test: running code snippets from docstring in CI (#11103)

Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>

Author: davidsbatista

haystack/components/audio/whisper_local.py

@@ -40,12 +40,16 @@ class LocalWhisperTranscriber:
     [GitHub repository](https://github.com/openai/whisper).
 
     ### Usage example
-    <!-- test-ignore -->
+
     ```python
     from haystack.components.audio import LocalWhisperTranscriber
 
     whisper = LocalWhisperTranscriber(model="small")
     transcription = whisper.run(sources=["test/test_files/audio/answer.wav"])
+    print(transcription)
+
+    # >> {'documents': [Document(id=dae7051417caaf19304a4ef2ec845e981abe1efd4c8e6ee7ffb25867f165c411,
+    # >> content: ' Answer.', meta: {'audio_file': PosixPath('test/test_files/audio/answer.wav'), 'language': 'en'})]}
     ```
     """
 

haystack/components/converters/file_to_file_content.py

@@ -27,17 +27,13 @@ class FileToFileContent:
     from haystack.components.converters import FileToFileContent
 
     converter = FileToFileContent()
-
-    sources = ["document.pdf", "video.mp4"]
-
+    sources = ["test/test_files/pdf/react_paper.pdf", "test/test_files/images/haystack-logo.png"]
     file_contents = converter.run(sources=sources)["file_contents"]
-    print(file_contents)
 
-    # [FileContent(base64_data='...',
-    #              mime_type='application/pdf',
-    #              filename='document.pdf',
-    #              extra={}),
-    #  ...]
+    print(file_contents)
+    # >> [FileContent(base64_data='...', mime_type='application/pdf', filename='react_paper.pdf', extra={}),
+    # >>  FileContent(base64_data='...', mime_type='image/png', filename='haystack-logo.png', extra={})
+    # >>]
     ```
     """
 

haystack/components/converters/image/document_to_image.py

@@ -34,31 +34,34 @@ class DocumentToImageContent:
     - For PDF files, a `page_number` key specifying which page to extract
 
     ### Usage example
-    <!-- test-ignore -->
+
     ```python
     from haystack import Document
     from haystack.components.converters.image.document_to_image import DocumentToImageContent
 
     converter = DocumentToImageContent(
         file_path_meta_field="file_path",
-        root_path="/data/files",
+        root_path="test/test_files",
         detail="high",
         size=(800, 600)
     )
 
     documents = [
-        Document(content="Optional description of image.jpg", meta={"file_path": "image.jpg"}),
-        Document(content="Text content of page 1 of doc.pdf", meta={"file_path": "doc.pdf", "page_number": 1})
+        Document(content="Optional description of apple.jpg", meta={"file_path": "images/apple.jpg"}),
+        Document(
+            content="Optional description of sample_pdf_1.pdf",
+            meta={"file_path": "pdf/sample_pdf_1.pdf", "page_number": 1}
+        )
     ]
 
     result = converter.run(documents)
     image_contents = result["image_contents"]
     # [ImageContent(
-    #    base64_image='/9j/4A...', mime_type='image/jpeg', detail='high', meta={'file_path': 'image.jpg'}
+    #    base64_image='/9j/4A...', mime_type='image/jpeg', detail='high', meta={'file_path': 'images/apple.jpg'}
     #  ),
     #  ImageContent(
     #    base64_image='/9j/4A...', mime_type='image/jpeg', detail='high',
-    #    meta={'page_number': 1, 'file_path': 'doc.pdf'}
+    #    meta={'file_path': 'pdf/sample_pdf_1.pdf', 'page_number': 1})
     #  )]
     ```
     """

haystack/components/extractors/named_entity_extractor.py

@@ -90,7 +90,7 @@ class NamedEntityExtractor:
     in the documents.
 
