mirror of
https://github.com/StanGirard/quivr.git
synced 2024-12-14 21:21:56 +03:00
6d024bc16d
# 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> |
||
|---|---|---|
| .. | ||
| .vscode | ||
| llm | ||
| middlewares | ||
| models | ||
| modules | ||
| packages | ||
| repository | ||
| routes | ||
| supabase/functions/add-new-email | ||
| tests | ||
| vectorstore | ||
| .dockerignore | ||
| celery_config.py | ||
| celery_worker.py | ||
| conftest.py | ||
| Dockerfile | ||
| Dockerfile.dev | ||
| logger.py | ||
| main.py | ||
| manage_services.sh | ||
| pyrightconfig.json | ||
| requirements.txt | ||