Comments

• 

  5 months ago by PSuarezHernandez | Reply

  Some conclusions after Hackweek 24:

  • ollama + open-webui is a nice combo to allow running LLMs locally (tried also Local AI)
  • open-webui allows you to add custom knoweldge bases (collections) to feed models.
  • Uyuni documentation, Salt documentation can be used on this collections to make models to learn.
  • Using a tailored documentation works better to feed models.
  • Tried different models: llama3.1, mistral, mistral-nemo, gemma2, phi3,..
  • Getting promising results, particularly with mistral-nemo.. but also getting model hallutinations - model parameters can be adjusted to reduce them.

  Takeaways

  • Small models runs fairly well with CPU only.
  • Making an expert assistance on Uyuni, with an extensive knowledge based on documentation, might be something to keep exploring.

  Next steps

  • Make the model to understand Uyuni API, so it is able to translate user requests to actual call to Uyuni API.

×
Edit Comment 9265
# A First Level Header
## A Second Level Header

Use one asterisk to *emphasize*

Use two asterisks for **strong emphasis**

- Use hyphens
- for unordereed
- lists

This is an [link to example.com](http://example.com/)

This is an image ![an openSUSE geeko icon](https://en.opensuse.org/images/d/d0/Icon-distribution.png)

This is a user link @hans

This is a project link hw#some-cool-title
More Complex Markdown Help
Formatting Help
• Edit
• Preview
#### Some conclusions after Hackweek 24: - ollama + open-webui is a nice combo to allow running LLMs locally (tried also Local AI) - open-webui allows you to add custom knoweldge bases (collections) to feed models. - Uyuni documentation, Salt documentation can be used on this collections to make models to learn. - Using a tailored documentation works better to feed models. - Tried different models: llama3.1, mistral, mistral-nemo, gemma2, phi3,.. - Getting promising results, particularly with `mistral-nemo`.. but also getting model hallutinations - model parameters can be adjusted to reduce them. #### Takeaways - Small models runs fairly well with CPU only. - Making an expert assistance on Uyuni, with an extensive knowledge based on documentation, might be something to keep exploring. #### Next steps - Make the model to understand Uyuni API, so it is able to translate user requests to actual call to Uyuni API.
 
×
Reply to PSuarezHernandez
Some conclusions after Hackweek 24:
• ollama + open-webui is a nice combo to allow running LLMs locally (tried also Local AI)
• open-webui allows you to add custom knoweldge bases (collections) to feed models.
• Uyuni documentation, Salt documentation can be used on this collections to make models to learn.
• Using a tailored documentation works better to feed models.
• Tried different models: llama3.1, mistral, mistral-nemo, gemma2, phi3,..
• Getting promising results, particularly with mistral-nemo.. but also getting model hallutinations - model parameters can be adjusted to reduce them.
Takeaways
• Small models runs fairly well with CPU only.
• Making an expert assistance on Uyuni, with an extensive knowledge based on documentation, might be something to keep exploring.
Next steps
• Make the model to understand Uyuni API, so it is able to translate user requests to actual call to Uyuni API.
---
# A First Level Header
## A Second Level Header

Use one asterisk to *emphasize*

Use two asterisks for **strong emphasis**

- Use hyphens
- for unordereed
- lists

This is an [link to example.com](http://example.com/)

This is an image ![an openSUSE geeko icon](https://en.opensuse.org/images/d/d0/Icon-distribution.png)

This is a user link @hans

This is a project link hw#some-cool-title
More Complex Markdown Help
Formatting Help
• Edit
• Preview