To satisfy these financial calls for, the Net 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, Net IQ buildings the knowledge retrieved from the underlying search engine information, delivering what Microsoft calls “structured proof objects” in addition to passage-level info from unstructured textual content paperwork. This could end in 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 Net IQ in your agent code
The API for Net IQ is an ordinary REST call, delivering a request object to the Net IQ endpoint. Alongside along 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 dimension of the responses and the format used. Responses could be returned in textual content, HTML, or markdown codecs, in addition to extracted passages which might be chosen for context. All different choices return the complete doc, so could be dearer to make use of. Markdown is an fascinating different, as it may be used as the premise for giving brokers semantic reminiscences.
Outcomes embody necessary contextual and quotation info, together with net web page titles and URLs, in addition to information 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 manner as Bing’s Copilot shows context within the type of footnotes in its responses.
