yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-11-09 14:23:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

update docstrings (#8225)

Browse Source
This commit is contained in:
Agnieszka Marzec 2024-08-14 15:33:21 +02:00 committed by GitHub
parent bcc4104729
commit 9427d7aee6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 23 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
haystack/components/converters/azure.py
View File

@ -27,16 +27,16 @@ with LazyImport(message="Run 'pip install \"azure-ai-formrecognizer>=3.2.0b2\"'"
@component @component
class AzureOCRDocumentConverter: class AzureOCRDocumentConverter:
""" """
Convert files to documents using Azure's Document Intelligence service. Converts files to documents using Azure's Document Intelligence service.
Supported file formats are: PDF, JPEG, PNG, BMP, TIFF, DOCX, XLSX, PPTX, and HTML. Supported file formats are: PDF, JPEG, PNG, BMP, TIFF, DOCX, XLSX, PPTX, and HTML.
In order to be able to use this component, you need an active Azure account To use this component, you need an active Azure account
and a Document Intelligence or Cognitive Services resource. Follow the steps described in the [Azure documentation] and a Document Intelligence or Cognitive Services resource. For help with setting up your resource, see
(https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/quickstarts/get-started-sdks-rest-api) [Azure documentation](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/quickstarts/get-started-sdks-rest-api).
to set up your resource.
### Usage example
Usage example:
```python ```python
from haystack.components.converters import AzureOCRDocumentConverter from haystack.components.converters import AzureOCRDocumentConverter
from haystack.utils import Secret from haystack.utils import Secret
@ -61,30 +61,28 @@ class AzureOCRDocumentConverter:
threshold_y: Optional[float] = 0.05, threshold_y: Optional[float] = 0.05,
): ):
""" """
Create an AzureOCRDocumentConverter component. Creates an AzureOCRDocumentConverter component.
:param endpoint: :param endpoint:
The endpoint of your Azure resource. The endpoint of your Azure resource.
:param api_key: :param api_key:
The key of your Azure resource. The API key of your Azure resource.
:param model_id: :param model_id:
The model ID of the model you want to use. Please refer to [Azure documentation] The ID of the model you want to use. For a list of available models, see [Azure documentation]
(https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/choose-model-feature) (https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/choose-model-feature).
for a list of available models. Default: `"prebuilt-read"`. :param preceding_context_len: Number of lines before a table to include as preceding context
:param preceding_context_len: Number of lines before a table to extract as preceding context (this will be added to the metadata).
(will be returned as part of metadata). :param following_context_len: Number of lines after a table to include as subsequent context (
:param following_context_len: Number of lines after a table to extract as subsequent context ( this will be added to the metadata).
will be returned as part of metadata). :param merge_multiple_column_headers: If `True`, merges multiple column header rows into a single row.
:param merge_multiple_column_headers: Some tables contain more than one row as a column header :param page_layout: The type reading order to follow. Possible options:
(i.e., column description). - `natural`: Uses the natural reading order determined by Azure.
This parameter lets you choose, whether to merge multiple column header rows to a single row. - `single_column`: Groups all lines with the same height on the page based on a threshold
:param page_layout: The type reading order to follow. If "natural" is chosen then the natural reading order determined by `threshold_y`.
determined by Azure will be used. If "single_column" is chosen then all lines with the same height on the :param threshold_y: Only relevant if `single_column` is set to `page_layout`.
page will be grouped together based on a threshold determined by `threshold_y`. The threshold, in inches, to determine if two recognized PDF elements are grouped into a
:param threshold_y: The threshold to determine if two recognized elements in a PDF should be grouped into a single line. This is crucial for section headers or numbers which may be spatially separated
single line. This is especially relevant for section headers or numbers which may be spacially separated from the remaining text on the horizontal axis.
on the horizontal axis from the remaining text. The threshold is specified in units of inches.
This is only relevant if "single_column" is chosen for `page_layout`.
""" """
azure_import.check() azure_import.check()