Building a Multimodal Agent with the ADK, Azure ACI, and Gemini Flash Live 3.1

--- title: Building a Multimodal Agent with the ADK, Azure ACI, and Gemini Flash Live 3.1 published: true series: Azure date: 2026-04-18 03:07:51 UTC tags: geminilive,azureaci,geminicli,appagent canonical_url: https://xbill999.medium.com/building-a-multimodal-agent-with-the-adk-azure-aci-and-gemini-flash-live-3-1-3780bd476f3c --- Leveraging the Google Agent Development Kit (ADK) and the underlying Gemini LLM to build Agentic apps using the Gemini Live API with the Python programming language deployed to Azure Container Instances.  #### Aren’t There a Billion Python ADK Demos? Yes there are. Python has traditionally been the main coding language for ML and AI tools. The goal of this article is to provide a minimal viable basic working ADK streaming multi-modal agent using the latest Gemini Live Models. #### In the Spirit of Mr. McConaughey’s “alright, alright, alright” So what is different about this lab compared to all the others out there? This is one of the first implementations of the latest Gemini 3.1 Flash Live Model with the Agent Development Kit (ADK). The starting point for the demo was an existing Code lab- which was updated and re-engineered with Gemini CLI. The original Codelab- is here: [Way Back Home - Building an ADK Bi-Directional Streaming Agent | Google Codelabs](https://codelabs.developers.google.com/way-back-home-level-3/instructions#0) #### What Is Python? Python is an interpreted language that allows for rapid development and testing and has deep libraries for working with ML and AI: [Welcome to Python.org](https://www.python.org/) #### Python Version Management One of the downsides of the wide deployment of Python has been managing the language versions across platforms and maintaining a supported version. The **pyenv** tool enables deploying consistent versions of Python: [GitHub - pyenv/pyenv: Simple Python version management](https://github.com/pyenv/pyenv) As of writing — the mainstream python version is 3.13. To validate your current Python: ```console python --version Python 3.13.12 ``` #### Azure Container Instances [Azure Container Instances](https://www.google.com/search?q=Azure+Container+Instances&sca_esv=9e0af5be28576de2&rlz=1CAIWTJ_enUS1110&sxsrf=ANbL-n7o0MyASoiBM0kA0-E5qMMzLudrbw%3A1775144526115&ei=To7OadXFBoOYptQP9JuB0A8&biw=1396&bih=632&ved=2ahUKEwiIvt3awM-TAxUolYkEHTTxLJIQgK4QegYIAQgAEAM&uact=5&oq=azure+aci&gs_lp=Egxnd3Mtd2l6LXNlcnAiCWF6dXJlIGFjaTIKECMYgAQYJxiKBTILEAAYgAQYkQIYigUyBRAAGIAEMgcQABiABBgKMgUQABiABDIFEAAYgAQyBRAAGIAEMgYQABgWGB4yBhAAGBYYHjIGEAAYFhgeSOwPUABY2gxwAHgBkAEAmAGVAaABqQmqAQMwLjm4AQPIAQD4AQGYAgmgAvYJwgIKEAAYgAQYQxiKBcICDhAAGIAEGLEDGIMBGIoFwgIREC4YgAQYsQMY0QMYgwEYxwHCAhAQABiABBixAxhDGIMBGIoFwgILEC4YgAQYxwEYrwHCAg0QABiABBixAxhDGIoFwgIIEAAYgAQYsQPCAgsQABiABBixAxiDAZgDAJIHAzAuOaAHsFWyBwMwLjm4B_YJwgcFMi04LjHIBzuACAA&sclient=gws-wiz-serp) (ACI) is a serverless, managed service that allows you to run Docker containers in the cloud without managing virtual machines. It is ideal for rapid deployment, bursting, and simple, isolated applications, offering per-second billing and quick startup times. ACI supports Linux and Windows containers, with options for volume mounting and GPU resources. More details are available here: [https://azure.microsoft.com/en-us/products/container-instances](https://azure.microsoft.com/en-us/products/container-instances)  #### Why would I want Gemini CLI with Azure? Isn’t that a Google Thing? Yes- Gemini CLI leverages the Google Cloud console and Gemini models but it is also open source and platform agnostic. Many applications are already cross-cloud so this enables familiar tools to be run natively on Microsoft Azure. #### Azure Container Instance Configuration To configure your Azure Service with the base system tools- this article provides a reference: [MCP Development with Python, and the Azure Container Instance](https://xbill999.medium.com/mcp-development-with-python-and-the-azure-container-instance-2b7e7bbcdcfe) #### Gemini Live Models Gemini Live is a conversational AI