Oracle Cloud Infrastructure Documentation

Analyzing Documents by Using a Single Request

Organize and extract text and structure from image-based documents and PDFs by calling the Document AI pretrained models with a single request in Vision.

The maximum size of each image is 5 MB.

To classify images in batch, see Analyzing Documents by Using a Batch Request. For more information about the image classification pretrained model, see Pretrained Image Analysis Models.

    1. Open the navigation menu and click Analytics & AI. Under AI Services, click Vision.
    2. On the Vision page, click Document AI.
    3. Select the compartment where you want to store the results.
    4. Select the location of the image, either Local file or Object storage.
    5. (Optional) If you selected Local file, drag the file to the Drop a file are, or click select one... and browse to the image.
    6. (Optional) If you selected Object storage, enter the image URL and click Upload.

      The analyzeDocument API is invoked, and the model immediately analyzes the image. The Results area shows the the document type, language, extracted text, and the request and response JSON.

  • Use the analyze-document command and required parameters to analyze the document:

    oci ai-vision analyze-document [OPTIONS]
    For a complete list of flags and variable options for CLI commands, see the CLI Command Reference.

  • Run the AnalyzeDocument operation to analyze a document.