Abstract: In an example embodiment, rather than use large language model (LLM) to directly generate desired computer code, an intermediate representation is generated by the LLM. The LLM is used to generate the portion of the computer code that cannot be computed programmatically (which may be called the “creative” part for purposes of the present disclosure). The intermediate representation can then be fed into a separate programmatic component that compiles the intermediate representation into compilable computer code. This fine-tuning may involve, for example, sanitizing the intermediate representation, enhancing the intermediate representation, and formatting the intermediate file, as well as modifying the intermediate representation based on a feature set.

Abstract: In an example embodiment, semantic chunking is combined with a metadata enrichment mechanism where chunks are enriched with additional metadata prior to being embedded. These embeddings may then be stored in a vector database and used to perform enriched similarity searches for augmentation of context provided to an LLM during LLM generation requests.

Abstract: In an example embodiment, supervisor code is coupled to each generated output from an LLM in response to multiple requests. This supervisor code contains instructions on how to handle errors, specifically errors in the generated output to which it is coupled but also in errors in other generated output. The supervisor codes for the different generated outputs are able to communicate with each other and coordinate how to handle the possible propagation of errors. In this manner, retries are able to be handled in an efficient manner where multiple generated outputs may be retried if just a single generated output causes an error, but without needing to retry all of the generated outputs. Thus, propagating errors can be contained using the minimum number of regeneration requests.

Abstract: In an example embodiment, a feature tree of all features in a request is generated. This feature tree describes interrelations between features that are dependent upon one another. The request is then broken into multiple, smaller requests. More particularly, each feature is included in its own dedicated request. Based on the dependencies, the smaller requests are then sent to the LLM in an order that preserve the dependency relationships. Intermediate results generated by the LLM in response to the multiple smaller request are then merged into a single intermediate result that can then be passed to the programmatic component for compiling.

Abstract: In an example embodiment, an iterative tools-based solution is utilized wherein a listing of possible tools for context gathering may be provided as input to an LLM along with a user prompt, by a host program. The LLM then generates text that invokes one or more of the tools when executed by the host program. When the host program executes the generated text from the LLM, context is gathered in accordance with the tool or tools selected by the LLM. This context can then be fed back into the LLM. This process can continuously iterate until the LLM has enough context to generate a response to the initial user prompt itself.

Abstract: In an example embodiment, a framework is provided to allow an LLM to regenerate an intermediate representation based on natural language feedback that is provided on the compilable computer code that was generated using the programmatic component from an earlier intermediate representation. The user is able to provide this feedback without having any knowledge of the intermediate representation and the framework is designed to allow the LLM to incorporate this feedback into future generation requests without the LLM being aware of the compilable computer code that was created from its prior iterations.

Abstract: In an example embodiment, a language server connected to an integrated Development Environment (IDE) is used to identify, from a given input code, various code artifacts, such as functions, variables, etc., and then to search a repository of code files for declarations, definitions, and references related to those identified code artifacts. The declarations, definitions, and references can then be passed as context into an LLM.

Abstract: In an example embodiment, a Language Server Protocol (LSP) is utilized to connect IDEs to test frameworks via a shared language server. More particularly, the shared language server is modified to permit feedback to be delivered regarding test results from the test framework to be delivered to the IDEs, either directly via a code action that supports direct feedback, or indirectly by causing the language server to write test results to the IDEs as code comments within the software code itself. The result is that a single test framework can be utilized by developers using completely different IDEs, without requiring a separate test framework to be developed for each IDE.

Abstract: Systems and methods include reception of a user query in natural language from a user, determination of a system prompt including instructions to generate a search query, transmission of a user prompt based on the user query and the system prompt to a text generation model, reception of a generated function call search query from the text generation model, transmission of the generated function call search query to a repository of function call metadata, reception of first function call metadata from the repository in response to the search query, transmission of the first function call metadata and the user prompt to the text generation model to generate a first function call, and transmission of the first function call to an endpoint indicated by the function call metadata.

Abstract: In an example embodiment, a solution is provided by utilizing an intermediate file format for either an input prompt to or output from a large language model (LLM) (or both). This intermediate file format is one that has the property of being minimizable, meaning that tokens contained in a file of that intermediate file format can be stripped out or otherwise removed without changing the semantic meaning of the file. The input prompt can be created in or converted to this intermediate file format and then minimized prior to being sent to the LLM for text generation. Furthermore, a system message included with the input prompt may instruct the LLM to generate text in the intermediate file format, in minimized form. A specialized parser may then be included to parse the minimized output produced by the LLM.

