Azure-Samples/azure-ai-content-understanding-pythonPublic

NotificationsYou must be signed in to change notification settings
Fork27
Star37

Refactor the flow of generate knowledge resources and add second sample for Pro mode#39

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 ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Jump to bottom

Open

chienyuanchang wants to merge11 commits intomain

base:main

Choose a base branch

fromchienyaunchang/pro_mode_generate_resource_flow_improvement

Open

Refactor the flow of generate knowledge resources and add second sample for Pro mode#39

chienyuanchang wants to merge11 commits intomainfromchienyaunchang/pro_mode_generate_resource_flow_improvement

+8,051 −73

Conversation

Copy link

Collaborator

chienyuanchang commentedJul 18, 2025

Purpose

We will gather the file paths to analyze/upload first (validation first) and then do the analyze/upload once the folder is clean.

Does this introduce a breaking change?

[ ] Yes[x] No

Pull Request Type

What kind of change does this Pull Request introduce?

[ ] Bugfix[ ] Feature[ ] Code style update (formatting, local variables)[x] Refactoring (no functional changes, no api changes)[ ] Documentation content changes[ ] Other... Please describe:

How to Test

Get the code

git clone [repo-address]cd [repo-name]git checkout [branch-name]npm install

Test the code

What to Check

Verify that the following are valid

Generation of notebook works normal

Other Information

chienyuanchang added4 commits

July 18, 2025 20:08

refactore cu_client

a183dce

improve some instruction for using exsiting OCR result

609dce0

clean up import

b23f551

add second sample

a29178b

chienyuanchang requested a review fromyungshinlintw

July 18, 2025 22:02

chienyuanchang changed the title~~Refactor the flow of generate knowledge resources for Pro mode~~Refactor the flow of generate knowledge resources and add second sample for Pro mode

Jul 18, 2025

chienyuanchang requested a review fromjuliagongms

July 18, 2025 22:02

chienyuanchang added2 commits

July 18, 2025 22:36

add sample data

c875091

add sample highlight

0c487bb

yungshinlintw reviewed

Jul 21, 2025

View reviewed changes

Copy link

Collaborator

yungshinlintw left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

For set_env_for_training_data_and_reference_doc.md, let's improve it by clarifying step 6: Set Environment Variables in.env File.

Let's call out:

Depending on the sample that you will run, you will need to set required environment variables in .env.

6.1:anlayzer_training Add the SAS URL as value ofTRAINIGN_DATA_SAS_URL, and a prefix forTRAINING_DATA_PATH. You can pick your own value, for example 'training_files'.

TRAINING_DATA_SAS_URL=<Blob container SAS URL>TRAINING_DATA_PATH=<Designated folder path under the blob container>

6.2 ....

python/content_understanding_client.py OutdatedShow resolvedHide resolved

python/content_understanding_client.pyShow resolvedHide resolved

yungshinlintw requested changes

Jul 21, 2025

View reviewed changes

notebooks/field_extraction_pro_mode.ipynbShow resolvedHide resolved

yungshinlintw requested changes

Jul 21, 2025

View reviewed changes

python/content_understanding_client.pyShow resolvedHide resolved

notebooks/field_extraction_pro_mode.ipynb OutdatedShow resolvedHide resolved

notebooks/field_extraction_pro_mode.ipynbShow resolvedHide resolved

chienyuanchang added3 commits

July 21, 2025 19:56

clarifying step 6: Set Environment Variables and aid aiohttp

ed30813

fix content_understanding_client

7e0cf93

clarify strengths and expectations in the sample

4eafde9

Copy link

CollaboratorAuthor

chienyuanchang commentedJul 21, 2025

For set_env_for_training_data_and_reference_doc.md, let's improve it by clarifying step 6: Set Environment Variables in.env File.
Let's call out:
Depending on the sample that you will run, you will need to set required environment variables in .env.
6.1:anlayzer_training Add the SAS URL as value ofTRAINIGN_DATA_SAS_URL, and a prefix forTRAINING_DATA_PATH. You can pick your own value, for example 'training_files'.
TRAINING_DATA_SAS_URL=<Blob container SAS URL>TRAINING_DATA_PATH=<Designated folder path under the blob container>
6.2 ....

@yungshinlintw, I've improved set_env_for_training_data_and_reference_doc.md by the suggestion in this comment. But, I couldn't reply/close this comment directly.

yungshinlintw approved these changes

Jul 21, 2025

View reviewed changes

Copy link

Collaborator

yungshinlintw left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Approve with more suggestions to improve the explanation text. Thanks a lot for the work here!

docs/set_env_for_training_data_and_reference_doc.md OutdatedShow resolvedHide resolved

notebooks/field_extraction_pro_mode.ipynb

		"cell_type":"markdown",
		"metadata": {},
		"source": [
		"### Generate knowledge base for the second sample\n",

Copy link

Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Remove "\n". This seems to cause the markdown not to display correctly in the Codespace.

Copy link

CollaboratorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

"\n" is added by notebook automatically. Mine codebase is good.

Copy link

CollaboratorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Won't fix

notebooks/field_extraction_pro_mode.ipynb OutdatedShow resolvedHide resolved

notebooks/field_extraction_pro_mode.ipynb Outdated

		"cell_type":"markdown",
		"metadata": {},
		"source": [
		"> In the LineItemCorroboration field, we see that each line item is extracted with its corresponding information, claim status, and evidence. Items that are not covered by the policy, such as the Starbucks drink and hotel stay, are not confirmed, while damage repairs that are supported by the supplied documents in the claim and are permitted by the policy are confirmed."

Copy link

Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

"are marked as suspicious."

Copy link

Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Also mention that these are generated from repair estimate document.

On top of these, can you please add another cell to show information that is only being avaiable from the car accident report.

This can better show that the information are extracted from both documents to generate one result. It will be great to explain the N:1 (input to analysis result) relationship. We also want to explain that there is always one anlaysis result, and this is not a batch model (N input documents to generate N analysis result).

We want to strive to provide our samples as a good source of learning the functionalties, so I would like to explain more knowlege beyond showing the code to call our serivce. Thanks!

Copy link

CollaboratorAuthor

chienyuanchangJul 22, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Current field schema does not have the field only available from the car accident report. I'm adding a new field "ReportingOfficer".

Copy link

CollaboratorAuthor

chienyuanchangJul 22, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Added additional field and explanation

chienyuanchang added2 commits

July 21, 2025 23:12

remove most descriptions

16fda45

add field

030d397

Labels

None yet

2 participants

Movatterモバイル変換

Refactor the flow of generate knowledge resources and add second sample for Pro mode#39

Are you sure you want to change the base?

Refactor the flow of generate knowledge resources and add second sample for Pro mode#39

Conversation

chienyuanchang commentedJul 18, 2025

Purpose

Does this introduce a breaking change?

Pull Request Type

How to Test

What to Check

Other Information

Uh oh!

yungshinlintw left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

chienyuanchang commentedJul 21, 2025

Uh oh!

yungshinlintw left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

yungshinlintwJul 21, 2025

Choose a reason for hiding this comment

Uh oh!

chienyuanchangJul 21, 2025

Choose a reason for hiding this comment

Uh oh!

chienyuanchangJul 22, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

yungshinlintwJul 21, 2025

Choose a reason for hiding this comment

Uh oh!

yungshinlintwJul 21, 2025

Choose a reason for hiding this comment

Uh oh!

chienyuanchangJul 22, 2025

Choose a reason for hiding this comment

Uh oh!

chienyuanchangJul 22, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!