feat: add tutorial_langgraph_human_in_the_loop.ipynb #1673
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
![code-review-assist[bot]](https://avatars.githubusercontent.com/in/1008254?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hi team,
I'm currently reviewing this pull request and will provide a full review shortly. In the meantime, here's a quick summary for you and other reviewers to get up to speed:
This pull request, submitted by shawn-yang-google, aims to add a new Jupyter Notebook tutorial: tutorial_langgraph_human_in_the_loop.ipynb. The description indicates it's a new feature and includes standard contribution checklist items.
Because the provided patch content is empty, I cannot provide specifics on the content of the notebook itself. I'll need to review the notebook directly to provide a detailed analysis of its content and functionality. This summary is therefore limited to the high-level information provided in the pull request metadata.
Summary of Changes:
- Addition of a new Jupyter Notebook:
tutorial_langgraph_human_in_the_loop.ipynbis added to the repository. The exact content of this notebook is currently unknown without access to the actual file contents.
Intent:
The intent appears to be to create a new tutorial focusing on language graphs and human-in-the-loop aspects. However, without more information from the notebook itself, this is just an inference based on the filename.
Disclaimer: This summary is incomplete due to the lack of patch details. A more comprehensive review will follow once I've examined the notebook's contents.
And now for a little haiku to brighten your day:
Code flows like a stream,
Reviews guide it to the sea,
Perfect, clean, and bright.
|
Gemini encountered an error creating the review. You can try again by commenting |
shawn-yang-google
changed the title
shawn-yang-google
force-pushed
the
main
branch
from
b051349 to
a7607f6
Compare
shawn-yang-google
changed the title
shawn-yang-google
force-pushed
the
main
branch
from
a7607f6 to
c0b30e5
Compare
shawn-yang-google
force-pushed
the
main
branch
from
c0b30e5 to
8b89d3a
Compare
gemini/reasoning-engine/tutorial_langgraph_human_in_the_loop.ipynb
Outdated
Show resolved
Hide resolved
gemini/reasoning-engine/tutorial_langgraph_human_in_the_loop.ipynb
Outdated
Show resolved
Hide resolved
gemini/reasoning-engine/tutorial_langgraph_human_in_the_loop.ipynb
Outdated
Show resolved
Hide resolved
gemini/reasoning-engine/tutorial_langgraph_human_in_the_loop.ipynb
Outdated
Show resolved
Hide resolved
gemini/reasoning-engine/tutorial_langgraph_human_in_the_loop.ipynb
Outdated
Show resolved
Hide resolved
gemini/reasoning-engine/tutorial_langgraph_human_in_the_loop.ipynb
Outdated
Show resolved
Hide resolved
gemini/reasoning-engine/tutorial_langgraph_human_in_the_loop.ipynb
Outdated
Show resolved
Hide resolved
Resolve all comments from Holt
| "outputs": [], | ||
| "source": [ | ||
| "agent = reasoning_engines.LanggraphAgent(\n", | ||
| " model=\"gemini-1.5-pro-001\",\n", |
There was a problem hiding this comment.
Suggest changing this to gemini-1.5-pro which aliases to the latest GA version.
There was a problem hiding this comment.
Thanks for the suggestion! Using gemini-1.5-pro as an alias for the latest GA version is a good practice for maintainability and future-proofing. This ensures the notebook remains compatible with updates. I've updated the code suggestion to reflect this change. I'm referencing Google's best practices for Python code style and clarity in this suggestion.
However, for clarity, it might be beneficial to add a comment explaining this choice in the code itself. This will help future readers understand why this specific model identifier was used.
| " model=\"gemini-1.5-pro-001\",\n", | |
| agent = reasoning_engines.LanggraphAgent( | |
| model="gemini-1.5-pro", # Alias to the latest Generally Available Gemini model | |
| "source": [ | ||
| "remote_agent = reasoning_engines.ReasoningEngine.create(\n", | ||
| " reasoning_engines.LanggraphAgent(\n", | ||
| " model=\"gemini-1.5-pro-001\",\n", |
There was a problem hiding this comment.
Suggest changing this to gemini-1.5-pro which aliases to the latest GA version.
There was a problem hiding this comment.
Thanks for the suggestion! Using gemini-1.5-pro as an alias for the latest GA version is a good idea for maintainability and future-proofing. This ensures the notebook will continue to work with future updates to the Gemini models. I've updated the code to reflect this change. I'm referencing Google's Python style guide for consistency and readability in this suggestion.
| " model=\"gemini-1.5-pro-001\",\n", | |
| model="gemini-1.5-pro", | |
| "%pip install --upgrade --user --quiet \\\n", | ||
| " \"google-cloud-aiplatform[langchain,reasoningengine]\" --force-reinstall" | ||
| ] |
There was a problem hiding this comment.
To be explicit, I typically include libs that are imported in the tool functions, which includes the requests lib in this sample notebook / tool. So I suggest adding requests to the list of libraries that are required.
| " requirements=[\n", | ||
| " \"google-cloud-aiplatform[reasoningengine,langchain]\",\n", | ||
| " ],\n", |
There was a problem hiding this comment.
To be explicit, I typically include libs that are imported in the tool functions, which includes the requests lib in this sample notebook / tool. So I suggest adding requests to the list of requirements.
| " model_kwargs={\"temperature\": 0, \"max_retries\": 6},\n", | ||
| " checkpointer_kwargs=checkpointer_kwargs,\n", | ||
| " checkpointer_builder=checkpointer_builder,\n", | ||
| " # enable_tracing=True, # https://github.com/Arize-ai/openinference/issues/1119\n", |
There was a problem hiding this comment.
Suggest removing the GitHub link in the comment from this sample notebook unless it gives clear actionable instructions for how to work around any issues that might come up.
Description
Thank you for opening a Pull Request!
Before submitting your PR, there are a few things you can do to make sure it goes smoothly:
CONTRIBUTINGGuide.CODEOWNERSfor the file(s).nox -s formatfrom the repository root to format).Fixes #<issue_number_goes_here> 🦕