This question originally came up in our Slack community and the thread has been consolidated here for long-term reference.
How do I give max tokens in the OpenAI Realtime model?
This question originally came up in our Slack community and the thread has been consolidated here for long-term reference.
How do I give max tokens in the OpenAI Realtime model?
Use update_options on the model:
llm_model = openai.realtime.RealtimeModel()
llm_model.update_options(max_response_output_tokens=500)
session = AgentSession(
llm=llm_model,
vad=silero.VAD.load()
)