Returned in the webPages.value key (an array of results) in the official API, our API returns the equivalent in the top level organic_results key (an array of results). Next we're going to authenticate via the api_key query parameter and remove the headers entirely as they're not necessary for any calls to our endpoint. The search page will also list the sources that the AI-generated text was created from below the answer, and will even present traditional search results in a sidebar on the right for those who are uninterested in Bing's curated AI experience. Microsoft has announced a major update to Bing Search that overhauls the search results page with AI at the heart of its experience.
Comparisons with Google AI Overviews
The system accesses additional documents to provide more accurate and up-to-date information, supplement, or verify information in the LLM’s training data. BGS leverages the underlying LLMs’ training data as well as Bing’s own search index. This can be good news for website owners if the query is competitive. If you’ve been following research into Google AIOs, this should sound familiar. On average, BGS summaries linked to 6.6 URLs ranging from 4 on the low end to 12 on the high end. To view the original source information, use the ‘Sources’ links.”
- 28.3% of URLs were found to not rank in the top 20 results for the query.
- This design reduces visual clutter, enhancing user experience by making the summary more visually accessible.
- Leveraging both Large Language Models (LLMs) and Small Language Models (SLMs) marks a significant milestone in enhancing our search capabilities.
- This aspect of personalization in search results could customize the information to more closely address user needs.
- The Bing search URL found at images.webSearchUrl in the official API can be found at inline_images.see_more_link in ours.
- With the explosion of e-commerce and online search activity, every new product leaves a digital footprint, from Google Shopping listings and reviews to news mentions.
Other Microsoft links
While the BGS has visible search results next to the summary on desktop, on mobile the results are located below the summary. This has a significant impact on the visibility of organic search results. AI summaries for both Google and Bing take up a significant amount of space on the search results page. While BGS features a document index and search results surrounding its summary on the left and right, the AIO opts for a minimalist approach with white space surrounding the summary.
Learn how to connect search, AI, and PPC into one unstoppable strategy. While we’ll have to wait and see the full impact, Bing’s move sets the stage for a new chapter in search. “… our product is built on the foundation of providing the best results, and we will not compromise on quality for speed.
Why Bing’s Move to LLM/SLM Models Matters
Overall, it's hard to see why this is better than a regular search engine with AI at the top of every search result. Copilot's current AI in search is much cleaner and shows the sites from which the information came directly under the result. This change follows the earlier addition of AI search summaries through Microsoft's Copilot technology. Returned in the relatedSearches.value key (array of related searches) in the official API, our API returns the equivalent in the top level related_searches key (array of related searches).
It states “This summary wan generated using AI based on multiple online sources. In BGS, you have to select the information icon to see any type of warning to the searcher. You do not have to be signed in to Bing for the AI summary to appear. This provides more specificity and transparency regarding how the information in the summary is verified. A key distinction here is that Google uses text fragments in URLs to highlight relevant excerpts directly on the sourced document page, enhancing the specificity and transparency of the citations. To see the links, you have to select the arrow under each section.
- Due to the sheer number of different possible response objects available, I’m only going to cover a few of them directly in this blog post.
- The Bing search URL that would be found under webPages.webSearchUrl in the official API can be found under search_metadata.bing_url in our API.
- What insights can we gain about influencing Bing Generative Search (BGS) to display specific URLs in its summaries?
- There is a a significant difference between how organic results are presented in Microsoft Edge and other browsers.
- Currently, BGS only activates for a small number of queries.
- TensorRT-LLM is a tool that helps reduce the time and cost of running large models on NVIDIA GPUs.
Link Diversity in Bing Generative Search
Instead of showing a list of blue links you usually see in search engines, it gives AI-generated summaries of answers. The Copilot Search mode will show a summary of what the user is searching for right on the page, including links to sources as well as to image and video searches. The images.readLink attribute in the official API which provides the URL for the equivalent API image search can be found at inline_images.serpapi_link in our API.
Moreover, Bing has taken a much stronger stance than Google in providing visibility to organic results and transparency in sourcing summary content. It seems that the system either seeks out documents responsive to related queries or documents with text that verifies the statements in the summary. Several studies from Advanced Web Ranking, SE Ranking, and Authoritas found that AIO summaries included a significant number of links that were low or unranked for that query. The fact that the summaries can include documents that don’t rank for the query provides some important clues as to how the system might work. Bing has provided several examples of its generative search experience which help provide some first insights into the linked sources.
Bing aims to do that using smaller language models and advanced optimization techniques. As users ask more complex questions, search engines need to better understand and deliver relevant results quickly. Bing’s switch to LLM/SLM models and TensorRT optimization could impact the future of search. This is where TensorRT-LLM comes into play, reducing model inference time and, consequently, the end-to-end experience latency without sacrificing result quality.” This update aims to gtbet casino login improve performance and reduce costs in search result delivery.
Today, we are releasing an open-source Model Context Protocol (MCP) server that exposes our web search API to AI agents and developers through a familiar and common interface. It's also worth taking a look at our Bing Playground and performing a few searches to see it all in action. The Bing search URL found at images.webSearchUrl in the official API can be found at inline_images.see_more_link in ours. Returned in the images.value key (array of images) in the official API, our API returns the equivalent in the inline_images.items key (array of images). The date attribute in our API will return the date displayed in the result, though it can be in the form of a formatted date (e.g. Oct 29, 2020) or a relative date (e.g. 3 days ago).
When building summaries, the system evaluates documents responsive to the query but, if the top results are repetitive, it will explore documents responsive to related queries as well. Overall, Bing’s experience provides more (albeit mixed) visibility to the organic search results, which potentially helps lessen the impact of the summaries on clicks. When you enter a query in Bing, if the query is identified for an AI-enhanced search result, you will receive a BGS summary. In Google AIOs, the summary pushes the organic search results further down the page for both mobile and desktop. Bing Generative Search (BGS) is an AI-enhanced search result page that uses traditional search results, large language models (LLMs), and small language models. Microsoft enhances Bing search with new language models, claiming to reduce costs while delivering faster, more accurate results.