Skip existing embeddings

[shanbady]

What are the relevant tickets?

Closes https://github.com/mitodl/hq/issues/6670

Description (What does it do?)

This PR makes it so that the embedding generation for both learning resources and contentfiles skips over existing embeddings by default. We can force re-embed by passing the --overwrite flag to the generate_embeddngs command.

How can this be tested?

1. checkout this branch
2. restart celery
   3.get the id of learning resource that has associated contentfiles and pass it into the generate_embeddings command python manage.py generate_embeddings --resource-ids <the id>
3. observe the celery container's output - there should be some output indicating that embeddings are being generated (different output depending on if fastembed or ollama via litellm is used).
4. Once that completes, verify there are embeddings on the qdrant dashboard
5. while keeping an eye on the celery output, re-run the embedding command
6. note that embeddings are not skipped
7. re-run the command with the overwrite flag python manage.py generate_embeddings --resource-ids <the id> --overwrite and note that once again embeddings are getting generated