feat: add jina emb #50
Merged
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
Signed-off-by: Keming <[email protected]>
Signed-off-by: Keming <[email protected]>
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR adds support for Jina AI embeddings by introducing new provider and model classes, integrating them into the existing pipeline, and defining a rate limit constant.
- Adds
JINA_EMBEDDING_RPSconstant and removes redundantSelffallbacks in utils and spec modules. - Introduces
JinaEmbeddingProvider,JinaDenseEmbedding, and corresponding msgspec request/response types. - Updates pipeline registration, model exports, error definitions, and documentation to include Jina.
Reviewed Changes
Copilot reviewed 11 out of 11 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| vechord/utils.py | Added JINA_EMBEDDING_RPS constant; unified Self import. |
| vechord/typing.py | New module exporting Self. |
| vechord/spec.py | Replaced inline Self fallback with import. |
| vechord/provider.py | Added JinaEmbeddingProvider and updated imports. |
| vechord/pipeline.py | Registered JinaDenseEmbedding in embedding factory. |
| vechord/model/jina.py | Defined Jina-specific msgspec structs and response handling. |
| vechord/model/gemini.py | Added return type hints and clarified docstrings on class methods. |
| vechord/model/init.py | Exposed JinaEmbeddingRequest and JinaEmbeddingResponse. |
| vechord/errors.py | Introduced UnexpectedResponseError. |
| vechord/embedding.py | Added JinaDenseEmbedding implementation and imports. |
| docs/source/utils.md | Documented JinaDenseEmbedding and fixed Co-here reranker description. |
Comments suppressed due to low confidence (4)
docs/source/utils.md:30
- The indentation for the CohereReranker bullet is misaligned. Align it with the other list items to ensure correct rendering in the docs.
- {py:class}`~vechord.rerank.CohereReranker`: Cohere reranker
vechord/provider.py:110
- Add unit tests to cover
JinaEmbeddingProvider.query(success and error paths) to ensure expected behavior and proper error handling.
class JinaEmbeddingProvider(BaseProvider):
vechord/model/jina.py:56
- [nitpick] The error message 'empty embedding data' is quite generic. Consider including context (e.g., 'Jina embedding response contains no data') to aid in debugging.
raise UnexpectedResponseError("empty embedding data")
vechord/model/gemini.py:135
- The docstring says 'first embedding' but this method returns the full embedding array. Update it to accurately describe the behavior (e.g., 'Get the embedding as a numpy array').
"""Get the first embedding as a numpy array."""
Co-authored-by: Copilot <[email protected]> Signed-off-by: Keming <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
No description provided.