GH-3786: Provide encodingFormat=base64 support for the OpenAI embedding model
#3804
+219
−1
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
…Api.Embedding` Introduce `OpenAiEmbeddingDeserializer` to handle base64-encoded embeddings returned by the model when encodingFormat=base64 is specified. Signed-off-by: Sun Yuhan <[email protected]>
Signed-off-by: Sun Yuhan <[email protected]>
sunyuhan1998
changed the title
encodingFormat=base64 support for the OpenAI embedding modelencodingFormat=base64 support for the OpenAI embedding model
sunyuhan1998
changed the title
encodingFormat=base64 support for the OpenAI embedding modelencodingFormat=base64 support for the OpenAI embedding model
|
Hi @ilayaperumalg can you help review this PR ? Thank you ! |
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Outdated suggestions cannot be applied.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.
As mentioned in the issue #3786 , when using embedding models, we need to support the
encodingFormat=base64parameter. When this format is used, the model returns theembeddingfield as a base64-encoded string representing a float array. This PR adds support for handling that format.Changes in this PR:
OpenAiEmbeddingDeserializer, for theembeddingfield inorg.springframework.ai.openai.api.OpenAiApi.Embedding. This deserializer automatically converts the base64-encoded string back into a float array when parsing the API response.Fixes: #3786