Docs/adjusting docs so that some snippets run others are skipped

docs-website/reference/haystack-api/builders_api.md

@@ -211,8 +211,7 @@ print(res)
 # 'index': 0, 'finish_reason': 'stop', 'usage': {'prompt_tokens': 27, 'completion_tokens': 681, 'total_tokens':
 # 708}})]}}
 
-messages = [system_message, ChatMessage.from_user("What's the weather forecast for {{location}} in the next
-{{day_count}} days?")]
+messages = [system_message, ChatMessage.from_user("What's the weather forecast for {{location}} in the next {{day_count}} days?")]
 
 res = pipe.run(data={"prompt_builder": {"template_variables": {"location": location, "day_count": "5"},
                                     "template": messages}})

docs-website/reference/haystack-api/connectors_api.md

@@ -180,10 +180,10 @@ result = service_connector.run(
 )
 print(result)
 
-# {'service_response': ChatMessage(_role=<ChatRole.USER: 'user'>, _content=[TextContent(text=
-# '{"searchParameters": {"q": "Why was Sam Altman ousted from OpenAI?",
-# "type": "search", "engine": "google"}, "answerBox": {"snippet": "Concerns over AI safety and OpenAI's role
-# in protecting were at the center of Altman's brief ouster from the company."...
+# >> {'service_response': ChatMessage(_role=<ChatRole.ASSISTANT: 'assistant'>, _content=[TextContent(text=
+# >> '{"searchParameters": {"q": "Why was Sam Altman ousted from OpenAI?",
+# >> "type": "search", "engine": "google"}, "answerBox": {"snippet": "Concerns over AI safety and OpenAI's role
+# >> in protecting were at the center of Altman's brief ouster from the company."...
 ```
 
 #### __init__

docs-website/reference/haystack-api/converters_api.md

@@ -146,6 +146,7 @@ It can attach metadata to the resulting documents.
 ### Usage example
 
 ```python
+from datetime import datetime
 from haystack.components.converters.csv import CSVToDocument
 converter = CSVToDocument()
 results = converter.run(sources=["sample.csv"], meta={"date_added": datetime.now().isoformat()})
@@ -1268,7 +1269,7 @@ from haystack import Document
 from haystack.components.converters import OutputAdapter
 
 adapter = OutputAdapter(template="{{ documents[0].content }}", output_type=str)
-documents = [Document(content="Test content"]
+documents = [Document(content="Test content")]
 result = adapter.run(documents=documents)
 
 assert result["output"] == "Test content"
@@ -1836,7 +1837,6 @@ Converts text files to documents.
 
 ### XLSXToDocument
 
-````
 Converts XLSX (Excel) files into Documents.
 
 Supports reading data from specific sheets or all sheets in the Excel file. If all sheets are read, a Document is
@@ -1846,13 +1846,14 @@ created for each sheet. The content of the Document is the table which can be sa
 
 ```python
 from haystack.components.converters.xlsx import XLSXToDocument
+from datetime import datetime
 
 converter = XLSXToDocument()
 results = converter.run(sources=["sample.xlsx"], meta={"date_added": datetime.now().isoformat()})
 documents = results["documents"]
 print(documents[0].content)
 # ",A,B
-````
+```
 
 1,col_a,col_b
 2,1.5,test

docs-website/reference/haystack-api/evaluators_api.md

@@ -635,7 +635,7 @@ print(result["score"])
 # 0.5
 print(result["results"])
 # [{'statements': ['Python is a high-level general-purpose programming language.',
-'Python was created by George Lucas.'], 'statement_scores': [1, 0], 'score': 0.5}]
+# 'Python was created by George Lucas.'], 'statement_scores': [1, 0], 'score': 0.5}]
 ```
 
 #### __init__

docs-website/reference/haystack-api/extractors_api.md

@@ -267,19 +267,19 @@ extractor = LLMMetadataExtractor(
 )
 
