Thanks for the confirmation Vishal! I managed to setup my new password
Postgres' pg_vector doesn't seem suitable for production because it is 150 times slower than a dedicated vector database like Qdrant [1].
Weaviate is great when dealing with complex data, which is applicable to many common Drupal use cases. However, Qdrant is significantly faster than Weaviate [2]. Both have somewhat unusual open-source licenses but are still permissive.
I have experience with Qdrant already, and it works great so far, but Weaviate looks better in the long run because I need to handle larger and more complex data sets.
[1] https://nirantk.com/writing/pgvector-vs-qdrant
[2] https://myscale.com/blog/weaviate-vs-qdrant-feature-comparison-database-...
DevElCuy → created an issue.
For those using wodby/nginx, make sure to include this env vars:
NGINX_BACKEND_HOST=drupal
NGINX_VHOST_PRESET=drupal10
NGINX_SERVER_ROOT=/drupal/path/web
By default the PHP container is "php" as set in NGINX_BACKEND_HOST. Also, if the drupal root folder is /drupal/path, then the nginx server root is the sub-folder: web
I was a bit tired of drupalisms back in 2012. Nowadays we have more people doing site building than coding at such low API levels. If somebody ever has the time to explore schema and propose specific changes, then we can reference this issue as a nice evidence of how many really care :)
Can we explore LocalAI that comes with LlamaCPP (so any ggml model is supported)?