Fix missing embeddings not skipped if filters are used #2230
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
julian-risch
requested changes
Feb 22, 2022
There was a problem hiding this comment.
Thank you for taking the initiative! Code changes look good to me. As we already had community members reporting an issue with the skip_missing_embeddings functionality and it's very helpful for allowing updating the document index at runtime, we should create a test here too. What I imagine is a doc store with some documents with meta data. Not all documents have an embedding. Let's run a vector search query with a filter and check that only documents that both have an embedding and fulfill the filter requirement are retrieved.
…thub.com/deepset-ai/haystack into fix_filter_skip_embeddings_elasticsearch
julian-risch
approved these changes
Feb 22, 2022
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Proposed changes:
This PR fixes the bug that the
skip_missing_embeddingsparameter is ignored when filters are specified. Closes #2113.Status (please check what you already did):