 extractor.run(documents=docs)
->> {'documents': [
-    Document(id=.., content: 'deepset was founded in 2018 in Berlin, and is known for its Haystack framework',
-    meta: {'entities': [{'entity': 'deepset', 'entity_type': 'company'}, {'entity': 'Berlin', 'entity_type': 'city'},
-          {'entity': 'Haystack', 'entity_type': 'product'}]}),
-    Document(id=.., content: 'Hugging Face is a company that was founded in New York, USA and is known for its Transformers library',
-    meta: {'entities': [
-            {'entity': 'Hugging Face', 'entity_type': 'company'}, {'entity': 'New York', 'entity_type': 'city'},
-            {'entity': 'USA', 'entity_type': 'country'}, {'entity': 'Transformers', 'entity_type': 'product'}
-            ]})
-       ]
-    'failed_documents': []
-   }
->>
+# >> {'documents': [
+# >>    Document(id=.., content: 'deepset was founded in 2018 in Berlin, and is known for its Haystack framework',
+# >>    meta: {'entities': [{'entity': 'deepset', 'entity_type': 'company'}, {'entity': 'Berlin', 'entity_type': 'city'},
+# >>          {'entity': 'Haystack', 'entity_type': 'product'}]}),
+# >>    Document(id=.., content: 'Hugging Face is a company that was founded in New York, USA and is known for its Transformers library',
+# >>    meta: {'entities': [
+# >>            {'entity': 'Hugging Face', 'entity_type': 'company'}, {'entity': 'New York', 'entity_type': 'city'},
+# >>            {'entity': 'USA', 'entity_type': 'country'}, {'entity': 'Transformers', 'entity_type': 'product'}
+# >>            ]})
+# >>       ]
+# >>    'failed_documents': []
+# >>   }
+# >>>>
 ```
 
 #### __init__

docs-website/reference/haystack-api/generators_api.md

@@ -746,7 +746,7 @@ print(result)
 
 #### With paid inference endpoints
 
-````python
+```python
 from haystack.components.generators.chat import HuggingFaceAPIChatGenerator
 from haystack.dataclasses import ChatMessage
 from haystack.utils import Secret
@@ -760,9 +760,11 @@ generator = HuggingFaceAPIChatGenerator(api_type="inference_endpoints",
 
 result = generator.run(messages)
 print(result)
+```
 
 #### With self-hosted text generation inference
 
+
 ```python
 from haystack.components.generators.chat import HuggingFaceAPIChatGenerator
 from haystack.dataclasses import ChatMessage
@@ -775,7 +777,7 @@ generator = HuggingFaceAPIChatGenerator(api_type="text_generation_inference",
 
 result = generator.run(messages)
 print(result)
-````
+```
 
 #### __init__
 
@@ -2136,11 +2138,11 @@ client = OpenAIGenerator()
 response = client.run("What's Natural Language Processing? Be brief.")
 print(response)
 
->> {'replies': ['Natural Language Processing (NLP) is a branch of artificial intelligence that focuses on
->> the interaction between computers and human language. It involves enabling computers to understand, interpret,
->> and respond to natural human language in a way that is both meaningful and useful.'], 'meta': [{'model':
->> 'gpt-5-mini', 'index': 0, 'finish_reason': 'stop', 'usage': {'prompt_tokens': 16,
->> 'completion_tokens': 49, 'total_tokens': 65}}]}
+# >> {'replies': ['Natural Language Processing (NLP) is a branch of artificial intelligence that focuses on
+# >> the interaction between computers and human language. It involves enabling computers to understand, interpret,
+# >> and respond to natural human language in a way that is both meaningful and useful.'], 'meta': [{'model':
+# >> 'gpt-5-mini', 'index': 0, 'finish_reason': 'stop', 'usage': {'prompt_tokens': 16,
+# >> 'completion_tokens': 49, 'total_tokens': 65}}]}
 ```
 
 #### __init__

docs-website/reference/haystack-api/joiners_api.md

@@ -49,8 +49,8 @@ messages = [ChatMessage.from_system("You are a helpful, respectful and honest as
             ChatMessage.from_user(query)]
 
 pipe = Pipeline()
-pipe.add_component("llm_1", OpenAIChatGenerator()
-pipe.add_component("llm_2", OpenAIChatGenerator()
+pipe.add_component("llm_1", OpenAIChatGenerator())
+pipe.add_component("llm_2", OpenAIChatGenerator())
 pipe.add_component("aba", AnswerBuilder())
 pipe.add_component("abb", AnswerBuilder())
 pipe.add_component("joiner", AnswerJoiner())
@@ -198,9 +198,8 @@ result = pipe.run(
 
 print(json.loads(result["validator"]["validated"][0].text))
 
-
->> {'first_name': 'Peter', 'last_name': 'Parker', 'nationality': 'American', 'name': 'Spider-Man', 'occupation':
->> 'Superhero', 'age': 23, 'location': 'New York City'}
+# >> {'first_name': 'Peter', 'last_name': 'Parker', 'nationality': 'American', 'name': 'Spider-Man', 'occupation':
+# >> 'Superhero', 'age': 23, 'location': 'New York City'}
 ```
 
 Note that `BranchJoiner` can manage only one data type at a time. In this case, `BranchJoiner` is created for
@@ -529,9 +528,6 @@ from haystack.components.joiners import StringJoiner
 from haystack.components.builders import PromptBuilder
 from haystack.core.pipeline import Pipeline
 
-from haystack.components.generators.chat import OpenAIChatGenerator
-from haystack.dataclasses import ChatMessage
-
 string_1 = "What's Natural Language Processing?"
 string_2 = "What is life?"
 
