provides an easy-to-use interface to store and analyze the massive datasets of the Legacy Survey of Space and Time (LSST), which will survey a third of the sky each night for ten years, detecting billions of stars and galaxies, and millions of supernovae, variable stars, and small bodies in our Solar System.

The LSST datasets are unprecedented in size and complexity, and will be far too large for scientists to download to their personal computers for analysis. Instead, scientists will use the RSP to process, query, visualize, and analyze the LSST data archives through a mixture of web portal, notebook, and other virtual data analysis services. An initial launch with simulated data, called Data Preview 0, builds on the Rubin Observatory’s three-year partnership with Google to develop an Interim Data Facility (IDF) on Google Cloud to prototype hosting of the massive LSST dataset. This agreement marks the first time a cloud-based data facility has been used for an astronomy application of this magnitude.

Bringing the stars to the cloud

For Data Preview 0, the IDF leverages Cloud Storage, Google Kubernetes Engine (GKE), and Compute Engine to provide the Rubin Observatory user community access to simulated LSST data in an early version of the RSP. The simulated data were developed over several years by the LSST Dark Energy Science Collaboration to imitate five years of an LSST-like survey over 300 square degrees of the sky (about 1,500 times the area of the moon). The resulting images are very realistic: they have the same instrumental characteristics, such as pixel size and sensitivity to photons, that are expected from the Rubin Observatory’s LSST Camera, and they were processed with an early version of the LSST Science Pipelines that will eventually be used to process LSST data. “This will be the first time that these workloads have ever been hosted in a cloud environment. Researchers will have an opportunity to explore an early version of this platform,” says Ranpal Gill, senior manager and head of communications at the Rubin Observatory.

Broadening access for more researchers

Over 200 scientists and students with Rubin Observatory data rights were selected to participate in Data Preview 0 from a pool of applicants that represents a wide range of demographic criteria, regions, and experience level. Participants will be supported with resources such as tutorials, seminars, communication channels, and networking opportunities—and they will be free to pursue their own science at their own pace using the data in the RSP. 

“The revolutionary nature of the future LSST dataset requires a commensurately innovative system for data access and analysis paired with robust support for scientists,” says Melissa Graham, lead community scientist for the Rubin Observatory and research scientist in the astronomy department at the University of Washington. “I’m personally excited to enhance my own skills by using the RSP’s tools for big data analysis, while also helping others to learn and to pursue their LSST-related science goals during Data Preview 0.” 

At the same time, the fact that the RSP is hosted in the cloud provides researchers at smaller institutions access to state-of-the-art astronomy infrastructure that is comparable to that of the largest national research centers.

The launch benefits the observatory too: the development team can learn what researchers are interested in while also testing and debugging the platform. Graham says that “the platform is still in active development so researchers using it will be able to follow along in the progress, and provide feedback on ways that we can optimize the development of the tools.”

Next steps

The LSST aims to begin the ten-year survey in 2023-24 and expects it to include 500 petabytes of data. Through the cloud, Google aims to help make this extraordinary project scalable and accessible to researchers everywhere. To learn more about Data Preview 0, watch this video.

Want to ramp up your own research in the cloud? We offer research credits to academics using Google Cloud for qualifying projects in eligible countries. You can find our application form on Google Cloud’s website or contact our sales team.