Aussie AI

Applications of Generative AI

  • Last Updated 12 December, 2024
  • by David Spuler, Ph.D.

Apps Built on AI

Building Applications for Generative AI

Research on building Gen AI apps:

Inference Frameworks

Research papers include:

Orchestration Frameworks

Research papers include:

Wrap Architectures for Gen AI Applications

The simplest architectures for AI applications are those that simply "wrap" around LLMs, whether it is commercial LLMs like GPT, or open source LLMs like Mistral or Llama.

OpenAI API Applications

One particular type of "wrap" AI application is to use the OpenAI API (e.g. for ChatGPT).

Batch API for Inference

Application Layer

The "application layer" is the whole range of applications that can be built on top of generative AI and its LLMs as building blocks. Research includes:

Code Generation Applications of Generative AI

Code Checker Applications

User Interface (UI) Issues for AI Apps

Consoles

Script Languages

  • L. Zheng, L. Yin, Z. Xie, J. Huang, C. Sun, C. H. Yu, S. Cao, C. Kozyrakis, I. Stoica, J. E. Gonzalez et al., Dec 2023, Efficiently programming large language models using SGLang, arXiv preprint arXiv:2312.07104, 2023, https://arxiv.org/abs/2312.07104 (Uses a radix attention method, a trie or prefix tree, for KV caching.)
  • Hongzheng Chen, Niansong Zhang, Shaojie Xiang, Zhichen Zeng, Mengjia Dai, Zhiru Zhang, 7 Apr 2024, Allo: A Programming Model for Composable Accelerator Design, https://arxiv.org/abs/2404.04815
  • Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vardhamanan, Saiful Haq, Ashutosh Sharma, Thomas T. Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, Christopher Potts, 5 Oct 2023, DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines, https://arxiv.org/abs/2310.03714 Code: https://github.com/stanfordnlp/dspy
  • Honghua Dong, Qidong Su, Yubo Gao, Zhaoyu Li, Yangjun Ruan, Gennady Pekhimenko, Chris J. Maddison, Xujie Si, 19 Jun 2024, APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts, https://arxiv.org/abs/2406.13161 Code: https://github.com/appl-team/appl (A Python-like script language for prompt engineering integration into applications and agents.)
  • Till Döhmen, 2024/10/17, Introducing the prompt() Function: Use the Power of LLMs with SQL! https://motherduck.com/blog/sql-llm-prompt-function-gpt-models/
  • Mandana Vaziri, Louis Mandel, Claudio Spiess, Martin Hirzel, 24 Oct 2024, PDL: A Declarative Prompt Programming Language, https://arxiv.org/abs/2410.19135
  • Saksham Goel, October 29, 2024, Build LLM/RAG pipelines with YAML templates by Pathway, https://pathway.com/blog/llm-yaml-templates
  • Yuka Ikarashi, Kevin Qian, Samir Droubi, Alex Reinking, Gilbert Bernstein, Jonathan Ragan-Kelley, 14 Nov 2024 (v2), Exo 2: Growing a Scheduling Language, https://arxiv.org/abs/2411.07211

API Architectures

Plugins

  • Reyna Abhyankar, Zijian He, Vikranth Srivatsa, Hao Zhang, Yiying Zhang, 2024, INFERCEPT: Efficient Intercept Support for Augmented Large Language Model Inference, https://openreview.net/pdf?id=wDDGQabYPQ
  • Zile Qiao, Wei Ye, Yong Jiang, Tong Mo, Pengjun Xie, Weiping Li, Fei Huang, Shikun Zhang, 12 Jun 2024, Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling, https://arxiv.org/abs/2406.08116
  • Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, Xu Jiang, Karl Cobbe, Tyna Eloundou, Gretchen Krueger, Kevin Button, Matthew Knight, Benjamin Chess, John Schulman, 1 Jun 2022 (v3), WebGPT: Browser-assisted question-answering with human feedback, https://arxiv.org/abs/2112.09332
  • Chuan Yan, Ruomai Ren, Mark Huasong Meng, Liuhuo Wan, Tian Yang Ooi, Guangdong Bai, 26 Aug 2024, Exploring ChatGPT App Ecosystem: Distribution, Deployment and Security, https://arxiv.org/abs/2408.14357

Custom AI Apps

No Code/Low Code for AI Apps

Miniapps

Tabular Data Applications

More AI Research

Read more about: