custom-llm

Overview ¶

Example: Custom LLM backend integration

This example demonstrates how to: - Create a PAL with a custom LLM backend (e.g., your own OpenAI proxy) - Configure LLM layer settings (model, base URL, API key) - Create a conversation using the custom LLM PAL

This is useful when you want to: - Use your own LLM endpoint instead of Tavus's default - Implement custom logic or caching in your LLM layer - Use a different LLM provider

Run with: TAVUS_API_KEY=your-key go run main.go

Based on: github.com/Tavus-Engineering/tavus-examples/cvi-custom-llm-with-backend