@@ -545,7 +541,7 @@ pipeline.connect("prompt_builder_2.prompt", "string_joiner.strings")
 
 print(pipeline.run(data={"prompt_builder_1": {"query": string_1}, "prompt_builder_2": {"query": string_2}}))
 
->> {"string_joiner": {"strings": ["Builder 1: What's Natural Language Processing?", "Builder 2: What is life?"]}}
+# >> {"string_joiner": {"strings": ["Builder 1: What's Natural Language Processing?", "Builder 2: What is life?"]}}
 ```
 
 #### run

docs-website/reference/haystack-api/preprocessors_api.md

@@ -660,13 +660,13 @@ from haystack.components.preprocessors import HierarchicalDocumentSplitter
 doc = Document(content="This is a simple test document")
 splitter = HierarchicalDocumentSplitter(block_sizes={3, 2}, split_overlap=0, split_by="word")
 splitter.run([doc])
->> {'documents': [Document(id=3f7..., content: 'This is a simple test document', meta: {'block_size': 0, 'parent_id': None, 'children_ids': ['5ff..', '8dc..'], 'level': 0}),
->> Document(id=5ff.., content: 'This is a ', meta: {'block_size': 3, 'parent_id': '3f7..', 'children_ids': ['f19..', '52c..'], 'level': 1, 'source_id': '3f7..', 'page_number': 1, 'split_id': 0, 'split_idx_start': 0}),
->> Document(id=8dc.., content: 'simple test document', meta: {'block_size': 3, 'parent_id': '3f7..', 'children_ids': ['39d..', 'e23..'], 'level': 1, 'source_id': '3f7..', 'page_number': 1, 'split_id': 1, 'split_idx_start': 10}),
->> Document(id=f19.., content: 'This is ', meta: {'block_size': 2, 'parent_id': '5ff..', 'children_ids': [], 'level': 2, 'source_id': '5ff..', 'page_number': 1, 'split_id': 0, 'split_idx_start': 0}),
->> Document(id=52c.., content: 'a ', meta: {'block_size': 2, 'parent_id': '5ff..', 'children_ids': [], 'level': 2, 'source_id': '5ff..', 'page_number': 1, 'split_id': 1, 'split_idx_start': 8}),
->> Document(id=39d.., content: 'simple test ', meta: {'block_size': 2, 'parent_id': '8dc..', 'children_ids': [], 'level': 2, 'source_id': '8dc..', 'page_number': 1, 'split_id': 0, 'split_idx_start': 0}),
->> Document(id=e23.., content: 'document', meta: {'block_size': 2, 'parent_id': '8dc..', 'children_ids': [], 'level': 2, 'source_id': '8dc..', 'page_number': 1, 'split_id': 1, 'split_idx_start': 12})]}
+# >> {'documents': [Document(id=3f7..., content: 'This is a simple test document', meta: {'block_size': 0, 'parent_id': None, 'children_ids': ['5ff..', '8dc..'], 'level': 0}),
+# >> Document(id=5ff.., content: 'This is a ', meta: {'block_size': 3, 'parent_id': '3f7..', 'children_ids': ['f19..', '52c..'], 'level': 1, 'source_id': '3f7..', 'page_number': 1, 'split_id': 0, 'split_idx_start': 0}),
+# >> Document(id=8dc.., content: 'simple test document', meta: {'block_size': 3, 'parent_id': '3f7..', 'children_ids': ['39d..', 'e23..'], 'level': 1, 'source_id': '3f7..', 'page_number': 1, 'split_id': 1, 'split_idx_start': 10}),
+# >> Document(id=f19.., content: 'This is ', meta: {'block_size': 2, 'parent_id': '5ff..', 'children_ids': [], 'level': 2, 'source_id': '5ff..', 'page_number': 1, 'split_id': 0, 'split_idx_start': 0}),
+# >> Document(id=52c.., content: 'a ', meta: {'block_size': 2, 'parent_id': '5ff..', 'children_ids': [], 'level': 2, 'source_id': '5ff..', 'page_number': 1, 'split_id': 1, 'split_idx_start': 8}),
+# >> Document(id=39d.., content: 'simple test ', meta: {'block_size': 2, 'parent_id': '8dc..', 'children_ids': [], 'level': 2, 'source_id': '8dc..', 'page_number': 1, 'split_id': 0, 'split_idx_start': 0}),
+# >> Document(id=e23.., content: 'document', meta: {'block_size': 2, 'parent_id': '8dc..', 'children_ids': [], 'level': 2, 'source_id': '8dc..', 'page_number': 1, 'split_id': 1, 'split_idx_start': 12})]}
 ```
 