feature from Google that enables free-flowing, real-time voice, video, and screen-sharing interactions, allowing you to brainstorm, learn, or problem-solve through natural dialogue. Powered by the **Gemini 3.1 Flash Live model** , it provides low-latency, human-like, and emotionally aware speech in over 200 countries. More details are available here: [Gemini 3.1 Flash Live Preview | Gemini API | Google AI for Developers](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-live-preview) The Gemini Live Models bring unique real-time capabilities than can be used directly from an Agent. A summary of the model is also available here: ```plaintext https://deepmind.google/models/model-cards/gemini-3-1-flash-live/ ```  #### Gemini CLI If not pre-installed you can download the Gemini CLI to interact with the source files and provide real-time assistance: ```console npm install -g @google/gemini-cli ``` #### Testing the Gemini CLI Environment Once you have all the tools and the correct Node.js version in place- you can test the startup of Gemini CLI. You will need to authenticate with a Key or your Google Account: ```plaintext ▝▜▄ Gemini CLI v0.33.1 ▝▜▄ ▗▟▀ Logged in with Google /auth ▝▀ Gemini Code Assist Standard /upgrade no sandbox (see /docs) /model Auto (Gemini 3) | 239.8 MB ``` #### Node Version Management Gemini CLI needs a consistent, up to date version of Node. The **nvm** command can be used to get a standard Node environment: [GitHub - nvm-sh/nvm: Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions](https://github.com/nvm-sh/nvm) #### Agent Development Kit The [Google Agent Development Kit](https://www.google.com/search?q=Google+Agent+Development+Kit&rlz=1CAIWTJ_enUS1114&oq=what+is+the+adk+google&gs_lcrp=EgZjaHJvbWUyBggAEEUYOTIICAEQABgWGB4yCAgCEAAYFhgeMggIAxAAGBYYHjIICAQQABgWGB4yCAgFEAAYFhgeMggIBhAAGBYYHjIKCAcQABgKGBYYHjINCAgQABiGAxiABBiKBTIKCAkQABiABBiiBNIBCDMxODlqMGo3qAIAsAIA&sourceid=chrome&ie=UTF-8&mstk=AUtExfB5Oo7ZHHcDEHu7aqZiPBA2l1c-QGh5dB7xkkDPIiYcn8O1Imt2IHNR7bzA6JnyDCSDCUGpGWTeBW14namlN_QqzJLLI5-px1BE9jfSxwli6njPDPERjm5pRqNP3uC6HhUKiRcTJ1T8x5LHQrCkVxylw7QWg0N8B4dQDIcWpnVX9Gc&csui=3&ved=2ahUKEwjYu-G8p-uSAxXrv4kEHUbpLo0QgK4QegQIARAB) (ADK) is an open-source, Python-based framework designed to streamline the creation, deployment, and orchestration of sophisticated, multi-agent AI systems. It treats agent development like software engineering, offering modularity, state management, and built-in tools (like Google Search) to build autonomous agents. The ADK can be installed from here: [Agent Development Kit (ADK)](https://google.github.io/adk-docs/) #### Where do I start? The strategy for starting multimodal real time agent development is a incremental step by step approach. First, the basic development environment is setup with the required system variables, and a working Gemini CLI configuration. Then, a minimal ADK Agent is built and tested locally. Next — the entire solution is deployed to Azure ACA. #### Setup the Basic Environment At this point you should have a working Python environment and a working Gemini CLI installation. All of the relevant code examples and documentation is available in GitHub. This repo has a wide variety of samples- but this lab will focus on the ‘level\_3-gemini’ setup. The next step is to clone the GitHub repository to your local environment: ```console cd ~ git clone https://github.com/xbill9/gemini-cli-azure cd gemini31-aci ``` Then run **init.sh** from the cloned directory. The script will attempt to determine your shell environment and set the correct variables: ```console source init.sh ``` If your session times out or you need to re-authenticate- you can run the **set\_env.sh** script to reset your environment variables: ```console source set_env.sh ``` Variables like PROJECT\_ID need to be setup for use in the various build scripts- so the **set\_env** script can be used to reset the environment if you time-out. #### Build the User Interface The front end files provide the user interface: ```console xbill@penguin:~/gemini-cli-azure/gemini31-aci$ make frontend cd frontend && npm