rebase keras3-dev on the current master #695
Conversation
This commit corrects various spelling mistakes in the markdown content of Jupyter notebooks located in the `notebooks/docker_and_kubernetes` directory. The following notebooks were checked and updated: - notebooks/docker_and_kubernetes/labs/1_intro_docker.ipynb - notebooks/docker_and_kubernetes/labs/2_intro_k8s.ipynb - notebooks/docker_and_kubernetes/labs/3_k8s_hello_node.ipynb - notebooks/docker_and_kubernetes/solutions/1_intro_docker.ipynb - notebooks/docker_and_kubernetes/solutions/2_intro_k8s.ipynb - notebooks/docker_and_kubernetes/solutions/3_k8s_hello_node.ipynb No changes were made to code cells or any other content.
Add langgraph agent section
updates: - [github.com/asottile/pyupgrade: v3.19.1 → v3.20.0](asottile/pyupgrade@v3.19.1...v3.20.0) - [github.com/pycqa/pylint: v3.3.6 → v3.3.7](pylint-dev/pylint@v3.3.6...v3.3.7)
…-config [pre-commit.ci] pre-commit autoupdate
…ents removing hackernews loader
…hain_components Revert "removing hackernews loader"
…ents removed hackernew loader
adding lab notebook for adk
Langgraph Solution notebook
…-kubernetes Fix typos in markdown cells of Docker and Kubernetes notebooks.
Deploy to Vertex AI Agent Engine
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
Summary of ChangesHello @takumiohym, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request introduces a substantial set of new educational content focused on building and deploying AI agents within the Vertex AI ecosystem, leveraging Google's Agent Development Kit (ADK) and LangGraph. It provides hands-on labs for creating various agent types, from simple tools to complex, stateful, and multi-agent systems, culminating in a guide for deploying these agents to the Vertex AI Agent Engine. Complementing these new features, the PR also includes general code quality improvements, such as updating development tool dependencies and correcting minor textual errors across existing documentation, ensuring a polished and up-to-date learning experience. Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request appears to be a rebase of the keras3-dev branch onto master, introducing a significant number of new lab notebooks and solutions related to Vertex AI, agents with ADK, and LangGraph. The changes also include minor dependency updates and typo fixes in existing notebooks. My review focuses on the newly added files. I've identified several incomplete implementations marked with TODO comments in the new lab files, which should be addressed. Additionally, there are some minor issues like typos and broken links in the new solution notebooks that need correction. Overall, the new content looks promising but requires completion and polishing.
|
|
||
| from .tools import get_weather | ||
|
|
||
| root_agent = None # TODO - define the weather agent |
There was a problem hiding this comment.
The root_agent is initialized to None with a TODO to define the weather agent. This file seems incomplete and the agent is not functional.
| greeting_agent = Agent( | ||
| # TODO - Define the greeting agent | ||
| ) |
There was a problem hiding this comment.
The greeting_agent is not defined and contains a TODO. This part of the implementation is incomplete.
| # The loop for refining the essay: Reflect -> Research Critique -> Rewrite | ||
| refinement_loop = LoopAgent( | ||
| name="refinement_loop", | ||
| sub_agents=[], # TODO: Define the loop. |
There was a problem hiding this comment.
The refinement_loop agent has an empty sub_agents list and is marked with a TODO. The implementation for the refinement loop is incomplete.
|
|
||
| # The main sequential agent that orchestrates the entire process | ||
| essay_writing_agent = SequentialAgent( | ||
| name="essay_writing_agent", sub_agents=[] # TODO: Define a sequential flow. |
There was a problem hiding this comment.
The essay_writing_agent has an empty sub_agents list and is marked with a TODO. The sequential flow for the agent is not defined.
| """TODO:Write a docstring for the | ||
| get_weather agent with a description of what the tool is | ||
| supposed to do and also the arguments that are needed. | ||
| """ |
There was a problem hiding this comment.
The docstring for the get_weather function is incomplete and contains a TODO. A detailed docstring is crucial for the LLM to understand how to use this tool effectively. Please complete the docstring with a description of the tool's purpose and its arguments.
"""Retrieves the current weather report for a specified city.
Args:
city (str): The name of the city (e.g., "New York", "London", "Tokyo").
"""| "\n", | ||
| "By the end of this notebook, you will understand how to:\n", | ||
| "* Set up required configuration and deploy ADK **Agents** to **Vertex AI Agent Engine**.\n", | ||
| "* Use the ADK **RemoteAgent** ans **RemoteSession** to execute agent interactions.\n", |
There was a problem hiding this comment.
There is a typo here. ans should be and.
| "* Use the ADK **RemoteAgent** ans **RemoteSession** to execute agent interactions.\n", | |
| "* Use the ADK **RemoteAgent** and **RemoteSession** to execute agent interactions.\n", |
| "Once deployed, remote_agent corresponds to an instance of agent that is running on Vertex AI and can be queried or deleted.\n", | ||
| "You can check deployed agents using Cloud Console: Vertex AI -> Agent Engine\n", | ||
| "\n", | ||
| "[https://console.cloud.google.com/vertex-ai/agents/agent-engines]()" |
There was a problem hiding this comment.
This markdown link is broken as it's missing a URL.
| "[https://console.cloud.google.com/vertex-ai/agents/agent-engines]()" | |
| "[https://console.cloud.google.com/vertex-ai/agents/agent-engines](https://console.cloud.google.com/vertex-ai/agents/agent-engines)" |
| "source": [ | ||
| "#### List all deployed agents for a given project and location:\n", | ||
| "In case if you need to list all active AI Agents deployments you cau use `agent_engines.list()` method.\n", | ||
| "Each deployed agent has a unique identifier ***Name*** and fully qualified resource name ***Resource Name***" |
There was a problem hiding this comment.
There is a typo here. cau should be can.
| "Each deployed agent has a unique identifier ***Name*** and fully qualified resource name ***Resource Name***" | |
| "In case if you need to list all active AI Agents deployments you can use `agent_engines.list()` method.\n", |
| " AGENT_RESOURCE_NAME = remote_agent.resource_name\n", | ||
| " print(f\"Resource Name: {remote_agent.resource_name}\")\n", | ||
| "else:\n", | ||
| " print(f'Cant find deployed agent with the display_name=\"{DISPLAY_NAME}\"')" |
There was a problem hiding this comment.
There is a typo here. Cant should be Can't.
| " print(f'Cant find deployed agent with the display_name=\"{DISPLAY_NAME}\"')" | |
| " print(f'Can\'t find deployed agent with the display_name=\"{DISPLAY_NAME}\"')" |
| "tags": [] | ||
| }, | ||
| "source": [ | ||
| "!cp ./adk_agents/agent1_weather_lookup/tools.py ./adk_agents/agent2_sub_agent/" |
There was a problem hiding this comment.
This cp command might fail if the destination directory adk_agents/agent2_sub_agent/ doesn't exist. It would be more robust to create it first using mkdir -p.
| "!cp ./adk_agents/agent1_weather_lookup/tools.py ./adk_agents/agent2_sub_agent/" | |
| "!mkdir -p ./adk_agents/agent2_sub_agent/ && cp ./adk_agents/agent1_weather_lookup/tools.py ./adk_agents/agent2_sub_agent/" |
No description provided.