docs: Fix double hashtag in code comments

[sjrl]

Related Issues

• fixes #issue-number

Proposed Changes:

Removes the double hash tags in our code comments

How did you test it?

Notes for the reviewer

Checklist

• I have read the contributors guidelines and the code of conduct.
• I have updated the related issue with new insights and changes.
• I have added unit tests and updated the docstrings.
• I've used one of the conventional commit types for my PR title: fix:, feat:, build:, chore:, ci:, docs:, style:, refactor:, perf:, test: and added ! in case the PR includes breaking changes.
• I have documented my code.
• I have added a release note file, following the contributors guidelines.
• I have run pre-commit hooks and fixed any issue.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
haystack-docs	Ready	Preview, Comment	May 13, 2026 9:19am

[sjrl]

@julian-risch I'm happy to wait on merging this one after the 2.29 release is finished.

[claude]

Inline review on docs-website/docs/pipeline-components/extractors/llmmetadataextractor.mdx — lines 86, 103, 105, 108.

The PR description says "Fix double hashtag in code comments", but those four lines are inside the NER_PROMPT triple-quoted string literal (lines 73-110), not Python comments. The blanket ## -> # substitution stripped one # from each run of # characters used as a visual separator inside that prompt template:

• Line 86: 22 hashes -> 21
• Line 103: 29 hashes -> 28
• Line 105: 22 hashes -> 21
• Line 108: 22 hashes -> 21

These characters are part of the prompt content the documentation tells users to send to the LLM (mirroring the GraphRAG-style NER prompt, where the original counts appear intentional). Suggest reverting just these four lines so the substitution only affects actual Python comments.

See

haystack/docs-website/docs/pipeline-components/extractors/llmmetadataextractor.mdx

Lines 73 to 110 in 75994fd

	NER_PROMPT = """
	-Goal-
	Given text and a list of entity types, identify all entities of those types from the text.
	-Steps-
	1. Identify all entities. For each identified entity, extract the following information:
	- entity_name: Name of the entity, capitalized
	- entity_type: One of the following types: [organization, product, service, industry]
	Format each entity as a JSON like: {"entity": <entity_name>, "entity_type": <entity_type>}
	2. Return output in a single list with all the entities identified in steps 1.
	-Examples-
	#####################
	Example 1:
	entity_types: [organization, person, partnership, financial metric, product, service, industry, investment strategy, market trend]
	text: Another area of strength is our co-brand issuance. Visa is the primary network partner for eight of the top
	10 co-brand partnerships in the US today and we are pleased that Visa has finalized a multi-year extension of
	our successful credit co-branded partnership with Alaska Airlines, a portfolio that benefits from a loyal customer
	base and high cross-border usage.
	We have also had significant co-brand momentum in CEMEA. First, we launched a new co-brand card in partnership
	with Qatar Airways, British Airways and the National Bank of Kuwait. Second, we expanded our strong global
	Marriott relationship to launch Qatar's first hospitality co-branded card with Qatar Islamic Bank. Across the
	United Arab Emirates, we now have exclusive agreements with all the leading airlines marked by a recent
	agreement with Emirates Skywards.
	And we also signed an inaugural Airline co-brand agreement in Morocco with Royal Air Maroc. Now newer digital
	issuers are equally
	------------------------
	output:
	{"entities": [{"entity": "Visa", "entity_type": "company"}, {"entity": "Alaska Airlines", "entity_type": "company"}, {"entity": "Qatar Airways", "entity_type": "company"}, {"entity": "British Airways", "entity_type": "company"}, {"entity": "National Bank of Kuwait", "entity_type": "company"}, {"entity": "Marriott", "entity_type": "company"}, {"entity": "Qatar Islamic Bank", "entity_type": "company"}, {"entity": "Emirates Skywards", "entity_type": "company"}, {"entity": "Royal Air Maroc", "entity_type": "company"}]}
	############################
	-Real Data-
	#####################
	entity_types: [company, organization, person, country, product, service]
	text: {{ document.content }}
	#####################
	output:
	"""

for context.