"To ground its Gemini models, Google uses a proprietary technology called FastSearch. FastSearch is based on RankEmbed signals - a set of search ranking signals-and generates abbreviated, ranked web results that a model can use to produce a grounded response. FastSearch delivers results more quickly than Search because it retrieves fewer documents, but the resulting quality is lower than Search's fully ranked web results."
"Google does not make FastSearch directly available to third parties through an API. Rather, the technology is integrated into a Google Cloud offering called Vertex AI, which is available to third parties to ground on Google Search results or other data sources. Vertex customers do not, however, receive the FastSearch-ranked web results themselves, only the information from those results. Google limits Vertex in this manner to protect its intellectual property."
FastSearch is a proprietary Google retrieval technology used to ground Gemini models by providing abbreviated, ranked web results. FastSearch uses RankEmbed signals, retrieves fewer documents, and therefore returns results faster than standard Google Search but with lower quality. The technology is integrated into Google Cloud's Vertex AI for grounding on Google Search results or other data sources. Vertex AI customers receive information derived from FastSearch results rather than the FastSearch-ranked web results themselves. Google limits direct access to FastSearch to protect its intellectual property.
Read at Search Engine Roundtable
Unable to calculate read time
Collection
[
|
...
]