DAGE-31: M3 index doc to solr with embeddings #201
Conversation
This file contains hidden or 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
…e to index embeddings in file `output/embeddings/doc_embeddings.jsonl`
nicolo-rinaldi
force-pushed
the
DAGE-31_M3_index-doc-to-solr
branch
3 times, most recently
from
20e9505 to
03f24e4
Compare
nicolo-rinaldi
force-pushed
the
DAGE-31_M3_index-doc-to-solr
branch
from
03f24e4 to
4ffff13
Compare
Now the vector field is created only when needed and the embedding dimension is detected from the first line of the doc_embedding.jsonl file
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Outdated suggestions cannot be applied.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.
Jira ticket: https://sease.atlassian.net/browse/DAGE-31
Updated the docker-related files inside solr-init/ folder to deal with the file output/embeddings/doc_embeddings.jsonland index documents’ embeddings into the solr instance. For now the embedding dimension is fixed to 10, then it needs to be changed later on when we have a complete configuration file. The folder where the file containing the embeddings is fixed. If the folder is not found, then an image creates the folder needed but empty. In this way, the code works even if the file doesn’t exists, it just index the documents without any embedding.