-
Notifications
You must be signed in to change notification settings - Fork 565
Update dotprompt and eval doc to reflect menuSuggestionFlow theme #145
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
docs/dotprompt.md
Outdated
| --- | ||
| Generate a tabletop RPG character that would be found in {{location}}. | ||
| Generate a restaurant menu that would be found in {{location}}. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This sample is showcasing the ability to coerce the LLM to provide complex JSON output. As such, the schema above (L159-164) specifies an output object with 3 fields name, hitPoints, description..
If we want to go with the menu theme, we should update the schema with a few different properties, and perhaps tweak the prompt.
We could do something like:
---
model: vertexai/gemini-1.0-pro
input:
schema:
theme: string
output:
format: json
schema:
name: string
price: integer
ingredients(array): string
---

Generate a menu item that could be found at a {{theme}} restaurant.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
| your flow uses. | ||
| 1. If you'll access your flow from a web app (which you will be doing in the | ||
| next section), in the `httpsOptions` parameter, set a CORS policy: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please remove this file, in favor of #112.
| Alternatively, you can provide an output file to inspect the output in a json file. | ||
|
|
||
| ```posix-terminal | ||
| genkit eval:flow bobQA --input testQuestions.json --output eval-result.json |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There is another reference to bobQA much further down below, under "Running on existing datasets"

No description provided.