how to set Gemini 2.5 Flash-Lite llm in streaming mode or is it streaming by default

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.

where do i add this code? give me example

Here’s a friendly example to help you get started with the

chat()

method using the

gemini-2.5-flash

model to enable streaming mode:

from livekit.agents import ChatContext
from livekit.plugins import google

# Initialize the LLM with the gemini-2.5-flash model
llm = google.LLM(model="gemini-2.5-flash")

# Create a chat context and add a user message
chat_ctx = ChatContext()
chat_ctx.add_message(role="user", content="Hello, how are you today?")

# Initiate a streaming chat session
async with llm.chat(chat_ctx=chat_ctx) as stream:
    async for chunk in stream:
        if chunk.delta.content:
            print("Streaming response chunk:", chunk.delta.content)

To break it down a bit: • The

chat()

method kicks off a streaming session for you. • The

LLMStream

object you get back lets you handle response chunks as they come in, in real-time. • Just remember to initialize the LLM with the

gemini-2.5-flash

model to make this work smoothly. If anything feels unclear or you’d like me to walk you through it more, please don’t hesitate to ask. I’m here to help! Sources: livekit-plugins/livekit-plugins-google/livekit/plugins/google/beta/gemini_t... | plugins/openai/src/llm.ts | Large language model (LLM) integrations | LiveKit Docs