install && npm run build added 218 packages, and audited 219 packages in 2s 49 packages are looking for funding run `npm fund` for details 1 high severity vulnerability To address all issues, run: npm audit fix Run `npm audit` for details. > frontend@0.0.0 build > vite build vite v7.3.1 building client environment for production... ✓ 33 modules transformed. dist/index.html 0.46 kB │ gzip: 0.29 kB dist/assets/index-xOQlTZZB.css 21.60 kB │ gzip: 4.54 kB dist/assets/index-0hbet2qm.js 214.56 kB │ gzip: 67.44 kB ✓ built in 1.02s xbill@penguin:~/gemini-cli-azure/gemini31-aca$ ``` #### Test The User Interface The mock server test script allows the interface and Browser settings to be set to allow multimedia — without using any external Model calls or tokens: ```console xbill@penguin:~/gemini-cli-azure/gemini31-aci$ make mock . ./mock.sh http://127.0.0.1:8080/ Serving static files from: /home/xbill/way-back-home/level_3_gemini/frontend/dist INFO: Started server process [24098] INFO: Waiting for application startup. INFO: Application startup complete. INFO: Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit) ``` The Deployed mock front-end will look similar to:  #### Verify The ADK Installation To verify the setup, run the ADK CLI locally with the biometric\_agent: ```console xbill@penguin:~/gemini-cli-azure/gemini31-aci$ make testadk . ./testadk.sh connect to local ADK CLI Log setup complete: /tmp/agents_log/agent.20260406_160553.log To access latest log: tail -F /tmp/agents_log/agent.latest.log /home/xbill/.local/lib/python3.13/site-packages/google/adk/cli/cli.py:204: UserWarning: [EXPERIMENTAL] InMemoryCredentialService: This feature is experimental and may change or be removed in future versions without notice. It may introduce breaking changes at any time. credential_service = InMemoryCredentialService() /home/xbill/.local/lib/python3.13/site-packages/google/adk/auth/credential_service/in_memory_credential_service.py:33: UserWarning: [EXPERIMENTAL] BaseCredentialService: This feature is experimental and may change or be removed in future versions without notice. It may introduce breaking changes at any time. super(). __init__ () Running agent biometric_agent, type exit to exit. [user]: hello [biometric_agent]: Scanner Online. [user]: ``` #### Test The ADK Web Interface This tests the Audio / Video ADK agent interactions: ```console xbill@penguin:~/gemini-cli-azure/gemini31-aci$ make adk . ./runadk.sh connect on http://127.0.0.1:8000/ 2026-04-06 16:06:25,026 - INFO - service_factory.py:266 - Using in-memory memory service 2026-04-06 16:06:25,026 - INFO - local_storage.py:84 - Using per-agent session storage rooted at /home/xbill/way-back-home/level_3_gemini/backend/app 2026-04-06 16:06:25,026 - INFO - local_storage.py:110 - Using file artifact service at /home/xbill/way-back-home/level_3_gemini/backend/app/.adk/artifacts /home/xbill/.local/lib/python3.13/site-packages/google/adk/cli/fast_api.py:193: UserWarning: [EXPERIMENTAL] InMemoryCredentialService: This feature is experimental and may change or be removed in future versions without notice. It may introduce breaking changes at any time. credential_service = InMemoryCredentialService() /home/xbill/.local/lib/python3.13/site-packages/google/adk/auth/credential_service/in_memory_credential_service.py:33: UserWarning: [EXPERIMENTAL] BaseCredentialService: This feature is experimental and may change or be removed in future versions without notice. It may introduce breaking changes at any time. super(). __init__ () INFO: Started server process [24350] INFO: Waiting for application startup. +-----------------------------------------------------------------------------+ | ADK Web Server started | | | | For local testing, access at [http://0.0.0.0:8000.](http://0.0.0.0:8000.) | +-----------------------------------------------------------------------------+ INFO: Application startup complete. INFO: Uvicorn running on [http://0.0.0.0:8000](http://0.0.0.0:8000) (Press CTRL+C to quit) ``` Then use the web interface — either on the local interface **127.0.0.1** or the catch-all web interface **0.0.0.0** -depending on your environment:  Special note for Google Cloud Shell Deployments- add a CORS **allow\_origins** configuration exemption to allow the ADK agent to run: ```console adk web --host 0.0.0.0 --allow_origins 'regex:.