fix: allow configuring embeddings encoding format - #322
Open
sergicasau wants to merge 2 commits into
Open
sergicasau wants to merge 2 commits into
sergicasau wants to merge 2 commits into
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
When using IONOS as an OpenAI-compatible embeddings provider, the OpenAI SDK sends
encoding_format: "base64"by default.IONOS cannot process this format correctly and returns an error because an embedding encoded as Base64 cannot be unmarshalled into the expected float array.
Setting
RAG_CHECK_EMBEDDING_CTX_LENGTH=falsefixes the input format, but does not change the embedding response format.Solution
This PR adds the optional
EMBEDDINGS_ENCODING_FORMATenvironment variable and forwards it throughmodel_kwargstoOpenAIEmbeddingsandAzureOpenAIEmbeddings.For IONOS, it can be configured as:
This follows the approach discussed by @metbosch in #163 (comment).
Related to #163.