LLM-Supported AI System

From GM-RKB
(Redirected from LMM-based system)
Jump to navigation Jump to search

An LLM-Supported AI System is an AI-supported software system that uses large language models to perform natural language processing tasks and AI-driven automation.

References

2025-05-13

  1. Citations
1. Gabor Melli. "LLM-Supported AI System." GM-RKB, 2023. https://www.gabormelli.com/RKB/LLM-based_System
2. Arash Nicoomanesh. "A Dive Into LLM Output Configuration, Prompt Engineering Techniques and Guardrails (Part I)." Medium, 2023. https://medium.com/@anicomanesh/a-dive-into-advanced-prompt-engineering-techniques-for-llms-part-i-23c7b8459d51
3. Microsoft Azure AI. "Retrieval Augmented Generation (RAG) in Azure AI Search – Overview." Microsoft Learn, 2023. https://learn.microsoft.com/en-us/azure/search/retrieval-augmented-generation-overview
4. Dor Amram. "Building on Solid Ground: The Critical Importance of Good Architecture for LLM Tools." Medium, 2023. https://medium.com/@doramram210/building-on-solid-ground-the-critical-importance-of-good-architecture-for-llm-tools-b54cb80ef338
5. Michael Fauscette. "Agentic AI vs. LLMs: Understanding the Shift from Reactive to Proactive AI." Arion Research, 2023. https://www.arionresearch.com/blog/agentic-ai-vs-llms-understanding-the-shift-from-reactive-to-proactive-ai
6. Mariya Mansurova. "From Prototype to Production: Enhancing LLM Accuracy." Medium (Data Science Archive), 2023. https://medium.com/data-science/from-prototype-to-production-enhancing-llm-accuracy-791d79b0af9b
7. Saif Abid. "The LLM Mirage: Why Dazzling Prototypes Often Crumble in Production." Bitstrapped Blog, 2023. https://www.bitstrapped.com/blog/the-llm-mirage-why-dazzling-prototypes-often-crumble-in-production
8. PixelPlex. "10 Real-World Applications of Large Language Models (LLMs) in 2024." PixelPlex Blog, 2023. https://pixelplex.io/blog/llm-applications/
9. AI Accelerator Institute. "What is LLMOps? Complete 2025 industry guide." AI Accelerator Institute, 2023. https://www.aiacceleratorinstitute.com/your-guide-to-llmops/
10. Daniel Jeffries. "How to Build Better LLM Applications: Practical Tips for Cutting Through the Hype." HackerNoon, 2023. https://hackernoon.com/how-to-build-better-llm-applications-practical-tips-for-cutting-through-the-hype
11. Langchain Documentation. "LangChain: Building applications with LLMs through composability." 2023. https://python.langchain.com/docs/get_started/introduction
12. Pinecone. "Retrieval Augmented Generation (RAG): From Theory to LangChain Implementation." 2023. https://www.pinecone.io/learn/retrieval-augmented-generation/

2023

  • https://www.fiddler.ai/blog/four-ways-that-enterprises-deploy-llms
    • QUOTE: With the rapid pace of LLM innovations, enterprises are actively exploring use cases and deploying their first generative AI applications into production. As the deployment of LLMs or LLMOps began in earnest this year, enterprises have incorporated four types of LLM deployment methods, contingent on a mix of their own talent, tools and capital investment. Bear in mind these deployment approaches will keep evolving as new LLM optimizations and tooling are launched regularly.

      The goal of this post is to walk through these approaches and talk about the decisions behind these design choices.


    • Four approaches to LLMs in production (AWS Generative AI Summit)
    • There are four different approaches that enterprises are taking to jumpstart their LLM journey. These four approaches range from easy and cheap to difficult and expensive to deploy, and enterprises should assess their AI maturity, model selection (open vs. closed), data available, use cases, and investment resources when choosing the approach that works for their company’s AI strategy. Let’s dive in.

2023

  • chat
    • Q: An LLM-based production system refers to a system that utilizes large language models (LLMs) like OpenAI's GPT series to enhance, automate, or support various aspects of production or operations. These systems leverage the natural language understanding, generation, and reasoning capabilities of LLMs to perform tasks that typically require human intervention or expertise. While I'm not aware of any specific production systems called "LLM-based production systems," I can give you some examples of systems that utilize LLMs in their functioning:
      • Content generation: LLMs like GPT-4 can automatically generate content for blogs, social media, and marketing campaigns, reducing the time and effort required by human content creators.
      • Customer support: LLMs can be integrated into chatbots and support systems to handle customer queries, complaints, and concerns more effectively and efficiently.
      • Document summarization: LLMs can automatically summarize long documents, reports, or articles, making it easier for professionals to extract relevant information quickly.
      • Legal analysis: LLMs can be employed to review contracts, analyze legal documents, and provide insights into complex legal matters, saving time and resources for legal professionals.
      • Language translation: LLMs can be used to develop translation systems that accurately convert text from one language to another, making communication easier across different countries and cultures.
      • Sentiment analysis: LLMs can analyze customer reviews and feedback to identify positive or negative sentiments, helping businesses improve their products and services.
      • Medical diagnosis: LLMs can assist medical professionals by analyzing patient symptoms and medical history to suggest potential diagnoses and treatment plans.
    • These are just a few examples of how LLMs can be integrated into various production systems to enhance efficiency, reduce costs, and improve overall output. As AI research and development continues, LLMs will likely find even more applications across a wide range of industries.
Retrieved from "http://www.gabormelli.com/RKB/index.php?title=LLM-Supported_AI_System&oldid=967403"