*' ``` #### Lint and Test the Main Python Code The final step is to build, lint, and test the main Python code. To Lint: ```console xbill@penguin:~/gemini-cli-azure/gemini31-aci$ make lint ruff check . All checks passed! ruff format --check . 10 files already formatted cd frontend && npm run lint > frontend@0.0.0 lint > eslint . xbill@penguin:~/gemini-cli-azure/gemini31-aca$ ``` To Test: ```console xbill@penguin:~/gemini-cli-azure/gemini31-aci$ make test python -m pytest ============================================================ test session starts ============================================================ platform linux -- Python 3.13.12, pytest-9.0.2, pluggy-1.6.0 rootdir: /home/xbill configfile: pyproject.toml plugins: anyio-4.11.0 collected 9 items / 1 skipped backend/app/biometric_agent/test_agent.py ..... [55%] test_ws_backend.py .. [77%] test_ws_backend_v2.py .. ``` #### Running Locally The main Python Code can then be run locally: ```console xbill@penguin:~/gemini-cli-azure/gemini31-aci$ make run . ./biosync.sh Local URL http://127.0.0.1:8080/ 2026-04-06 16:09:42,868 - INFO - System Config: 2.0 FPS, 10.0s Heartbeat Serving static files from: /home/xbill/way-back-home/level_3_gemini/frontend/dist INFO: Started server process [25860] INFO: Waiting for application startup. INFO: Application startup complete. INFO: Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit) ``` Then connect to the local front end:  #### Deploying to Google Azure ACA A utility script runs the deployment to Azure ACA. Use the deploy version from the local system: ```console xbill@penguin:~/gemini-cli-azure/gemini31-aci$ make deploy ./deploy.sh 0.0s 0.0s ``` You can validate the final result by checking the messages: ```console Azure Deployment complete. URL: https://biometric-scout-app.wonderfuldune-ec8eec50.eastus.azurecontainerapps.io xbill@penguin:~/gemini-cli-azure/gemini31-aci$ ``` Once the container is deployed- you can then get the endpoint: ```console xbill@penguin:~/gemini-cli-azure/gemini31-aca$ make status Name State URL ------------------- --------- ----------------------------------------------------------------------- biometric-scout-app Succeeded biometric-scout-app.wonderfuldune-ec8eec50.eastus.azurecontainerapps.io xbill@penguin:~/gemini-cli-azure/gemini31-aca$ make endpoint biometric-scout-app.wonderfuldune-ec8eec50.eastus.azurecontainerapps.io xbill@penguin:~/gemini-cli-azure/gemini31-aca$ ``` The service will be visible in the Azure console: ```plaintext biometric-scout-ssl-pengu.eastus.azurecontainer.io ```  #### Running the Web Interface Start a connection to the Azure deployed app: ```plaintext biometric-scout-ssl-pengu.eastus.azurecontainer.io ``` Then connect to the app :  Then use the Live model to process audio and video:  Finally — complete the sequence:  #### Project Code Review Gemini CLI was used for a final project review: ```plaintext ✦ The code is in great shape. All 8 tests passed, and the entire project is compliant with the linter rules. There is one warning related to an experimental feature (PLUGGABLE_AUTH) in the Google ADK, but this is informational and doesn't indicate an error. Since the automated checks are clean, what specific part of the codebase would you like me to review? For example, we could look at: * The agent's logic in backend/app/biometric_agent/agent.py * The frontend WebSocket and component logic in frontend/src/BiometricLock.jsx * The Azure deployment scripts * The overall architecture ``` #### Summary The Agent Development Kit was used to enable a multi-modal agent using the Gemini Live Model. This Agent was tested locally with the CLI and then deployed to Azure ACI. Several key take-aways and lessons learned were summarized from working with the transition to a new Live Gemini LLM model. Finally, Gemini CLI was used for a complete project code review.