RAG mlops

[obriensystems]

Requirements

• DevOps LLM via RAG pipeline#12
  Determine how to do rag using a local or CSP LLM

• 2020 papar on RAG from Patrick Lewis - https://arxiv.org/pdf/2005.11401

• see https://github.com/ObrienlabsDev/blog/wiki/Machine-Learning-for-Java-Developers#rag

NVIDIA

• https://nvdam.widen.net/s/brxsxxtskb/dli-learning-journey-2009000-r5-web
• https://blogs.nvidia.com/blog/what-is-retrieval-augmented-generation/?ncid=so-nvsh-638671&dysig_tid=31f0d1bfe62940b888d8953572a4f045
• https://developer.nvidia.com/blog/getting-started-with-large-language-models-for-enterprise-solutions/

Start with

• "Augumenting Your LLM using Retrieval Augumented Generation" https://learn.nvidia.com/courses/course-detail?course_id=course-v1:DLI+S-FX-16+V1
• google search "rag ai wikipedia"
• https://blogs.nvidia.com/blog/what-is-retrieval-augmented-generation/
• https://en.wikipedia.org/wiki/Retrieval-augmented_generation

Workflows

LangChain - https://www.langchain.com/

• https://python.langchain.com/v0.2/docs/tutorials/
• https://python.langchain.com/v0.2/docs/tutorials/rag/
• https://python.langchain.com/v0.2/docs/tutorials/local_rag/

Misc

• https://research.google/blog/grounding-ai-in-reality-with-a-little-help-from-data-commons/?linkId=11011193
• https://n8n.io/integrations/categories/ai/