Implementations are described herein for augmenting a traditional search session with stateful chat—via what will be referred to as a “generative companion”—to facilitate more interactive searching. In various implementations, a query may be received, e.g., from a client device operated by a user. Contextual information associated with the user or the client device may be retrieved. Generative model (GM) output may be generated based on processing, using a generative model, data indicative of the query and the contextual information.

At least utilizing a custom corpus of documents to condition a large language model (LLM) when generating a response to a user query. In some implementations, a user query associated with a client device is received. An API query for an external application is generated by an LLM based on the user query.

A machine-learned system for modeling contextual data such as long user historical data is provided. The system includes a machine-learned embedding model and a machine-learned sequence processing model.

Google Patent

An example method for prompt-based query generation is provided. The method includes receiving, by a computing device, at least two prompts associated with a retrieval task to be performed on a corpus of documents associated with the task. The method includes applying, based on the at least two prompts and the corpus of documents, a large language model to generate a synthetic training dataset comprising a plurality of query-document pairs, wherein each query-document pair comprises a synthetically generated query and a document from the corpus of documents.

Un nouveau brevet chez Google pour ajouter des critères de considération concernant les prochaines pages qui pourraient intéresser l'internaute en se basant sur sa page actuelle et la précédente