-
Notifications
You must be signed in to change notification settings - Fork 284
sample to demo passing images to skills #40
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
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.
Mostly fixed typos. Once this is merged, I will take a pass through this repo and fix multiple readmes, probably creating one for this sample. You need a readme if you want the sample to show up in the Azure samples browser.
"# Azure Cognitive Search sample \n", | ||
"## Passing Images as Binary File References\n", | ||
"\n", | ||
"Cognitive Search skillsets that need to pass images to custom skills use a binary file reference to serialize the images to pass them to and from skills. This sample demosntrates an example of how skills can be configured to accept an image as an input from the skillset and return images as outputs to the skillset. This example does nothing more than segment an image based on the layout from OCR. The sole purpose of this sample is to demosntrate how you pass images to skills and how skills can return images.\n", |
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.
Line 10 -- two typos on "demonstrate" in this paragraph
Can explain why the REST API used here? You could put this in the intro or in the prerequisites: "This sample uses Python and the Search REST API (the Azure SDK for Python does not support knowledge store definitions at this time)."
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.
I'd rather not call that out as we would need to go back and change that when the knowledge store is supported.
"skillset_name = f'{datasource_container}-ss'\n", | ||
"skillset_def = {\n", | ||
" 'name': f'{skillset_name}',\n", | ||
" 'description': 'Skillset to enrich hotel reviews with aspect based sentiment',\n", |
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.
line 168 -- Update the description to match the scenario
@HeidiSteen Are we ok to merge? |
@jennifermarsman can you review the changes? Added a driver notebook for testing and a python skill that accepts and returns images.