     Usage example:
-    <!-- test-ignore -->
+
     ```python
     from haystack import Document
     from haystack.components.extractors.named_entity_extractor import NamedEntityExtractor
@@ -103,6 +103,10 @@ class NamedEntityExtractor:
     results = extractor.run(documents=documents)["documents"]
     annotations = [NamedEntityExtractor.get_stored_annotations(doc) for doc in results]
     print(annotations)
+    # >> [[NamedEntityAnnotation(entity='PER', start=4, end=10, score=np.float32(0.99054915))],
+    # >> [NamedEntityAnnotation(entity='PER', start=11, end=16, score=np.float32(0.99641764)),
+    # >>  NamedEntityAnnotation(entity='LOC', start=31, end=39, score=np.float32(0.996198)),
+    # >>  NamedEntityAnnotation(entity='LOC', start=41, end=51, score=np.float32(0.9990196))]]
     ```
     """
 

haystack/components/generators/azure.py

@@ -28,25 +28,23 @@ class AzureOpenAIGenerator(OpenAIGenerator):
     the component or when you run it. Any parameter that works with
     `openai.ChatCompletion.create` will work here too.
 
-
     For details on OpenAI API parameters, see
     [OpenAI documentation](https://platform.openai.com/docs/api-reference/chat).
 
-
     ### Usage example
     <!-- test-ignore -->
     ```python
     from haystack.components.generators import AzureOpenAIGenerator
     from haystack.utils import Secret
+
     client = AzureOpenAIGenerator(
-        azure_endpoint="<Your Azure endpoint e.g. `https://your-company.azure.openai.com/>",
-        api_key=Secret.from_token("<your-api-key>"),
-        azure_deployment="<this is a model name, e.g. gpt-4.1-mini>")
+        azure_endpoint=Secret.from_env_var("AZURE_OPENAI_ENDPOINT").resolve_value(),
+        api_key=Secret.from_env_var("AZURE_OPENAI_API_KEY"),
+        azure_deployment="gpt-4.1-mini")
+
     response = client.run("What's Natural Language Processing? Be brief.")
-    print(response)
-    ```
 
-    ```
+    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':

haystack/components/generators/chat/hugging_face_api.py

@@ -264,27 +264,33 @@ class HuggingFaceAPIChatGenerator:
     ### Usage examples
 
     #### With the serverless inference API (Inference Providers) - free tier available
-    <!-- test-ignore -->
+
     ```python
     from haystack.components.generators.chat import HuggingFaceAPIChatGenerator
     from haystack.dataclasses import ChatMessage
     from haystack.utils import Secret
     from haystack.utils.hf import HFGenerationAPIType
 
     messages = [ChatMessage.from_system("\\nYou are a helpful, respectful and honest assistant"),
-                ChatMessage.from_user("What's Natural Language Processing?")]
+                ChatMessage.from_user("What's Natural Language Processing? Please be succinct")]
 
     # the api_type can be expressed using the HFGenerationAPIType enum or as a string
     api_type = HFGenerationAPIType.SERVERLESS_INFERENCE_API
     api_type = "serverless_inference_api" # this is equivalent to the above
 
-    generator = HuggingFaceAPIChatGenerator(api_type=api_type,
-                                            api_params={"model": "Qwen/Qwen2.5-7B-Instruct",
-                                                        "provider": "together"},
-                                            token=Secret.from_token("<your-api-key>"))
+    generator = HuggingFaceAPIChatGenerator(
+        api_type=api_type,
+        api_params={"model": "Qwen/Qwen2.5-7B-Instruct", "provider": "together"},
+        token=Secret.from_env_var("HF_API_TOKEN")
+    )
 
     result = generator.run(messages)
     print(result)
+    # >> {'replies': [ChatMessage(_role=<ChatRole.ASSISTANT: 'assistant'>,
+    # >> _content=[TextContent(text='Natural Language Processing (NLP) is a field of AI that focuses on the interaction
+    # >> between humans and computers using natural language. It enables machines to understand, interpret, and
+    # >> generate human language.')], _name=None, _meta={'model': 'Qwen/Qwen2.5-7B-Instruct', 'finish_reason':
+    # >> 'tool_calls', 'index': 0, 'usage': {'prompt_tokens': 33, 'completion_tokens': 39}})]}
     ```
 
     #### With the serverless inference API (Inference Providers) and text+image input
@@ -296,18 +302,17 @@ class HuggingFaceAPIChatGenerator:
     from haystack.utils.hf import HFGenerationAPIType
 
     # Create an image from file path, URL, or base64
-    image = ImageContent.from_file_path("path/to/your/image.jpg")
+    image = ImageContent.from_file_path("test/test_files/images/apple.jpg")
 
     # Create a multimodal message with both text and image
     messages = [ChatMessage.from_user(content_parts=["Describe this image in detail", image])]
 
     generator = HuggingFaceAPIChatGenerator(
         api_type=HFGenerationAPIType.SERVERLESS_INFERENCE_API,
         api_params={
-            "model": "Qwen/Qwen2.5-VL-7B-Instruct",  # Vision Language Model
-            "provider": "hyperbolic"
+            "model": "Qwen/Qwen3.5-9B", "provider": "together"  # Vision Language Model
         },
-        token=Secret.from_token("<your-api-key>")
+        token=Secret.from_env_var("HF_API_TOKEN")
     )
 
     result = generator.run(messages)