Mark Mirchandani is joined again by Priyanka Vergadia this week for an ML-filled interview with Radu Miclaus of Lucidworks. Lucidworks, a company specializing in information retrieval, strives to make data searching easier for developers and users. Building off Solr, Lucidworks created Fusion, an environment more conducive to easy AI-enhanced query capabilities, better scalability, and more. With Fusion, developers can take advantage of the highly advanced relevance tuning tools such as query rewrites, which analyze user behavior and automatically rewrite queries based on that information.

On the tech side, Fusion was built with a combination of Java, Kubernetes to increase scalability, Solr management tools, and logging and reporting tools. The engineers at Lucidworks have created Fusion-specific system-enhancing pieces as well, including a machine learning service that allows data scientists to train their models elsewhere and plug them in for a completely customized experience. The team also created Smart Answers, which is a Q-And-A system built on a search engine that can connect to chatbots, virtual assistants, and others. Radu goes into detail explaining the Smart Answers system and how the layers of the project work together. We also learn about the customization capabilities and integration of Smart Answers.

Radu wraps up the show with interesting use-case stories and how Fusion is working in the real world. In the future, Lucidworks will be available right in the GCP marketplace!

Radu Miclaus

Radu has over 12 years of experience in the data science space with applications in general machine learning architecture, search, customer analytics, risk and financial analysis. At Lucidworks, Radu focuses on low-code AI for search developers, pluggable machine learning for data scientists, and cloud managed services that offload the burden of operating search applications.

Cool things of the week

• Week 2 sessions on productivity and collaboration site
• Online shopping gets more personal with Recommendations AI blog
• Using new traffic control features in External HTTP(S) load balancer blog
• Optimizing your costs on Compute Engine video
• Google Cloud Talks by DevRel site
• Giving you better cost analytics capabilities—and a simpler invoice blog
• GCP Podcast Episode 217: Cost Optimization with Justin Lerma and Pathik Sharma podcast

Interview

• Lucidworks site
• Solr site
• Lucene site
• Fusion site
• Try Fusion site
• Smart Answers site
• Spark site
• Kubernetes site
• GKE site
• Dialogflow site
• Webinar: Smart Answers for Employee and Customer Support After COVID-19 site
• Deconstructing Chatbots video
• GCP Podcast Episode 227: Pandium with Cristina Flaschen and Kelly Sarabyn podcast
• GCP Podcast Episode 188: Conversation AI with Priyanka Vergadia podcast
• GCP Podcast Episode 195: Conversational AI Best Practices with Cathy Pearl and Jessica Dene Earley-Cha podcast

Tip of the week

We’re talking to Dale Markowitz about Prototyping Machine Learning projects.

You can also hear more from Dale in GCP Podcast Episode 214: AI in Healthcare with Dale Markowitz and GCP Podcast Episode 194: ML with Dale Markowitz.

What’s something cool you’re working on?

Priyanka has been working on GCP Comics and Sketchnote.