 #### __init__
@@ -861,12 +861,10 @@ AI technology is widely used throughout industry, government, and science. Some
 doc = Document(content=text)
 doc_chunks = chunker.run([doc])
 print(doc_chunks["documents"])
->[
->Document(id=..., content: 'Artificial intelligence (AI) - Introduction\n\n', meta: {'original_id': '...', 'split_id': 0, 'split_idx_start': 0, '_split_overlap': []})
->Document(id=..., content: 'AI, in its broadest sense, is intelligence exhibited by machines, particularly computer systems.\n', meta: {'original_id': '...', 'split_id': 1, 'split_idx_start': 45, '_split_overlap': []})
->Document(id=..., content: 'AI technology is widely used throughout industry, government, and science.', meta: {'original_id': '...', 'split_id': 2, 'split_idx_start': 142, '_split_overlap': []})
->Document(id=..., content: ' Some high-profile applications include advanced web search engines; recommendation systems; interac...', meta: {'original_id': '...', 'split_id': 3, 'split_idx_start': 216, '_split_overlap': []})
->]
+# >>[Document(id=..., content: 'Artificial intelligence (AI) - Introduction\n\n', meta: {'original_id': '...', 'split_id': 0, 'split_idx_start': 0, '_split_overlap': []})
+# >>Document(id=..., content: 'AI, in its broadest sense, is intelligence exhibited by machines, particularly computer systems.\n', meta: {'original_id': '...', 'split_id': 1, 'split_idx_start': 45, '_split_overlap': []})
+# >>Document(id=..., content: 'AI technology is widely used throughout industry, government, and science.', meta: {'original_id': '...', 'split_id': 2, 'split_idx_start': 142, '_split_overlap': []})
+# >>Document(id=..., content: ' Some high-profile applications include advanced web search engines; recommendation systems; interac...', meta: {'original_id': '...', 'split_id': 3, 'split_idx_start': 216, '_split_overlap': []})]
 ```
 
 #### __init__

docs-website/reference/haystack-api/rankers_api.md

@@ -47,8 +47,8 @@ result = reranker.run(query="What is the capital of France?", documents=docs)
 
 ranked_docs = result["documents"]
 print(ranked_docs)
->> {'documents': [Document(id=..., content: 'the capital of France is Paris', score: 0.9979767),
->>                Document(id=..., content: 'the capital of Germany is Berlin', score: 0.13982213)]}
+# >> {'documents': [Document(id=..., content: 'the capital of France is Paris', score: 0.9979767),
+# >>                Document(id=..., content: 'the capital of Germany is Berlin', score: 0.13982213)]}
 ```
 
 #### __init__

docs-website/reference/haystack-api/routers_api.md

@@ -516,12 +516,12 @@ Categorize files or byte streams according to their MIME types.
 
 ### LLMMessagesRouter
 
-````
 Routes Chat Messages to different connections using a generative Language Model to perform classification.
 
 This component can be used with general-purpose LLMs and with specialized LLMs for moderation like Llama Guard.
 
