AI LLM - terrytaylorbonn/auxdrone GitHub Wiki

25.0208 Gdrive

GOAL1:

  • Agent/RAG for ChatGPT
  • retrieves local doc/website for augmentation
  • (must pay for tokens)

GOAL2:

  • UI interface to
  • local LLM
  • trained on API sandbox doc/website content
  • (free, no tokens)

1 LLMs

image

https://www.youtube.com/shorts/FJtFZwbvkI4

2 AI agents

How to Build Effective AI Agents in Pure Python - Beginner Course Dave Ebbelaar https://www.youtube.com/watch?v=bZzyPscbtI8

3 RAG

https://www.k2view.com/blog/rag-genai/#Enter-RAG

"Retrieval-Augmented Generation (RAG) is a generative AI framework that enhances the response capabilities of an LLM by retrieving and injecting into the LLM, fresh, trusted data from your very own knowledge bases and enterprise systems.Essentially, RAG enables LLMs to integrate public, external information with private, internal data to instantly formulate the most accurate answer possible.With RAG, LLMs can gain deep understanding into specific areas without having to be retrained – making it an efficient and cost-effective method to keep LLMs current, relevant, accurate, and helpful in various situations."

image

Google "rag ai"

Retrieval-Augmented Generation (RAG) is an AI technique that combines generative AI models with information retrieval systems. This technique improves the accuracy and relevance of AI-generated text.

How it works

  • Search: RAG uses search algorithms to query external data sources, such as databases, knowledge bases, and web pages.
  • Pre-process: RAG pre-processes the retrieved information.
  • Integrate: RAG incorporates the pre-processed information into a pre-trained large language model (LLM).
  • Generate: The LLM uses the retrieved information to generate a response.

Benefits

  • RAG can produce more accurate and relevant responses.
  • RAG can be used to extend the capabilities of LLMs to specific domains.
  • RAG can be used to improve the output of LLMs without retraining the model.

Limitations

  • The accuracy of RAG's responses depends on the quality of the data it pulls from.
  • RAG can be computationally expensive.
  • Adding a retrieval step to an LLM can increase latency.
  • RAG can be used in many applications, including customer service, sales, marketing, and commerce.