ghostwrAIter - a local AI assisted tool for helping with support cases
an invention by paolodepa
Updated 5 months ago. 4 hacker ♥️. 1 follower.

Description

This project is meant to fight the loneliness of the support team members, providing them an AI assistant (hopefully) capable of scraping supportconfigs in a RAG fashion, trying to answer specific questions.

Goals

  • Setup an Ollama backend, spinning one (or more??) code-focused LLMs selected by license, performance and quality of the results between:
  • Setup a Web UI for it, choosing an easily extensible and customizable option between:
  • Extend the solution in order to be able to:
    • Add ZIU/Concord shared folders to its RAG context
    • Add BZ cases, splitted in comments to its RAG context
      • A plus would be to login using the IDP portal to ghostwrAIter itself and use the same credentials to query BZ
    • Add specific packages picking them from IBS repos
      • A plus would be to login using the IDP portal to ghostwrAIter itself and use the same credentials to query IBS
      • A plus would be to desume the packages of interest and the right channel and version to be picked from the added BZ cases

Looking for hackers with the skills:

ai support

This project is part of:

Hack Week 24

Activity

  • 5 months ago: paolodepa started this project.
  • 6 months ago: m.crivellari liked this project.
  • 6 months ago: HvdHeuvel liked this project.
  • 6 months ago: livdywan liked this project.
  • 6 months ago: lthadeus liked this project.
  • 6 months ago: paolodepa added keyword "support" to this project.
  • 6 months ago: paolodepa added keyword "ai" to this project.
  • 6 months ago: paolodepa originated this project.


    • Comments

    • paolodepa
      5 months ago by paolodepa | Reply

      The project soon moved to CLI, as the skills for integrating a WEB-UI are not my cup of tea :-/
      Its description and source code can be found at ghostwrAIter

      I tested the listed LLMs and also the following embedding models: mxbai-embed-large, nomic-embed-text, all-minilm.
      My impression is that the current state of the art for the really open-source llms and embedding models is not still mature and ready for production grade and that a big gap exists with the most well-known commercial product.

      Hopefully will run a refresh for the next hackweek.

    Similar Projects

    This project is one of its kind!