 ### Usage example
+
 ```python
 from haystack.components.generators.chat import HuggingFaceAPIChatGenerator
 from haystack.components.routers.llm_messages_router import LLMMessagesRouter
@@ -530,32 +530,21 @@ from haystack.dataclasses import ChatMessage
 # initialize a Chat Generator with a generative model for moderation
 chat_generator = HuggingFaceAPIChatGenerator(
     api_type="serverless_inference_api",
-    api_params={"model": "meta-llama/Llama-Guard-4-12B", "provider": "groq"},
+    api_params={"model": "openai/gpt-oss-safeguard-20b"},
 )
 
-router = LLMMessagesRouter(chat_generator=chat_generator,
-                            output_names=["unsafe", "safe"],
-                            output_patterns=["unsafe", "safe"])
-
+router = LLMMessagesRouter(
+  chat_generator=chat_generator, output_names=["unsafe", "safe"], output_patterns=["unsafe", "safe"]
+)
 
 print(router.run([ChatMessage.from_user("How to rob a bank?")]))
 
-# {
-#     'chat_generator_text': 'unsafe
-````
-
-S2',
-\# 'unsafe': \[
-\# ChatMessage(
-\# \_role=\<ChatRole.USER: 'user'>,
-\# \_content=[TextContent(text='How to rob a bank?')],
-\# \_name=None,
-\# \_meta={}
-\# )
-\# \]
-\# }
-\`\`\`
+# >> {'chat_generator_text': 'I’m sorry, but I can’t help with that.',
+# >>  'unmatched': [ChatMessage(_role=<ChatRole.USER: 'user'>,
+# >>  _content=[TextContent(text='How to rob a bank?')], _name=None, _meta={})]
+# }
 
+```
 #### __init__
 
 ```python

docs-website/reference/haystack-api/tools_api.md

@@ -212,20 +212,20 @@ def get_weather(
 tool = create_tool_from_function(get_weather)
 
 print(tool)
->>> Tool(name='get_weather', description='A simple function to get the current weather for a location.',
->>> parameters={
->>> 'type': 'object',
->>> 'properties': {
->>>     'city': {'type': 'string', 'description': 'the city for which to get the weather', 'default': 'Munich'},
->>>     'unit': {
->>>         'type': 'string',
->>>         'enum': ['Celsius', 'Fahrenheit'],
->>>         'description': 'the unit for the temperature',
->>>         'default': 'Celsius',
->>>     },
->>>     }
->>> },
->>> function=<function get_weather at 0x7f7b3a8a9b80>)
+# >> Tool(name='get_weather', description='A simple function to get the current weather for a location.',
+# >> parameters={
+# >> 'type': 'object',
+# >> 'properties': {
+# >>     'city': {'type': 'string', 'description': 'the city for which to get the weather', 'default': 'Munich'},
+# >>     'unit': {
+# >>         'type': 'string',
+# >>         'enum': ['Celsius', 'Fahrenheit'],
+# >>         'description': 'the unit for the temperature',
+# >>         'default': 'Celsius',
+# >>     },
+# >>     }
+# >> },
+# >> function=<function get_weather at 0x7f7b3a8a9b80>)
 ```
 
 **Parameters:**
@@ -339,20 +339,20 @@ def get_weather(
     return f"Weather report for {city}: 20 {unit}, sunny"
 
 print(get_weather)
->>> Tool(name='get_weather', description='A simple function to get the current weather for a location.',
->>> parameters={
->>> 'type': 'object',
->>> 'properties': {
->>>     'city': {'type': 'string', 'description': 'the city for which to get the weather', 'default': 'Munich'},
->>>     'unit': {
->>>         'type': 'string',
->>>         'enum': ['Celsius', 'Fahrenheit'],
->>>         'description': 'the unit for the temperature',
->>>         'default': 'Celsius',
->>>     },
->>>     }
->>> },
->>> function=<function get_weather at 0x7f7b3a8a9b80>)
+# >> Tool(name='get_weather', description='A simple function to get the current weather for a location.',
+# >> parameters={
+# >> 'type': 'object',
+# >> 'properties': {
+# >>     'city': {'type': 'string', 'description': 'the city for which to get the weather', 'default': 'Munich'},
+# >>     'unit': {
+# >>         'type': 'string',
+# >>         'enum': ['Celsius', 'Fahrenheit'],
+# >>         'description': 'the unit for the temperature',
+# >>         'default': 'Celsius',
+# >>     },
+# >>     }
+# >> },
+# >> function=<function get_weather at 0x7f7b3a8a9b80>)
 ```
 
 **Parameters:**
@@ -662,8 +662,8 @@ from haystack.tools import Tool, SearchableToolset
 
 # Create a catalog of tools
 catalog = [
-    Tool(name="get_weather", description="Get weather for a city", ...),
-    Tool(name="search_web", description="Search the web", ...),
+    Tool(name="get_weather", description="Get weather for a city"),
+    Tool(name="search_web", description="Search the web"),
     # ... 100s more tools
 ]
 toolset = SearchableToolset(catalog=catalog)