# Description
With this pull request, I add a fix that **enables Ollama**.
Running quivr in a Docker container, Ollama needs to be accessed via
http://host.docker.internal:11434.
This URL is defined as `api_base` of the `ChatLiteLLM` constructor. But
there are calls that are missing `api_base`. This leads to fallback URLs
being used. This is now fixed.
Fixes#2270#2267#2217#2204
## Checklist before requesting a review
Please delete options that are not relevant.
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged
## Screenshots (if appropriate):
None
Co-authored-by: Niels Garve <niels.garve@experienceone.com>
This pull request updates the system templates to include support for
custom personality. It adds a new parameter called "custom_personality"
to the generate_stream function, which allows users to provide a custom
personality for the AI assistant. This feature enhances the user
experience by allowing them to personalize the assistant's responses.
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
