Azure Document Intelligence extracts text from files in the following formats:

JPEG
PNG
BMP
TIFF
DOCX
XLSX
PPTX
HTML

For more details on the service capabilities, see the Azure Document Intelligence website. For a list of models you can use to process your files, see model overview in Document Intelligence documentation.

Prerequisites

You need an API key from your Azure account with the Document Intelligence resource. For details, see Get started wtih Document Intelligence in Azure documentation.

Use Azure Document Intelligence

First, connect deepset Cloud to Azure Document Intelligence through the Connections page:

Click your initials in the top right corner and select Connections.
Click Connect next to the provider.
Enter your user access token and submit it.

Then, add the AzureOCRDocumentConverter component to your indexing pipeline.

Usage Examples

This is an example of an indexing pipeline that uses Azure's OCR converter to process PDF files:

components:
  file_classifier:
    type: haystack.components.routers.file_type_router.FileTypeRouter
    init_parameters:
      mime_types:
      - text/plain
      - application/pdf
      - text/markdown
      - text/html
      - application/vnd.openxmlformats-officedocument.wordprocessingml.document
      - application/vnd.openxmlformats-officedocument.presentationml.presentation

  text_converter:
    type: haystack.components.converters.txt.TextFileToDocument
    init_parameters:
      encoding: utf-8

  ocr_converter: #This is the Azure OCR converter
    type: haystack.components.converters.azure.AzureOCRDocumentConverter
    init_parameters:
      api_key: {"type": "env_var", "env_vars": ["AZURE_AI_API_KEY"], "strict": false}
      endpoint: "YOUR-ENDPOINT"
      model_id: "prebuilt-read"
      page_layout: "natural"

  markdown_converter:
    type: haystack.components.converters.markdown.MarkdownToDocument
    init_parameters:
      table_to_single_line: false

  html_converter:
    type: haystack.components.converters.html.HTMLToDocument
    init_parameters:
      # A dictionary of keyword arguments to customize how you want to extract content from your HTML files.
      # For the full list of available arguments, see
      # the [Trafilatura documentation](https://trafilatura.readthedocs.io/en/latest/corefunctions.html#extract).
      extraction_kwargs:
        output_format: txt  # Extract text from HTML. You can also also choose "markdown"
        target_language: null  # You can define a language (using the ISO 639-1 format) to discard documents that don't match that language.
        include_tables: true  # If true, includes tables in the output
        include_links: false  # If true, keeps links along with their targets

  docx_converter:
    type: haystack.components.converters.docx.DOCXToDocument
    init_parameters: {}

  pptx_converter:
    type: haystack.components.converters.pptx.PPTXToDocument
    init_parameters: {}

  joiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate
      sort_by_score: false

  splitter:
    type: deepset_cloud_custom_nodes.preprocessors.document_splitter.DeepsetDocumentSplitter
    init_parameters:
      split_by: word
      split_length: 250
      split_overlap: 30
      respect_sentence_boundary: True
      language: en

  document_embedder:
    type: haystack.components.embedders.sentence_transformers_document_embedder.SentenceTransformersDocumentEmbedder
    init_parameters:
      model: "intfloat/e5-base-v2"

  writer:
    type: haystack.components.writers.document_writer.DocumentWriter
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          embedding_dim: 768
          similarity: cosine
      policy: OVERWRITE

connections:  # Defines how the components are connected
- sender: file_classifier.text/plain
  receiver: text_converter.sources
- sender: file_classifier.application/pdf
  receiver: ocr_converter.sources # Azure converter receives PDF files
- sender: file_classifier.text/markdown
  receiver: markdown_converter.sources
- sender: file_classifier.text/html
  receiver: html_converter.sources
- sender: file_classifier.application/vnd.openxmlformats-officedocument.wordprocessingml.document
  receiver: docx_converter.sources
- sender: file_classifier.application/vnd.openxmlformats-officedocument.presentationml.presentation
  receiver: pptx_converter.sources
- sender: text_converter.documents
  receiver: joiner.documents
- sender: ocr_converter.documents #It then sends the resulting documents to DocumentJoiner
  receiver: joiner.documents
- sender: markdown_converter.documents
  receiver: joiner.documents
- sender: html_converter.documents
  receiver: joiner.documents
- sender: docx_converter.documents
  receiver: joiner.documents
- sender: pptx_converter.documents
  receiver: joiner.documents
- sender: joiner.documents
  receiver: splitter.documents
- sender: splitter.documents
  receiver: document_embedder.documents
- sender: document_embedder.documents
  receiver: writer.documents

max_loops_allowed: 100

inputs:  # Define the inputs for your pipeline
  files: "file_classifier.sources"  # This component will receive the files to index as input