streaming-patterns

# ADK Streaming Patterns

Comprehensive patterns for configuring Google ADK bidi-streaming (bidirectional streaming) to build real-time, multimodal AI agents with voice, video, and streaming tool capabilities.

## Core Concepts

ADK bidi-streaming enables low-latency, bidirectional communication between users and AI agents with:

- **Real-time interaction**: Process and respond while user is still providing input
- **Natural interruption**: User can interrupt agent mid-response
- **Multimodal support**: Text, audio, and video inputs/outputs
- **Streaming tools**: Tools that yield intermediate results over time
- **Session persistence**: Maintain context across ~10-minute connection timeouts

## Quick Start Patterns

### 1. Basic Bidi-Streaming Setup

```python
from google.adk.agents import Agent
from google.adk.agents.run_config import RunConfig, StreamingMode
from google.genai import types

# Configure for audio streaming
run_config = RunConfig(
    response_modalities=["AUDIO"],
    streaming_mode=StreamingMode.BIDI
)

# Run agent with bidi-streaming
async for event in agent.run_live(request_queue, run_config=run_config):
    if event.server_content:
        # Handle streaming response
        handle_response(event)
```

### 2. LiveRequestQueue Pattern

```python
from google.adk.agents import LiveRequestQueue

# Create queue for multimodal inputs
request_queue = LiveRequestQueue()

# Enqueue text
await request_queue.put("What's the weather?")

# Enqueue audio chunks
await request_queue.put(audio_bytes)

# Signal activity boundaries
await request_queue.put(types.LiveClientRealtimeInput(
    media_chunks=[types.LiveClientRealtimeInputMediaChunk(
        data=audio_chunk
    )]
))
```

## Configuration Patterns

### Response Modalities

**CRITICAL**: Only ONE response modality per session. Cannot switch mid-session.

```python
# Audio output (voice agent)
RunConfig(response_modalities=["AUDIO"])

# Text output (chat agent)
RunConfig(response_modalities=["TEXT"])
```