Open-LLM-VTuber
Replies: 1 comment
|
The part that stands out to me is "Is there anyone who made a successful connection to llama-server from llama.cpp?". That is usually where agent workflow routing starts to matter in practice, because the integration works at small scale but gets harder once real users, retries, and longer sessions show up. I would make provider/model choice explicit per agent step, then log usage and fallback reason for each tool loop. That makes it easier to move simple steps to cheaper routes while keeping stronger models for planning or final synthesis. I am testing an OpenAI-compatible multi-model API layer around official Chinese models, so this kind of agent workflow routing is directly relevant. For Open-LLM-VTuber, would routing be configured per agent role, per tool call, or dynamically from runtime signals? |
Uh oh!
There was an error while loading. Please reload this page.
I heard about Open-LLM-VTuber and decided to run it on my computer. When I tried to run and send my message, I saw error messages like below.
I changed only character_config.agent_config.agent_settings.basic_memory_agent.llm_provider to "openai_compatible_llm",
and character_config.agent_config.agent_settings.llm_configs.openai_compatible_llm like below.
And here is the verbose execution logs and error messages.
Please let me know the correct way to connect to llama-server.
All reactions