Skip to content

fix: propagate local files only and specific model path into embed pa… #524

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
joein merged 1 commit into from
May 20, 2025
Merged

fix: propagate local files only and specific model path into embed pa… #524

joein merged 1 commit into from
May 20, 2025

Conversation

@joein
Copy link
Member

@joein joein commented May 19, 2025

@coderabbitai
Copy link

coderabbitai bot commented May 19, 2025 •
edited
Loading

📝 Walkthrough

Walkthrough

The changes across multiple modules introduce consistent handling and propagation of the specific_model_path and local_files_only parameters throughout the model initialization, embedding, and reranking workflows. Constructors for various embedding and reranking classes now store specific_model_path as a private or instance attribute, which is then used in downstream method calls such as model downloading and embedding routines. Corresponding internal methods for embedding documents, images, and reranking pairs have updated signatures to accept these parameters and ensure they are passed to parallel worker pools where applicable. Additionally, an unused import of numpy was removed from one file. No core logic or control flow was altered beyond parameter management.

Note

⚡️ AI Code Reviews for VS Code, Cursor, Windsurf

CodeRabbit now has a plugin for VS Code, Cursor and Windsurf. This brings AI code reviews directly in the code editor. Each commit is reviewed immediately, finding bugs before the PR is raised. Seamless context handoff to your AI code agent ensures that you can easily incorporate review feedback.
Learn more here.

Note

⚡️ Faster reviews with caching

CodeRabbit now supports caching for code and dependencies, helping speed up reviews. This means quicker feedback, reduced wait times, and a smoother review experience overall. Cached data is encrypted and stored securely. This feature will be automatically enabled for all accounts on May 16th. To opt out, configure Review - Disable Cache at either the organization or repository level. If you prefer to disable all data retention across your organization, simply turn off the Data Retention setting under your Organization Settings.
Enjoy the performance boost—your workflow just got faster.

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 4e5575f and 95d166f.

📒 Files selected for processing (14)
  • fastembed/image/onnx_embedding.py (2 hunks)
  • fastembed/image/onnx_image_model.py (2 hunks)
  • fastembed/late_interaction/colbert.py (2 hunks)
  • fastembed/late_interaction/token_embeddings.py (1 hunks)
  • fastembed/late_interaction_multimodal/colpali.py (3 hunks)
  • fastembed/late_interaction_multimodal/onnx_multimodal_model.py (4 hunks)
  • fastembed/rerank/cross_encoder/onnx_text_cross_encoder.py (2 hunks)
  • fastembed/rerank/cross_encoder/onnx_text_model.py (2 hunks)
  • fastembed/sparse/bm25.py (4 hunks)
  • fastembed/sparse/bm42.py (2 hunks)
  • fastembed/sparse/minicoil.py (3 hunks)
  • fastembed/sparse/splade_pp.py (2 hunks)
  • fastembed/text/onnx_embedding.py (2 hunks)
  • fastembed/text/onnx_text_model.py (2 hunks)
🧰 Additional context used
🧬 Code Graph Analysis (9)
fastembed/sparse/splade_pp.py (1)
fastembed/common/model_management.py (1)
  • download_model (378-458)
fastembed/late_interaction_multimodal/colpali.py (1)
fastembed/common/model_management.py (1)
  • download_model (378-458)
fastembed/sparse/minicoil.py (1)
fastembed/common/model_management.py (1)
  • download_model (378-458)
fastembed/late_interaction/colbert.py (1)
fastembed/common/model_management.py (1)
  • download_model (378-458)
fastembed/rerank/cross_encoder/onnx_text_cross_encoder.py (1)
fastembed/common/model_management.py (1)
  • download_model (378-458)
fastembed/sparse/bm42.py (1)
fastembed/common/model_management.py (1)
  • download_model (378-458)
fastembed/image/onnx_embedding.py (1)
fastembed/common/model_management.py (1)
  • download_model (378-458)
fastembed/text/onnx_embedding.py (1)
fastembed/common/model_management.py (1)
  • download_model (378-458)
fastembed/sparse/bm25.py (1)
fastembed/common/model_management.py (1)
  • download_model (378-458)
⏰ Context from checks skipped due to timeout of 90000ms (15)
  • GitHub Check: Python 3.13.x on ubuntu-latest test
  • GitHub Check: Python 3.11.x on windows-latest test
  • GitHub Check: Python 3.12.x on macos-latest test
  • GitHub Check: Python 3.11.x on macos-latest test
  • GitHub Check: Python 3.13.x on macos-latest test
  • GitHub Check: Python 3.12.x on windows-latest test
  • GitHub Check: Python 3.13.x on windows-latest test
  • GitHub Check: Python 3.12.x on ubuntu-latest test
  • GitHub Check: Python 3.11.x on ubuntu-latest test
  • GitHub Check: Python 3.10.x on windows-latest test
  • GitHub Check: Python 3.10.x on macos-latest test
  • GitHub Check: Python 3.9.x on windows-latest test
  • GitHub Check: Python 3.10.x on ubuntu-latest test
  • GitHub Check: Python 3.9.x on macos-latest test
  • GitHub Check: Python 3.9.x on ubuntu-latest test
🔇 Additional comments (42)
fastembed/late_interaction/token_embeddings.py (1)

12-12: Unused import removed.

