⚡ Optimize HuggingFaceEmbeddings initialization with caching

[Kshitij-KS]

💡 What: Added @functools.lru_cache() to get_embedding_function in both createDatabase.py and query.py.
🎯 Why: The initialization of HuggingFaceEmbeddings (loading the sentence-transformer model) is a computationally expensive and time-consuming operation. By caching the output of get_embedding_function, we ensure that the model is only loaded once per process execution.
📊 Measured Improvement: Since the actual dependencies were not available in the sandbox environment, I established a baseline using a synthetic benchmark that mocked the HuggingFaceEmbeddings initialization with a 1-second delay.

• Baseline: 5.00 seconds for 5 calls.
• After Optimization: 1.00 second for 5 calls.
• Result: ~80% reduction in total time for 5 calls in the benchmark scenario. In real-world usage, this prevents redundant model loads into memory.

---

PR created automatically by Jules for task 4129824360451056911 started by @Kshitij-KS

[google-labs-jules]

👋 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 @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.