Rapid Development of Compositional AI
- URL: http://arxiv.org/abs/2302.05941v1
- Date: Sun, 12 Feb 2023 15:41:14 GMT
- Title: Rapid Development of Compositional AI
- Authors: Lee Martie, Jessie Rosenberg, Veronique Demers, Gaoyuan Zhang, Onkar
Bhardwaj, John Henning, Aditya Prasad, Matt Stallone, Ja Young Lee, Lucy Yip,
Damilola Adesina, Elahe Paikari, Oscar Resendiz, Sarah Shaw, David Cox
- Abstract summary: (Bee)* is a framework for building integrated, scalable, and interactive compositional AI applications.
We show how (Bee)* supports building integrated, scalable, and interactive compositional AI applications with a simplified developer experience.
- Score: 5.1158486685898374
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Compositional AI systems, which combine multiple artificial intelligence
components together with other application components to solve a larger
problem, have no known pattern of development and are often approached in a
bespoke and ad hoc style. This makes development slower and harder to reuse for
future applications. To support the full rapid development cycle of
compositional AI applications, we have developed a novel framework called
(Bee)* (written as a regular expression and pronounced as "beestar"). We
illustrate how (Bee)* supports building integrated, scalable, and interactive
compositional AI applications with a simplified developer experience.
Related papers
- OpenDevin: An Open Platform for AI Software Developers as Generalist Agents [109.8507367518992]
We introduce OpenDevin, a platform for the development of AI agents that interact with the world in similar ways to those of a human developer.
We describe how the platform allows for the implementation of new agents, safe interaction with sandboxed environments for code execution, and incorporation of evaluation benchmarks.
arXiv Detail & Related papers (2024-07-23T17:50:43Z) - Inference Optimization of Foundation Models on AI Accelerators [68.24450520773688]
Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI.
As the number of model parameters reaches to hundreds of billions, their deployment incurs prohibitive inference costs and high latency in real-world scenarios.
This tutorial offers a comprehensive discussion on complementary inference optimization techniques using AI accelerators.
arXiv Detail & Related papers (2024-07-12T09:24:34Z) - Toward Programming Languages for Reasoning: Humans, Symbolic Systems, and AI Agents [0.0]
Integration, composition, mechanization, and AI assisted development are the driving themes in the future of software development.
This paper proposes a novel approach to this challenge -- instead of new language features or logical constructs, we propose radical simplification in the form of the Bosque platform and language.
arXiv Detail & Related papers (2024-07-08T19:50:42Z) - AI2Apps: A Visual IDE for Building LLM-based AI Agent Applications [23.3982451133068]
We introduce AI2Apps, a Visual Integrated Development Environment (Visual IDE) with full-cycle capabilities that accelerates developers to build deployable AI agent Applications.
On one hand, AI2Apps integrates a comprehensive development toolkit ranging from a prototyping canvas and AI-assisted code editor to agent debugger, management system, and deployment tools all within a web-based graphical user interface.
On the other hand, AI2Apps visualizes reusable front-end and back-end code as intuitive drag-and-drop components.
arXiv Detail & Related papers (2024-04-07T10:02:09Z) - Rapid Mobile App Development for Generative AI Agents on MIT App Inventor [12.091916451641021]
We present a methodology for the rapid development of AI agent applications using the development platform provided by MIT App Inventor.
We share the development journey of three distinct mobile applications: SynchroNet for fostering sustainable communities; ProductiviTeams for addressing procrastination; and iHELP for enhancing community safety.
arXiv Detail & Related papers (2024-04-01T02:35:19Z) - Cognition is All You Need -- The Next Layer of AI Above Large Language
Models [0.0]
We present Cognitive AI, a framework for neurosymbolic cognition outside of large language models.
We propose that Cognitive AI is a necessary precursor for the evolution of the forms of AI, such as AGI, and specifically claim that AGI cannot be achieved by probabilistic approaches on their own.
We conclude with a discussion of the implications for large language models, adoption cycles in AI, and commercial Cognitive AI development.
arXiv Detail & Related papers (2024-03-04T16:11:57Z) - A Graphical Modeling Language for Artificial Intelligence Applications
in Automation Systems [69.50862982117127]
An interdisciplinary graphical modeling language that enables the modeling of an AI application as an overall system comprehensible to all disciplines does not yet exist.
This paper presents a graphical modeling language that enables consistent and understandable modeling of AI applications in automation systems at system level.
arXiv Detail & Related papers (2023-06-20T12:06:41Z) - i-Code Studio: A Configurable and Composable Framework for Integrative
AI [93.74891865028867]
We propose the i-Code Studio, a flexible and composable framework for Integrative AI.
The i-Code Studio orchestrates multiple pre-trained models in a fine-tuning-free fashion to conduct complex multimodal tasks.
The i-Code Studio achieves impressive results on a variety of zero-shot multimodal tasks, such as video-to-text retrieval, speech-to-speech translation, and visual question answering.
arXiv Detail & Related papers (2023-05-23T06:45:55Z) - A User-Centred Framework for Explainable Artificial Intelligence in
Human-Robot Interaction [70.11080854486953]
We propose a user-centred framework for XAI that focuses on its social-interactive aspect.
The framework aims to provide a structure for interactive XAI solutions thought for non-expert users.
arXiv Detail & Related papers (2021-09-27T09:56:23Z) - Accelerating the Development of Multimodal, Integrative-AI Systems with
Platform for Situated Intelligence [1.595445991573573]
We describe Platform for Situated Intelligence, an open-source framework for multimodal, integrative-AI systems.
We provide a brief, high-level overview of the framework and its main affordances, and discuss its implications for HRI.
arXiv Detail & Related papers (2020-10-12T23:53:12Z) - Plato Dialogue System: A Flexible Conversational AI Research Platform [64.82999992143448]
Plato is a flexible Conversational AI platform written in Python that supports any kind of conversational agent architecture.
Plato has been designed to be easy to understand and debug and is agnostic to the underlying learning frameworks that train each component.
arXiv Detail & Related papers (2020-01-17T18:27:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.