Add rate limiting configuration for LLM providers

[hoangnb24]

• Introduce rate limit parameters (requests/sec and max bucket size) for all LLM providers
• Update webui.py to include new rate limit inputs in UI and function signatures
• Modify utils.py to create InMemoryRateLimiter for each LLM provider
• Add rate limiter configuration to all supported LLM models

[CLAassistant]

All committers have signed the CLA.