⚡ Bolt: Reuse Gemini client to save ~400ms per request#26
⚡ Bolt: Reuse Gemini client to save ~400ms per request#26suvadityamuk wants to merge 1 commit intomainfrom
Conversation
Instantiates `google.genai.Client` once in `operators.py` and passes it to `utils.py` functions, eliminating ~400ms of overhead (5 instantiations x ~80ms) per generation request. - Updated `utils.refine_prompt` and `utils.generate_image` to accept a client instance. - Updated `operators.py` to create the client once and pass it down. - Added performance note in code. Co-authored-by: suvadityamuk <70141886+suvadityamuk@users.noreply.github.com>
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
|
🤖 Hi @suvadityamuk, I've received your request, and I'm working on it now! You can track my progress in the logs for more details. |
Summary of ChangesHello @suvadityamuk, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly enhances the performance of the generation pipeline by optimizing the instantiation of the Highlights
Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
There was a problem hiding this comment.
The Pull Request successfully optimizes the Gemini generation pipeline by reusing the genai.Client instance across multiple API calls. This architectural change eliminates approximately 400ms of latency per request, directly improving the responsiveness of the 3D generation process.
🔍 General Feedback
- Efficiency: The consolidation of client instantiation is a significant win for performance, especially in a Blender add-on where responsiveness is key.
- Maintainability: Adopting dependency injection for the Gemini client makes the code more modular and easier to test in the future.
- Documentation: While the changes are clear, minor enhancements to docstrings could help keep the documentation in sync with the new function signatures.
|
|
||
|
|
||
| def refine_prompt(api_key, prompt): | ||
| def refine_prompt(client, prompt): |
There was a problem hiding this comment.
|
|
||
|
|
||
| def generate_image(api_key, prompt, output_path, input_image_path=None): | ||
| def generate_image(client, prompt, output_path, input_image_path=None): |
There was a problem hiding this comment.
| def _run_pipeline(self, gemini_key, meshy_key, prompt, q): | ||
| try: | ||
| # ⚡ Bolt: Create client once and reuse to avoid instantiation overhead (~80ms per call) | ||
| client = utils.get_client(gemini_key) |
There was a problem hiding this comment.
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request effectively addresses a performance bottleneck by reusing the google.genai.Client instance across multiple API calls, saving significant time on each request. The implementation correctly uses dependency injection by creating the client once and passing it to the helper functions. The changes are clear, well-motivated, and a great optimization. I have a couple of suggestions to improve the maintainability of the updated function signatures by adding type hints.
|
|
||
|
|
||
| def refine_prompt(api_key, prompt): | ||
| def refine_prompt(client, prompt): |
There was a problem hiding this comment.
For better code clarity and maintainability, please add type hints to this function signature. The type of the new client parameter is not obvious, and a hint would help developers understand what object is expected without tracing its origin. This follows the best practices outlined in PEP 484 for improving static analysis and code readability.
| def refine_prompt(client, prompt): | |
| def refine_prompt(client: "genai.Client", prompt: str) -> str: |
|
|
||
|
|
||
| def generate_image(api_key, prompt, output_path, input_image_path=None): | ||
| def generate_image(client, prompt, output_path, input_image_path=None): |
There was a problem hiding this comment.
Similar to refine_prompt, please add type hints to this function's signature. This makes the function easier to use correctly, especially with the new client parameter, and improves overall code quality and maintainability as recommended by PEP 484.
| def generate_image(client, prompt, output_path, input_image_path=None): | |
| def generate_image(client: "genai.Client", prompt: str, output_path: str, input_image_path: str | None = None) -> str: |
1 participant
💡 What: Refactored the generation pipeline to instantiate the
google.genai.Clientonce and reuse it across multiple API calls, instead of creating a new client for each call.🎯 Why: Benchmarking revealed that instantiating
google.genai.Clienttakes approximately 80ms. The original implementation instantiated the client 5 times (1 for prompt refinement + 4 for view generation), adding ~400ms of avoidable latency to every generation request.📊 Impact: Reduces the total pipeline execution time by ~400ms. This is a pure overhead reduction that makes the UI feel more responsive and reduces unnecessary object creation.
🔬 Measurement: Confirmed via
benchmark_overhead.pywhich showed a reduction from ~447ms to ~83ms for client overhead in the simulated pipeline.PR created automatically by Jules for task 10245002133299409996 started by @suvadityamuk