Abstract: In an example embodiment, rather than use large language model (LLM) to directly generate desired computer code, an intermediate representation is generated by the LLM. The LLM is used to generate the portion of the computer code that cannot be computed programmatically (which may be called the “creative” part for purposes of the present disclosure). The intermediate representation can then be fed into a separate programmatic component that compiles the intermediate representation into compilable computer code. This fine-tuning may involve, for example, sanitizing the intermediate representation, enhancing the intermediate representation, and formatting the intermediate file, as well as modifying the intermediate representation based on a feature set.

Abstract: In an example embodiment, a common, composable abstraction is provided that allows components to work efficiently across programming languages and services without the need to write glue code. Application developers can concentrate on the application logic itself. The functionality of services can be developed by framework developers only once, using the programming language of their choice.

Abstract: In an example embodiment, a solution is provided that automatically adds a system message to natural language text provided by a user to generate a prompt to a Large Language Model (LLM) to automatically generate a code in a declarative language format, the code corresponding to the natural language text. Furthermore, retrieval augmented generation may be utilized to overcome the maximum number of contextual tokens permitted as input to an LLM. More particularly, the system message may be designed to include an instruction to the LLM to generate search calls for one or more entity definitions in a specified format from a database. The search calls may then be performed on the database via a similarity search to obtain the relevant information, which can then be passed back into the LLM for the generation of the code.

Abstract: In an example, a software package is provided that provides an interface such that when the software is executed, a user is able to provide a natural language prompt using a scripting language that directs the interface to interact with a Large Language Model (LLM), adding contextual information to prompts sent to the LLM. The interface is then also able to extract and evaluate programming code generated by the LLM, so that the generated code may be used immediately in a software package, without the need for user edits and/or copy/pasting.

Abstract: In an example embodiment, a solution is provided in which an outbox table is added to each container in a database. Rather than perform an emit solely using the application instance alone (in response to a notification from the database that the underlying database action has been performed), or using an outside outbox table processor, an outbox table processor is integrated into the microservice application. When a database action is performed by the microservice application, that database action is written into the outbox table in the corresponding container in the database. Furthermore, whenever the outbox table processor determines that the state of the database has changed in a way that leads to an emit, it then reads the actions in the outbox table, issues an emit to notify one or more external systems of the actions, and deletes those actions from the outbox table.

Abstract: In an example, Generative Artificial Intelligence (GAI) is utilized to automatically generate software servers. More particularly, a GAI model may be used to create a declarative-based data model and accompanying data for a software server, such as a web server. Furthermore, the created declarative-based data model can be automatically tested and resubmitted to the GAI model to refine the software server file upon failure of the testing.

Abstract: In an example embodiment, a Language Server Protocol (LSP) is utilized to connect IDEs to test frameworks via a shared language server. More particularly, the shared language server is modified to permit feedback to be delivered regarding test results from the test framework to be delivered to the IDEs, either directly via a code action that supports direct feedback, or indirectly by causing the language server to write test results to the IDEs as code comments within the software code itself. The result is that a single test framework can be utilized by developers using completely different IDEs, without requiring a separate test framework to be developed for each IDE.

Abstract: In an example embodiment, a common, composable abstraction is provided that allows components to work efficiently across programming languages and services without the need to write glue code. Application developers can concentrate on the application logic itself. The functionality of services can be developed by framework developers only once, using the programming language of their choice.

Abstract: In an example embodiment, a solution is provided in which an outbox table is added to each container in a database. Rather than perform an emit solely using the application instance alone (in response to a notification from the database that the underlying database action has been performed), or using an outside outbox table processor, an outbox table processor is integrated into the microservice application. When a database action is performed by the microservice application, that database action is written into the outbox table in the corresponding container in the database. Furthermore, whenever the outbox table processor determines that the state of the database has changed in a way that leads to an emit, it then reads the actions in the outbox table, issues an emit to notify one or more external systems of the actions, and deletes those actions from the outbox table.

Abstract: Various examples are directed to systems and methods for operating an application for use with an enterprise database system. A common format process may receive, from a user device, a first request directed to the enterprise database system, convert the first request into a common protocol, and send a first common protocol request to the application logic code. The application logic code may generate a second request in the common protocol and send the second request to the common format process. The common format process may convert the second request from the common protocol to a database query protocol to generate at least one database query and send the at least one database query to the enterprise database system.