Python: Azure AI Search Citation Extraction - V2

[giles17]

Motivation and Context

Adds extraction method to sample

Description

Contribution Checklist

• The code builds clean without any errors or warnings
• The PR follows the Contribution Guidelines
• All unit tests pass, and I have added new tests where possible
• Is this a breaking change? If yes, add "[BREAKING]" prefix to the title of the PR.

[Copilot]

Pull request overview

This PR enhances the Azure AI Search sample by adding citation extraction functionality to demonstrate how to retrieve and display citation information from agent responses.

Key Changes:

• Added extract_citations_from_response helper function to parse citations from agent responses
• Modified the query to request detailed winter hotel information
• Changed query_type from "simple" to "vector" mode
• Added citation display logic to show extracted citation URLs

[Copilot]

The extract_citations_from_response function has incomplete citation output. Currently only the URL is printed (line 94), but the function extracts title, file_id, and positions which are not displayed. This makes the citation information incomplete for users who may need these additional details.

Consider printing all extracted citation information:

print(f"Citation {i}:")
print(f"  URL: {citation['url']}")
if citation.get('title'):
    print(f"  Title: {citation['title']}")
if citation.get('file_id'):
    print(f"  File ID: {citation['file_id']}")
if citation.get('positions'):
    print(f"  Positions: {citation['positions']}")

Suggested change

	print(f" URL: {citation['url']}")
	print(f" URL: {citation['url']}")
	if citation.get('title'):
	print(f" Title: {citation['title']}")
	if citation.get('file_id'):
	print(f" File ID: {citation['file_id']}")
	if citation.get('positions'):
	print(f" Positions: {citation['positions']}")

[eavanvalkenburg]

you can skip a bunch of these checks (it's a sample, so we can be a less strict on typing, to improve readability) and inverse the logic for the rest:

Suggested change

	if hasattr(response, "messages") and response.messages:
	from itertools import chain
	if not response.messages:
	return citations
	for content in chain.from_iterable(message.contents for message in response.messages):
	if not content.annotations:
	continue
	# parse the annotations

Also why not just return the citations instead of this dict?

[eavanvalkenburg]

Is this still current @giles17, or can we close?

[giles17]

@eavanvalkenburg yes, I'll close it