Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Shanbady/qdrant docs #1932

Merged
merged 5 commits into from
Jan 2, 2025
Merged

Shanbady/qdrant docs #1932

merged 5 commits into from
Jan 2, 2025

Conversation

shanbady
Copy link
Contributor

What are the relevant tickets?

Closes https://github.com/mitodl/hq/issues/6352

Description (What does it do?)

This PR consolidates some useful information (scattered through existing PRs) regarding embeddings.

How can this be tested?

Give it a read through. Note if there are mistakes or if anything needs clarity.

@shanbady shanbady added the Needs Review An open Pull Request that is ready for review label Dec 23, 2024
@shanbady shanbady marked this pull request as ready for review December 23, 2024 21:39
@ChristopherChudzicki ChristopherChudzicki self-assigned this Jan 2, 2025
Copy link
Contributor

@ChristopherChudzicki ChristopherChudzicki left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍 Docs look good.

Question: Reading "Embeddings are automatically generated for new conetnt by a periodic celery task." made me look at the code a little, where I saw:

@app.task(bind=True)
def embed_new_learning_resources(self):
    # ...
    new_learning_resources = LearningResource.objects.filter(
        published=True,
        created_on__gt=since,
    ).exclude(resource_type=CONTENT_FILE_TYPE)

Do we need to update the embeddings when resources are updated? (not created)

@ChristopherChudzicki ChristopherChudzicki added Waiting on author and removed Needs Review An open Pull Request that is ready for review labels Jan 2, 2025
@shanbady
Copy link
Contributor Author

shanbady commented Jan 2, 2025

👍 Docs look good.

Question: Reading "Embeddings are automatically generated for new conetnt by a periodic celery task." made me look at the code a little, where I saw:

@app.task(bind=True)
def embed_new_learning_resources(self):
    # ...
    new_learning_resources = LearningResource.objects.filter(
        published=True,
        created_on__gt=since,
    ).exclude(resource_type=CONTENT_FILE_TYPE)

Do we need to update the embeddings when resources are updated? (not created)

We will. There is still some work left around detecting both contentfile and resource embedding changes so it will probably get covered there.

@shanbady shanbady merged commit 7ff0b29 into main Jan 2, 2025
11 checks passed
@shanbady shanbady deleted the shanbady/qdrant-docs branch January 2, 2025 15:11
This was referenced Jan 2, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants