Integration: Azure Form Recognizer
Convert files to Documents using Azure's Document Intelligence service (Form Recognizer SDK)
Table of Contents
Overview
AzureOCRDocumentConverter converts files to Haystack Documents using
Azure’s Document Intelligence service through the
azure-ai-formrecognizer SDK.
Supported file formats: PDF, JPEG, PNG, BMP, TIFF, DOCX, XLSX, PPTX, HTML.
Unlike the
AzureDocumentIntelligenceConverter (which produces Markdown), this component extracts tables as separate Document objects that preserve their two-dimensional (CSV) structure, and returns the remaining text with page breaks (\f) so it can be split per page by downstream preprocessors.
You need an active Azure account and a Document Intelligence or Cognitive Services resource. Follow the Azure setup guide to create your resource.
Installation
pip install azure-form-recognizer-haystack
Usage
Provide your service endpoint and an API key. By default the component reads the key from the AZURE_AI_API_KEY environment variable.
import os
from haystack_integrations.components.converters.azure_form_recognizer import AzureOCRDocumentConverter
from haystack.utils import Secret
converter = AzureOCRDocumentConverter(
endpoint=os.environ["AZURE_AI_ENDPOINT"],
api_key=Secret.from_env_var("AZURE_AI_API_KEY"),
)
results = converter.run(sources=["document.pdf"])
documents = results["documents"]
print(documents[0].content)
In a pipeline
from haystack import Pipeline
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.components.preprocessors import DocumentCleaner, DocumentSplitter
from haystack.components.writers import DocumentWriter
from haystack.utils import Secret
from haystack_integrations.components.converters.azure_form_recognizer import AzureOCRDocumentConverter
document_store = InMemoryDocumentStore()
pipeline = Pipeline()
pipeline.add_component("converter", AzureOCRDocumentConverter(endpoint="azure_resource_url", api_key=Secret.from_env_var("AZURE_AI_API_KEY")))
pipeline.add_component("cleaner", DocumentCleaner())
pipeline.add_component("splitter", DocumentSplitter(split_by="sentence", split_length=5))
pipeline.add_component("writer", DocumentWriter(document_store=document_store))
pipeline.connect("converter", "cleaner")
pipeline.connect("cleaner", "splitter")
pipeline.connect("splitter", "writer")
pipeline.run({"converter": {"sources": ["my_file.pdf"]}})