feat: mesop cloudrun gemini app #1388
Conversation
| @@ -0,0 +1,100 @@ | |||
| # Cloud Run application utilizing Mesop that demonstrates working with Vertex AI Gemini API | |||
There was a problem hiding this comment.
| # Cloud Run application utilizing Mesop that demonstrates working with Vertex AI Gemini API | |
| # Mesop Gemini App on Cloud Run |
There was a problem hiding this comment.
Will revise with a different suggestion for review "Mesop application using Vertex AI Gemini API on Cloud Run"
There was a problem hiding this comment.
I'd recommend changing the folder name to just mesop-cloudrun (gemini is redundant)
There was a problem hiding this comment.
This was to align with the streamlit example
There was a problem hiding this comment.
The streamlit one probably shouldn't have "gemini" either, tbh.
| ## Marketing events | ||
| def on_change_marketing_category(e: me.RadioChangeEvent) -> None: | ||
| state = me.state(State) | ||
| state.marketing_product_category = e.value | ||
|
|
||
|
|
||
| def on_change_marketing_target(e: me.RadioChangeEvent) -> None: | ||
| state = me.state(State) | ||
| state.marketing_target_audience = e.value | ||
|
|
||
|
|
||
| def on_change_marketing_location(e: me.RadioChangeEvent) -> None: | ||
| state = me.state(State) | ||
| state.marketing_target_location = e.value | ||
|
|
||
|
|
||
| def on_selection_change_marketing_goals(e: me.SelectSelectionChangeEvent) -> None: | ||
| s = me.state(State) | ||
| s.marketing_campaign_selected_goals = e.values | ||
| print(f"selected: {s.marketing_campaign_selected_goals}") | ||
|
|
||
|
|
||
| def on_change_marketing_brand_voice(e: me.RadioChangeEvent) -> None: | ||
| state = me.state(State) | ||
| state.marketing_brand_voice = e.value | ||
|
|
||
|
|
||
| def on_change_marketing_budget(e: me.RadioChangeEvent) -> None: | ||
| state = me.state(State) | ||
| state.marketing_budget = e.value |
There was a problem hiding this comment.
Is there any way to simplify this into fewer methods?
There was a problem hiding this comment.
There's a lot of duplicated code in this file. Is it possible to clean it up/split into separate files/modularize?
I would also recommend moving the prompts into dedicated files. Possibly in the .prompt format https://docs.continue.dev/customize/deep-dives/prompt-files
|
Please resolve linting errors as well https://github.com/GoogleCloudPlatform/generative-ai/actions/runs/11782270743/job/32816928938 |
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).Fixes #1387 🦕