Removing the unused numpy import keeps the code clean and reduces unnecessary imports.

fastembed/sparse/splade_pp.py (3)

117-117: Store specific_model_path as instance variable.

This stores the specific_model_path parameter as an instance variable, allowing it to be consistently referenced across methods.

122-122: Pass stored specific_model_path to download_model.

Correctly passes the instance variable to download_model, ensuring consistent parameter handling during model initialization.

169-170: Propagate local_files_only and specific_model_path to embed method.

Ensures that both parameters are passed to the embedding method, maintaining consistent behavior throughout the embedding workflow.

fastembed/late_interaction_multimodal/colpali.py (4)

98-98: Store specific_model_path as instance variable.

This change stores the specific_model_path parameter as an instance variable, following the same pattern used in other embedding classes.

103-103: Pass stored specific_model_path to download_model.

Correctly passes the instance variable to the download_model method, ensuring that the specific model path is used during model initialization.

239-240: Propagate parameters to text embedding method.

Ensures that both local_files_only and specific_model_path parameters are consistently passed to the text embedding method.

274-275: Propagate parameters to image embedding method.

Similarly ensures that both parameters are passed to the image embedding method, maintaining consistent behavior for all embedding types.

fastembed/sparse/minicoil.py (4)

130-130: Store specific_model_path as instance variable.

This change follows the consistent pattern of storing the parameter as an instance variable for later use.

135-135: Pass stored specific_model_path to download_model.

Ensures the specific model path is used during model initialization if provided.

215-217: Propagate parameters to embed method.

Correctly passes both local_files_only and specific_model_path to the document embedding method.

237-239: Propagate parameters to query_embed method.

Similarly ensures the parameters are passed to the query embedding method, maintaining consistent behavior across all embedding workflows.

fastembed/text/onnx_embedding.py (3)

250-250: Proper state encapsulation for model path parameter.

The addition of instance attribute _specific_model_path properly stores the constructor parameter, ensuring consistent state management throughout the object's lifecycle.

255-255: Consistent usage of stored model path.

Using the instance attribute _specific_model_path rather than directly accessing the constructor parameter ensures state consistency and proper encapsulation.

292-293: Proper parameter propagation to embedding process.

Adding local_files_only and specific_model_path parameters to the _embed_documents call ensures these important configuration options are consistently propagated to worker processes during parallel embedding operations.

fastembed/late_interaction/colbert.py (3)

172-172: Proper state encapsulation for model path parameter.

The addition of instance attribute _specific_model_path properly stores the constructor parameter, ensuring consistent state management throughout the object's lifecycle.

177-177: Consistent usage of stored model path.

Using the instance attribute _specific_model_path rather than directly accessing the constructor parameter ensures state consistency and proper encapsulation.

237-238: Proper parameter propagation to embedding process.

Adding local_files_only and specific_model_path parameters to the _embed_documents call ensures these important configuration options are consistently propagated to worker processes during parallel embedding operations.

fastembed/sparse/bm42.py (3)

113-113: Proper state encapsulation for model path parameter.

The addition of instance attribute _specific_model_path properly stores the constructor parameter, ensuring consistent state management throughout the object's lifecycle.

118-118: Consistent usage of stored model path.

Using the instance attribute _specific_model_path rather than directly accessing the constructor parameter ensures state consistency and proper encapsulation.

305-306: Proper parameter propagation to embedding process.

Adding local_files_only and specific_model_path parameters to the _embed_documents call ensures these important configuration options are consistently propagated to worker processes during parallel embedding operations.

fastembed/image/onnx_embedding.py (3)

115-115: Proper state encapsulation for model path parameter.

The addition of instance attribute _specific_model_path properly stores the constructor parameter, ensuring consistent state management throughout the object's lifecycle.

120-120: Consistent usage of stored model path.

Using the instance attribute _specific_model_path rather than directly accessing the constructor parameter ensures state consistency and proper encapsulation.

181-182: Proper parameter propagation to image embedding process.

Adding local_files_only and specific_model_path parameters to the _embed_images call ensures these important configuration options are consistently propagated to worker processes during parallel image embedding operations.

fastembed/text/onnx_text_model.py (2)

111-112: Parameter signature extended appropriately

The addition of local_files_only and specific_model_path parameters extends the method signature to support more flexible model loading options, enabling users to specify a custom model path or restrict to using only local files.

