Palantir Technologies

Computer-implemented systems and methods including language models for providing an application-aware model-based assistant. A computer-implemented method, for communicating with a front end device to generate application specific recommended actions, may include: determining lists of available global and application actions; receiving a user query; generating a first prompt for a language model and providing a first response for display to the user; generating a second prompt for a language model; and in response to receiving an output: parsing the output to generate a list of recommended actions, and providing a second response for display to the user, where the second response includes the third list of recommended actions.

A method performed by one or more processors comprises displaying code, receiving user selection of a portion of code, determining one or more settable data items, generating a template, displaying the template, receiving a user input value for the settable data items by the template, and executing the code with each of the settable data items set to the received user input value. A data processing pipeline is configured to pass a data item to a first transformer to provide first transformed data, store the first transformed data in a temporary memory, write the first transformed data to the data storage system, and pass the transformed data from the temporary memory to a second transformer.

An artificial intelligence system (AIS) can improve relevance of LLM responses through selection of appropriate examples to provide in an enhanced user prompt. The system may receive user inputs indicating a task to be performed by the LLM, determine a set of examples based at least on an initial user prompt and to potentially include in an enhanced user prompt, and determine which examples in the set of examples are ideal to include in the enhanced user prompt to increase the usefulness of the LLM response. The AIS can generate an enhanced prompt for the LLM based on the user input and identified ideal examples. The enhanced prompt can include at least a portion of the initial user input and each of the identified ideal examples.

An artificial intelligence system (AIS) can generate documentation documents describing a user's workflow through capturing meaningful and event-based workflow information to provide in an LLM prompt. The system may receive user inputs indicating start of a workflow capture session, monitor a user's use of a software application for selective, meaningful triggers, generate screen captures based on detected triggers and determine associated metadata. The system may record audio. The system may receive user inputs indicating stop of a workflow capture session, transcribe recorded audio to generate a transcript, and may associate text of the transcript with the generated screen captures based on determined metadata. The AIS can generate a prompt for the LLM based on at least some of the meaningful workflow information. The prompt can include at least some of the generated screen captures and associated metadata, some of the transcript, and instructions to generate a documentation document.

Systems and methods for image matching are provided. An example method includes receiving an incoming image of a first imaging modality; receiving a reference image of a second imaging modality, the second imaging modality being different from the first imaging modality; generating a reference view of the reference image based on one or more priors associated with the incoming image; detecting a plurality of features corresponding to a plurality of feature points in the incoming image using a first algorithm that generates relatively even distribution of the plurality of feature points; generating a plurality of feature descriptors corresponding to the plurality of features, at least one of the plurality of feature descriptors being associated with at least one of a plurality of orientation bins.

In some examples, systems and methods for mixed reality are provided. For example, a method includes: generating a three-dimensional image based on target area data from one or more first data sources; receiving object data associated with one or more digital objects from one or more second data sources; generating an object representation including a representation of at least one of the one or more digital objects based on the object data associated with one or more digital objects; overlaying the object representation on the three-dimensional image to generate a three-dimensional representation; and projecting the three-dimensional representation including the overlaid object representation via a virtual reality device; wherein the method is performed by one or more processors.

In some examples, systems and methods for document writing and/or document generation are provided. For example, a method includes: identifying one or more document types associated with a request, each document type being associated with a document template; extracting one or more pieces of evidence from one or more data records based on the request; accessing one or more routes for document generations, each route of the one or more routes using one or more template-specific computing models; generating one or more documents using the one or more routes; and outputting a selected document that is selected from the one or more generated documents.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

A database system comprised of a decoupled compute layer and storage layer is implemented to store, build, and maintain a canonical dataset, a temporary buffer, and an edits dataset. The canonical dataset is a set of batch updated data. The data is appended in chunks to the canonical dataset such that the canonical dataset becomes a historical dataset over time. The buffer is a write ahead log that contains the most recent chunks of data and provides atomicity and durability for the database system. The edits dataset is the set of data that contains edits such as cell mutations, row appends and/or row deletions. The database system enables users to make cell or row-level edits to tables and observe those edits in analytical systems or downstream builds with minimal latency.