To satisfy these financial calls for, the Internet IQ platform doesn’t ship complete paperwork to querying brokers. Complete paperwork can result in costly inference additional down the chain, as LLMs course of outcomes repeatedly to drive the agent workflow. As an alternative, Internet IQ buildings the data retrieved from the underlying search engine knowledge, delivering what Microsoft calls “structured proof objects” in addition to passage-level info from unstructured textual content paperwork. This could lead to a a lot greater signal-to-noise ratio than merely querying a search engine, with a deal with delivering info that lets brokers work utilizing fewer tokens.
Utilizing Internet IQ in your agent code
The API for Internet IQ is a regular REST call, delivering a request object to the Internet IQ endpoint. Alongside together with your API authorization key, you’ll ship a question, a set of parameters that management the variety of outcomes returned, the language and area used, and the utmost measurement of the responses and the format used. Responses might be returned in textual content, HTML, or markdown codecs, in addition to extracted passages which can be chosen for context. All different choices return the total doc, so might be costlier to make use of. Markdown is an attention-grabbing different, as it may be used as the premise for giving brokers semantic recollections.
Outcomes embrace essential contextual and quotation info, together with internet web page titles and URLs, in addition to knowledge about when the positioning was final crawled and the way stale the underlying info is. This can be utilized to enhance grounding and supply extra info that may be included in formatted responses — a lot in the identical approach as Bing’s Copilot shows context within the type of footnotes in its responses.
