Abstract: One example method includes integrating user space applications with kernel space events including primitives. The events are intercepted in kernel space and processed in user space. The events can be stored in a session cache that allows a holistic view of behavior to be determined with regard to resources of the computing system. The events in the session cache can be correlated to user or process behavior by provided a time-based view of the events.

Abstract: One example method includes receiving a plain language request from a user, with a zero shot classification model, determining, and selecting, application program interfaces (APIs) needed to fulfill the plain language request, with a large language model (LLM), processing the APIs to generate a preliminary plan which comprises an order in which the APIs must be called in order to fulfill the plain language request, for each of the APIs in the preliminary plan, determining respective parameters, and combining the parameters with the APIs to generate a final plan which, when executed, fulfills the plain language request.

Abstract: Generating a call or request from unstructured input. Natural language, which is unstructured, is received and processed by a language interface engine. The language interface engine executes a series of models in a cascaded manner. One model selects an application programming interface from a set of target application programming interfaces. Another model then selects a particular method of the selected application programming interface. Another model then uses values from the unstructured input as arguments to include in the call. The call is then generated and executed.

Abstract: Integration of structural information into an asset management catalog (e.g., using a computerized tool), is enabled. For example, a system can comprise a processor and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising: based on schema data applicable to data stored in a data storage asset, determining structure data representative of a structure of the data stored in the data storage asset, in response to determining the structure data, generating a data entry, applicable to the structure data, to be added to an asset management catalog associated with the data storage asset, and in response to generating the data entry, associating the data entry with the data stored in the data storage asset.

Abstract: Shared function execution mitigates cold start penalties for execution units. When a serverless platform receives a request, the request is performed when the serverless platform has a warm execution unit for the request. If a warm execution unit is not available or running, the serverless platform may send the request to another serverless platform rather than cold start an execution unit. The cold start is performed when the warm execution unit is not available at other platforms.

Abstract: A method includes identifying, by a server module running at a stream data platform, a set of data to be moved to a target data storage tier of the stream data platform, querying, by the server module, service level agreement (SLA) objectives of the target data storage tier, fetching, by the server module, the set of data, selecting, by the server module, a compressor based on the SLA objectives, compressing the set of data using the selected compressor, and storing the set of data in the target data storage tier.

Abstract: Integration of structural information into an asset management catalog (e.g., using a computerized tool), is enabled. For example, a system can comprise a processor and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising: based on schema data applicable to data stored in a data storage asset, determining structure data representative of a structure of the data stored in the data storage asset, in response to determining the structure data, generating a data entry, applicable to the structure data, to be added to an asset management catalog associated with the data storage asset, and in response to generating the data entry, associating the data entry with the data stored in the data storage asset.

Abstract: Integration of semantic information into an asset management catalog (e.g., using a computerized tool), is enabled. For example, a system can comprise a processor and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising: based on structure data representative of a structure of data stored in a data storage asset, determining semantic metadata applicable to the data stored in the data storage asset, in response to determining the semantic metadata, generating a data entry, applicable to the semantic metadata, to be added to an asset management catalog associated with the data storage asset, and in response to generating the data entry, associating the data entry with the data stored in the data storage asset.

Abstract: One example method includes injecting processing into sessions including IO sessions. Events in a file system are intercepted and processed. During processing, policies may be applied to the events. Some of the policies are triggered such that external actions or processing is applied to the event. Once the actions have been performed, the event may be processed by the file system.

Abstract: Detecting a decrease or loss in performance of a prediction engine configured to predict a compressor for compressing data. The prediction engine suffers a loss in performance when the compressor inferred by the prediction engine does not match or does not sufficiently match a compressor inferred by a compressor selector. Using compressors inferred by two different models allows the loss in performance to be detected. The loss in performance may constitute a violation of a service level agreement (SLA) or service level objective (SLO). Then the loss in performance is determined.

Abstract: One example method includes receiving a data stream, collecting a sequence of one or more batches of data from the data stream, analyzing the batches of data in the sequence, obtaining compressor choices for the batches of data in the sequence, obtaining a new batch of data from the data stream, analyzing the new batch of data, based on the analyzing and the compressor choices for the batches of data in the sequence, and the analyzing of the new batch of data, generating a prediction that identifies recommended data compressor for the new batch of data, and in response to a change in the data stream, compressing the new batch of data using the recommended data compressor.

Abstract: Shared function execution mitigates cold start penalties for execution units. When a serverless platform receives a request, the request is performed when the serverless platform has a warm execution unit for the request. If a warm execution unit is not available or running, the serverless platform may send the request to another serverless platform rather than cold start an execution unit. The cold start is performed when the warm execution unit is not available at other platforms.

Abstract: A method includes identifying, by a server module running at a stream data platform, a set of data to be moved to a target data storage tier of the stream data platform, querying, by the server module, service level agreement (SLA) objectives of the target data storage tier, fetching, by the server module, the set of data, selecting, by the server module, a compressor based on the SLA objectives, compressing the set of data using the selected compressor, and storing the set of data in the target data storage tier.

Abstract: One method includes receiving a user-defined function, generating a binary based on the user-defined function, copying the binary to a target host where the user-defined function will run, in response to a lookup request, received from an API gateway based on a function invocation by a user, looking up the target host and a route, and returning, to the API gateway, a target host ID and the route, so as to enable the API gateway to request the target host to respond to the function invocation.

Abstract: Executing functions in serverless platforms leveraging metadata is disclosed. Embodiments of the invention related to using metadata when placing and/or executing functions. The metadata includes request metadata, container or function metadata, node metadata, and/or data metadata. The metadata allows a function to be placed and executed in a manner that accounts for user intent, container requirements, node resources, and data location. Functions can be placed across different serverless platforms. Once the metadata is evaluated and a location is selected, a function is placed and executed at the selected location.

Abstract: One example method includes receiving a data event notification, retrieving data to which the data event notification pertains, analyzing the data, based on the analyzing, generating metadata pertaining to the data, and transmitting the metadata to a repository. These operations may be performed automatically in response to receipt of the data event notification. The data event notification may likewise be generated automatically in response to implementation of the data event, which may be any of a data create, read, update, or delete, operation.

Abstract: One example method includes data orchestration. Data sets are available to users in an online marketplace. Based on requests for data sets, other data sets may be recommended. The recommended data sets are moved or copied to recommended locations. This ensures that the data sets are available to the user more quickly if subsequently requested.

Abstract: One example method includes receiving, by an administrator from a user computer system, a query identifying content the user wants to access, and the administrator and user computer system are elements of a system that includes a group of networked user computer systems, parsing, by the administrator, the query to identify metadata included in the query, identifying, by the administrator, any content of a datastore that matches the metadata, packaging, by the administrator, the datastore content into a virtual filesystem, and exposing, by the administrator, the virtual filesystem to one of the user computer systems.

Abstract: One example method includes, at a computer system that is an element of a network, intercepting stream elements of a stream associated with the computer system, selecting one or more of the stream elements, analyzing the selected stream elements, and based on the analyzing, emitting the selected stream elements to an external, query-able, storage entity that is external to the computer system. The metadata emitted to the storage entity may further include metadata that was natively generated at the computer system.

Abstract: One example method includes declaring a management requirement for a collection of data, defining metadata that embodies the requirement, associating the management requirement with the collection of data, and performing a filesystem operation, with respect to the collection of data, based on the metadata. The declaring and defining operations may be performed by an administrator operating in a centralized datastore that includes a metadata repository, and the defined metadata may be stored in the metadata repository.