When I trigger a dispatch request, sometimes it ta...
# ask-ai
b
When I trigger a dispatch request, sometimes it takes a lot for the call to get triggered? How can I improve that?
t
Thanks for reaching out, Harsh. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
To improve the speed of call triggering after a dispatch request in LiveKit, consider the following strategies: • Explicit Agent Dispatch During Token Generation: Dispatch the agent when generating the token so both user and agent connect simultaneously, reducing connection time. • Optimize Server Configuration: Ensure your server has adequate resources and avoid running other applications on the same server. Use multiple servers per agent along with load balancing and auto-scaling based on production guidelines. • Network and Latency Management: Configure network settings to reduce latency, including setting appropriate ping intervals and timeouts. • Implement Connection Indicators: Provide users with clear connection status updates to better manage expectations and perceived responsiveness. Applying these methods can help decrease the delay and improve overall reliability of dispatch calls. Sources: Web and mobile frontends | LiveKit Docs | How to Get Help from LiveKit | tests/test_llm.py