141-142: Parameters correctly propagated to worker pool

These parameters are correctly passed to the worker pool, ensuring that parallel processing respects the same model loading options specified by the user.

fastembed/rerank/cross_encoder/onnx_text_cross_encoder.py (3)

134-134: Instance variable for specific_model_path properly stored

The specific model path is now correctly stored as an instance variable, ensuring it's available throughout the object's lifecycle.

139-139: Model path properly passed to download_model

The specific model path is correctly passed to the download_model method, allowing it to bypass downloading when a specific path is provided.

193-194: Parameters correctly propagated to _rerank_pairs

Both local_files_only and specific_model_path parameters are now correctly passed to the underlying _rerank_pairs method, ensuring consistent behavior across the embedding pipeline.

fastembed/rerank/cross_encoder/onnx_text_model.py (2)

97-98: Parameter signature extended appropriately

The addition of local_files_only and specific_model_path parameters to _rerank_pairs aligns with the pattern used in other embedding methods, providing consistent options for model loading.

125-126: Parameters correctly propagated to worker pool

These parameters are correctly included in the params dictionary passed to the worker pool, ensuring consistent model loading behavior in parallel processing contexts.

fastembed/image/onnx_image_model.py (2)

100-101: Parameter signature extended appropriately

The _embed_images method signature is consistently extended with the same parameters as other embedding methods, maintaining a uniform API across text and image embedding functions.

128-129: Parameters correctly propagated to worker pool

The parameters are correctly included in the worker pool configuration, ensuring parallel image embedding tasks respect the model loading preferences.

fastembed/sparse/bm25.py (5)

118-118: Good addition of instance variable for model path.

Storing specific_model_path as an instance variable allows it to be used consistently throughout the class methods.

123-123: Correct propagation to download_model.

Passing the stored _specific_model_path to the download_model method ensures the specific path is used when loading the model.

164-165: Parameter addition to _embed_documents signature is correct.

Adding local_files_only and specific_model_path parameters to the method signature is necessary for propagation to worker pools.

194-195: Proper parameter propagation to worker pool.

The parameters are correctly added to the params dictionary that's passed to the parallel worker pool, ensuring workers have access to these configuration options.

234-235: Complete parameter forwarding in embed method.

The stored instance variables are properly forwarded to the _embed_documents method, completing the propagation chain from constructor to worker pools.

fastembed/late_interaction_multimodal/onnx_multimodal_model.py (4)

123-124: Appropriate parameter addition to text embedding method.

Adding local_files_only and specific_model_path parameters with default values to the method signature ensures compatibility with the parameter propagation pattern.

151-152: Correct parameter propagation to text embedding worker pool.

Adding these parameters to the params dictionary ensures they're properly passed to the text embedding workers.

190-191: Consistent parameter handling for image embedding.

The same parameters are added to the _embed_images method, maintaining consistency between text and image embedding workflows.

218-219: Complete parameter propagation to image embedding worker pool.

The parameters are correctly added to the image embedding worker pool configuration, ensuring consistent behavior across all embedding types.

✨ Finishing Touches
  • 📝 Docstrings were successfully generated. (🔄 Check again to generate docstrings again)

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

coderabbitai bot added a commit that referenced this pull request May 19, 2025
@coderabbitai
📝 Add docstrings to fix-no-internet-embed-parallel
14eddad 
Docstrings generation was requested by @joein.

* #524 (comment)

The following files were modified:

* `fastembed/image/onnx_embedding.py`
* `fastembed/image/onnx_image_model.py`
* `fastembed/late_interaction/colbert.py`
* `fastembed/late_interaction_multimodal/colpali.py`
* `fastembed/late_interaction_multimodal/onnx_multimodal_model.py`
* `fastembed/rerank/cross_encoder/onnx_text_cross_encoder.py`
* `fastembed/rerank/cross_encoder/onnx_text_model.py`
* `fastembed/sparse/bm25.py`
* `fastembed/sparse/bm42.py`
* `fastembed/sparse/minicoil.py`
* `fastembed/sparse/splade_pp.py`
* `fastembed/text/onnx_embedding.py`
* `fastembed/text/onnx_text_model.py`
@coderabbitai coderabbitai bot mentioned this pull request May 19, 2025
Open
@coderabbitai
Copy link

coderabbitai bot commented May 19, 2025

Note

Generated docstrings for this pull request at #525

@joein joein merged commit a260022 into main May 20, 2025
28 checks passed
@joein joein deleted the fix-no-internet-embed-parallel branch May 20, 2025 10:46
This was referenced Nov 10, 2025
Closed
Merged
@coderabbitai coderabbitai bot mentioned this pull request Dec 1, 2025
Merged
@coderabbitai coderabbitai bot mentioned this pull request Jan 2, 2026
Open
9 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@generall generall generall approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@joein @generall