Add mulit-explore support for looker datasource #2361
Conversation
# with '#' will be ignored, and an empty message aborts the commit. # # On branch main # Your branch is up to date with 'origin/main'. # # Changes to be committed: # renamed: agents/geminidataanalytics/colabs/geminidataanalytics_public_http_demo_|_vPublished.ipynb -> agents/gemini_data_analytics/intro_gemini_data_analytics_http.ipynb # renamed: agents/geminidataanalytics/colabs/geminidataanalytics_public_SDK_demo_|_vPublished.ipynb -> agents/gemini_data_analytics/intro_gemini_data_analytics_sdk.ipynb #
Summary of ChangesHello @vermaAstra, 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 significantly upgrades the Gemini Data Analytics notebooks by enabling the configuration and querying of multiple Looker explores simultaneously. This enhancement allows for more comprehensive and flexible data analysis directly within the notebooks, streamlining the process of interacting with diverse Looker datasets through a single data agent. 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 successfully adds support for multiple Looker explores as datasources, enhancing the functionality of both the HTTP and SDK notebooks. The changes are consistent and well-implemented. My review includes a few minor suggestions for improving code style and readability, as well as a medium-severity comment on a potential issue in the SDK notebook related to how conversation history is managed. Overall, this is a solid contribution.
| " show_message(response)\n", | ||
| " if response.system_message or response.user_message:\n", | ||
| " conversation_messages.append(response)" | ||
| " conversation_messages.append(response)" |
There was a problem hiding this comment.
Removing the if response.system_message or response.user_message: check could introduce a bug. If the stream contains messages that are not meant to be part of the conversation history (e.g., progress updates, empty messages), appending them to conversation_messages could corrupt the history for subsequent multi-turn requests. It would be safer to retain the check to ensure only valid conversational messages are stored.
if response.system_message or response.user_message:
conversation_messages.append(response)
| "# # \"lookml_model\": lookml_model_2,\n", | ||
| "# # \"explore\": explore_2,\n", | ||
| "# # },\n", | ||
| "#. # Add up to 5 total explore references here\n", |
There was a problem hiding this comment.
There appears to be a typo in this comment. Please remove the leading . character.
| "#. # Add up to 5 total explore references here\n", | |
| #. # Add up to 5 total explore references here |
| " try:\n", | ||
| " json_object = json_lib.loads(str)\n", | ||
| " except ValueError:\n", | ||
| " except ValueError as e:\n", |
There was a problem hiding this comment.
The caught exception e is not used. It's a good practice to omit the variable to signal that it's intentionally unused, which also avoids potential linter warnings.
except ValueError:
| " data_json = json_lib.loads(acc)\n", | ||
| "\n", | ||
| " if \"systemMessage\" not in data_json:\n", | ||
| " if not \"systemMessage\" in data_json:\n", |
There was a problem hiding this comment.
For better readability and adherence to Python style conventions (PEP 8), it's recommended to use if 'key' not in a_dict: instead of if not 'key' in a_dict:.
if "systemMessage" not in data_json:
| " conversation_messages.append(data_json)\n", | ||
| "\n", | ||
| " if \"systemMessage\" not in data_json:\n", | ||
| " if not \"systemMessage\" in data_json:\n", |
There was a problem hiding this comment.
For better readability and adherence to Python style conventions (PEP 8), it's recommended to use if 'key' not in a_dict: instead of if not 'key' in a_dict:.
if "systemMessage" not in data_json:
agents/gemini_data_analytics/intro_gemini_data_analytics_sdk.ipynb
Outdated
Show resolved
Hide resolved
|
Thanks for pointing out this. Corrected. |
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> 🦕