Have you ever wondered how search engines like Google and Bing are able to provide you with the answers to your queries within seconds? Behind the scenes, there is a complex system of algorithms and artificial intelligence models that work together to give you the most relevant and accurate results. Microsoft’s latest search engine, new Bing, utilizes a proprietary AI model called Prometheus, which combines the capabilities of the Bing index, ranking, and answers with the reasoning capabilities of OpenAI’s GPT models. We’ll take a closer look at how this new technology works and what makes it unique.
What is Microsoft Prometheus?
Microsoft Prometheus is a first-of-its-kind AI model developed that uses a combination of Bing and GPT to generate a set of internal queries iteratively through a component called Bing Orchestrator. The model then provides an accurate and rich answer for the user query within the given conversation context, all within a matter of milliseconds. The rich of Prometheus is that it uses its reasoning skill over the data provided by Bing and hence it’s grounded by Bing data, via the Bing Orchestrator.
What is the History of Microsoft Prometheus?
Prometheus, the multi-dimensional data model, operational simplicity, scalable data collection, and powerful query language tool that has been making waves since its inception at SoundCloud in 2012.
When SoundCloud realized their existing metrics and monitoring solutions using StatsD and Graphite just weren’t cutting it, they decided to take matters into their own hands and create a tool that would meet all of their needs. And thus, Prometheus was born.
From the beginning, Prometheus was open-source, which allowed it to be picked up by other companies, including Boxever and Docker users. And with its inspired design taken from Google’s own monitoring tool Borgmon, Prometheus was destined for greatness.
By 2013, Prometheus was already being used for production monitoring at SoundCloud, and in 2015, it was finally announced to the public. And it wasn’t long before other companies, including DigitalOcean, Ericsson, CoreOS, Weaveworks, Red Hat, and Google, took notice and began using it as well.
And with the release of Prometheus 1.0 in July 2016, this tool only continued to grow in popularity. Additional updates were released throughout 2016 and 2017, leading up to the highly anticipated release of Prometheus 2.0 in November 2017.
It’s no wonder that the Cloud Native Computing Foundation accepted Prometheus as its second incubated project in May 2016, shortly after the success of Kubernetes. And in August 2018, they announced that the Prometheus project had graduated, cementing its position as one of the most essential tools for modern monitoring solutions.
How Does Prometheus Work?
Microsoft Prometheus works by selecting the relevant internal queries and leveraging the respective Bing search results, which is a critical component of the technology. It provides relevant and fresh information to the model, enabling it to answer recent questions and reducing inaccuracies. After selecting the queries, the model uses its reasoning capability to generate the most relevant answer within the conversation context. Finally, it attaches relevant Bing search answers such as weather, stock, sports, news, and so on, to the Chat answer. With the search results in mind, Prometheus is able to integrate citations into sentences in the Chat answer so that users can easily click to access those sources and verify the information.
What Makes Microsoft Prometheus Unique?
The special feature of Prometheus is that it combines the capabilities of Bing and GPT models to provide a rich and accurate answer to the user query. GPT models are known for their reasoning and creative capabilities, while Bing provides a comprehensive index, ranking, and answers results. By combining the strengths of both technologies, Prometheus is able to generate the most relevant and accurate answers within milliseconds.
Additionally, Microsoft has also introduced Azure Monitor managed service for Prometheus, which allows users to collect and analyze metrics at scale using a Prometheus-compatible monitoring solution, based on the Prometheus project from the Cloud Native Compute Foundation. This fully managed service enables users to use the Prometheus query language (PromQL) to analyze and alert on the performance of monitored infrastructure.
The Challenges of Creating the Ideal Bing Search Product
Jordi Ribas, Corporate Vice President of Search & AI at Microsoft, has expressed in the blog post that besides Prometheus, his team faced challenges in creating an ideal Bing search product. In the end, the team developed a new Bing UX that has a unified Search and Chat in a single interface because some queries would perform better in the classical or Search mode, while others would do better in a conversational or Chat mode. This new UX is designed to provide a seamless and intuitive experience for users.
How is Microsoft Prometheus different from Chat GPT?
Microsoft Prometheus is a customized version of Chat GPT, which has been fine-tuned for the Bing search engine. It has been trained on a large dataset of search queries and web pages to better understand user intent and provide more accurate search results.
What is the role of Microsoft Prometheus in Bing Chat?
Microsoft Prometheus powers the chat feature in Bing, allowing users to interact with the search engine using natural language. It enables the search engine to understand user intent and provide more personalized and relevant search results.
Benefits of Microsoft’s New Bing Search Engine
The new Bing search engine has several benefits for users, including:
- Accurate and rich answers within milliseconds
- Combines the capabilities of Bing and GPT models to provide the most relevant and accurate results
- Integrates Bing search results and citations into the Chat answer for easy verification
- Unified Search and Chat UX for a seamless and intuitive experience
What is Azure Monitor Managed Service for Prometheus?
Azure Monitor Managed Service for Prometheus is a fully managed service that allows users to collect, analyze, and alert on metrics at scale using a Prometheus-compatible monitoring solution. It automates complex tasks such as scaling, high-availability, and long-term data retention.
What is the role of Azure Monitor Managed Service for Prometheus in Azure Monitor?
Azure Monitor Managed Service for Prometheus is a part of Azure Monitor, which is Microsoft’s integrated platform for monitoring and managing Azure resources and applications. It provides users with a rich set of enterprise-ready capabilities to ensure complete observability of their hybrid environment.
What are the benefits of using Azure Monitor Managed Service for Prometheus?
Azure Monitor Managed Service for Prometheus delivers the best of what you like about the open-source ecosystem while automating complex tasks such as scaling, high-availability, and long-term data retention. It enables users to collect, analyze, and alert on metrics at scale using the Prometheus query language (PromQL).
Is Azure Monitor Managed Service for Prometheus publicly available?
Yes, Azure Monitor Managed Service for Prometheus is publicly available in public preview. It can be used as a standalone service from Azure Monitor or as an integrated component of Container Insights. Users need to have self-managed Prometheus running on their AKS cluster to use this service.
Microsoft’s new Bing search engine, powered by the Prometheus AI model, is a significant advancement in search technology. By combining the capabilities of Bing and GPT models, users can expect more accurate and relevant answers within seconds. The integration of Bing search results and citations into the Chat answer also provides an easy way to verify information.