add readme

Author: tschellenbach

plugins/aws/README.md

@@ -0,0 +1,43 @@
+# AWS Plugin for Vision Agents
+
+AWS (Bedrock) LLM integration for Vision Agents framework with support for both standard and realtime interactions.
+
+## Installation
+
+```bash
+pip install vision-agents-plugins-aws
+```
+
+## Usage
+
+### Standard LLM Usage
+
+This example shows how to use qwen3 on bedrock for the LLM.
+
+```python
+agent = Agent(
+    edge=getstream.Edge(),
+    agent_user=User(name="Friendly AI"),
+    instructions="Be nice to the user",
+    llm=aws.LLM(model="qwen.qwen3-32b-v1:0"),
+    tts=cartesia.TTS(),
+    stt=deepgram.STT(),
+    turn_detection=smart_turn.TurnDetection(buffer_duration=2.0, confidence_threshold=0.5),
+)
+```
+
+The full example is available in example/aws_qwen_example.py
+
+### Realtime Text/Image Usage
+
+Nova sonic audio realtime STS is also supported:
+
+```python    
+agent = Agent(
+    edge=getstream.Edge(),
+    agent_user=User(name="Story Teller AI"),
+    instructions="Tell a story suitable for a 7 year old about a dragon and a princess",
+    llm=aws.Realtime(),
+)
+```
+

plugins/aws/example/.env.example

@@ -0,0 +1,7 @@
+# Stream API credentials
+STREAM_API_KEY=your_stream_api_key_here
+STREAM_API_SECRET=your_stream_api_secret_here
+EXAMPLE_BASE_URL=https://pronto.getstream.io
+
+# Deepgram API credentials
+DEEPGRAM_API_KEY=your_deepgram_api_key_here

plugins/aws/example/__init__.py

@@ -0,0 +1,40 @@
+import asyncio
+import logging
+from uuid import uuid4
+
+from dotenv import load_dotenv
+
+from vision_agents.core import User
+from vision_agents.core.agents import Agent
+from vision_agents.plugins import aws, getstream, cartesia, deepgram, smart_turn
+
+load_dotenv()
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s [call_id=%(call_id)s] %(name)s: %(message)s")
+logger = logging.getLogger(__name__)
+
+
+async def start_agent() -> None:
+    agent = Agent(
+        edge=getstream.Edge(),
+        agent_user=User(name="Friendly AI"),
+        instructions="Be nice to the user",
+        llm=aws.LLM(model="qwen.qwen3-32b-v1:0"),
+        tts=cartesia.TTS(),
+        stt=deepgram.STT(),
+        turn_detection=smart_turn.TurnDetection(buffer_duration=2.0, confidence_threshold=0.5),
+        # Enable turn detection with FAL/ Smart turn
+    )
+    await agent.create_user()
+
+    call = agent.edge.client.video.call("default", str(uuid4()))
+    await agent.edge.open_demo(call)
+
+    with await agent.join(call):
+        await asyncio.sleep(5)
+        await agent.llm.simple_response(text="Say hi")
+        await agent.finish()
+
+
+if __name__ == "__main__":
+    asyncio.run(start_agent())

plugins/aws/example/aws_qwen_example.py

@@ -0,0 +1,36 @@
+import asyncio
+import logging
+from uuid import uuid4
+
+from dotenv import load_dotenv
+
+from vision_agents.core import User
+from vision_agents.core.agents import Agent
+from vision_agents.plugins import aws, getstream
+
+load_dotenv()
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s [call_id=%(call_id)s] %(name)s: %(message)s")
+logger = logging.getLogger(__name__)
+
+
+async def start_agent() -> None:
+    agent = Agent(
+        edge=getstream.Edge(),
+        agent_user=User(name="Story Teller AI"),
+        instructions="Tell a story suitable for a 7 year old about a dragon and a princess",
+        llm=aws.Realtime(),
+    )
+    await agent.create_user()
+
+    call = agent.edge.client.video.call("default", str(uuid4()))
+    await agent.edge.open_demo(call)
+
+    with await agent.join(call):
+        await asyncio.sleep(5)
+        await agent.llm.simple_response(text="Say hi and start the story")
+        await agent.finish()
+
+
+if __name__ == "__main__":
+    asyncio.run(start_agent())

plugins/aws/example/aws_realtime_nova_example.py

@@ -0,0 +1,22 @@
+[project]
+name = "gemini-live-realtime-example"
+version = "0.0.0"
+requires-python = ">=3.10"
+
+# put only what this example needs
+dependencies = [
+  "python-dotenv>=1.0",
+  "vision-agents-plugins-gemini",
+  "vision-agents-plugins-getstream",
+  "vision-agents",
+  "google-genai>=1.33.0",
+  "opentelemetry-exporter-otlp>=1.37.0",
+  "opentelemetry-exporter-prometheus>=0.58b0",
+  "prometheus-client>=0.23.1",
+  "opentelemetry-sdk>=1.37.0",
+]
+
+[tool.uv.sources]
+"vision-agents-plugins-getstream" = {path = "../../../plugins/getstream", editable=true}
+"vision-agents-plugins-gemini" = {path = "../../../plugins/gemini", editable=true}
+"vision-agents" = {path = "../../../agents-core", editable=true}

plugins/aws/example/pyproject.toml

@@ -0,0 +1,41 @@
+[build-system]
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+[project]
+name = "vision-agents-plugins-aws"
+dynamic = ["version"]
+description = "AWS (Bedrock) LLM integration for Vision Agents"
+readme = "README.md"
+keywords = ["aws", "bedrock", "LLM", "AI", "voice agents", "agents"]
+requires-python = ">=3.12"
+license = "MIT"
+dependencies = [
+    "vision-agents",
+    "boto3>=1.28.0",
+    "aws-sdk-bedrock-runtime>=0.1.0",
+]
+
+[project.urls]
+Documentation = "https://visionagents.ai/"
+Website = "https://visionagents.ai/"
+Source = "https://github.com/GetStream/Vision-Agents"
+
+[tool.hatch.version]
+source = "vcs"
+raw-options = { root = "..", search_parent_directories = true, fallback_version = "0.0.0" }
+
+[tool.hatch.build.targets.wheel]
+packages = ["."]
+
+[tool.hatch.build.targets.sdist]
+include = ["/vision_agents"]
+
+[tool.uv.sources]
+vision-agents = { workspace = true }
+
+[dependency-groups]
+dev = [
+    "pytest>=8.4.1",
+    "pytest-asyncio>=1.0.0",
+]