diff --git a/docs-website/reference/haystack-api/audio_api.md b/docs-website/reference/haystack-api/audio_api.md
index fd7e95b1043..394c7877bbe 100644
--- a/docs-website/reference/haystack-api/audio_api.md
+++ b/docs-website/reference/haystack-api/audio_api.md
@@ -18,13 +18,15 @@ For the supported audio formats, languages, and other parameters, see the
### Usage example
-
-
```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'})]}
```
#### __init__
diff --git a/docs-website/reference/haystack-api/converters_api.md b/docs-website/reference/haystack-api/converters_api.md
index dd0f1a02cda..f5f4d1e0f7d 100644
--- a/docs-website/reference/haystack-api/converters_api.md
+++ b/docs-website/reference/haystack-api/converters_api.md
@@ -385,17 +385,13 @@ Converts files to FileContent objects to be included in ChatMessage objects.
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={})
+# >>]
```
#### run
@@ -537,32 +533,33 @@ Documents are expected to have metadata containing:
### Usage example
-
-
```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})
# )]
```
diff --git a/docs-website/reference/haystack-api/extractors_api.md b/docs-website/reference/haystack-api/extractors_api.md
index 55b9b372fa9..5196eefb777 100644
--- a/docs-website/reference/haystack-api/extractors_api.md
+++ b/docs-website/reference/haystack-api/extractors_api.md
@@ -469,8 +469,6 @@ in the documents.
Usage example:
-
-
```python
from haystack import Document
from haystack.components.extractors.named_entity_extractor import NamedEntityExtractor
@@ -483,6 +481,10 @@ extractor = NamedEntityExtractor(backend="hugging_face", model="dslim/bert-base-
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))]]
```
#### __init__
diff --git a/docs-website/reference/haystack-api/generators_api.md b/docs-website/reference/haystack-api/generators_api.md
index 9b420e13ef4..87aa43939de 100644
--- a/docs-website/reference/haystack-api/generators_api.md
+++ b/docs-website/reference/haystack-api/generators_api.md
@@ -32,15 +32,15 @@ For details on OpenAI API parameters, see
```python
from haystack.components.generators import AzureOpenAIGenerator
from haystack.utils import Secret
+
client = AzureOpenAIGenerator(
- azure_endpoint="",
- api_key=Secret.from_token(""),
- azure_deployment="")
+ 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':
@@ -708,8 +708,6 @@ format for input and output. Use it to generate text with Hugging Face APIs:
#### With the serverless inference API (Inference Providers) - free tier available
-
-
```python
from haystack.components.generators.chat import HuggingFaceAPIChatGenerator
from haystack.dataclasses import ChatMessage
@@ -717,19 +715,25 @@ 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(""))
+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=,
+# >> _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
@@ -743,7 +747,7 @@ from haystack.utils import Secret
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])]
@@ -751,10 +755,9 @@ messages = [ChatMessage.from_user(content_parts=["Describe this image in detail"
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("")
+ token=Secret.from_env_var("HF_API_TOKEN")
)
result = generator.run(messages)
diff --git a/docs-website/reference/haystack-api/image_converters_api.md b/docs-website/reference/haystack-api/image_converters_api.md
index eb4415f7c6d..11d61480767 100644
--- a/docs-website/reference/haystack-api/image_converters_api.md
+++ b/docs-website/reference/haystack-api/image_converters_api.md
@@ -24,32 +24,33 @@ Documents are expected to have metadata containing:
### Usage example
-
-
```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})
# )]
```