CtrlK
CommunityDocumentationLog inGet started
Tessl Logo

tessl/pypi-azure-ai-documentintelligence

tessl install tessl/pypi-azure-ai-documentintelligence@1.0.0

Azure AI Document Intelligence client library for Python - a cloud service that uses machine learning to analyze text and structured data from documents

Agent Success

Agent success rate when using this tile

76%

Improvement

Agent success rate improvement when using this tile compared to baseline

1.19x

Baseline

Agent success rate without this tile

64%

rubric.jsonevals/scenario-5/

{
  "context": "Evaluates how well the solution uses azure-ai-documentintelligence to manage the document model lifecycle. Checks correct use of building from blob training data, composing existing models, inspecting catalogs/quotas, deleting models, and checking operation status.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Admin client setup",
      "description": "Initializes DocumentIntelligenceAdministrationClient with the provided endpoint and AzureKeyCredential (or compatible TokenCredential) from azure.ai.documentintelligence.",
      "max_score": 10
    },
    {
      "name": "Build request",
      "description": "Creates a BuildDocumentModelRequest using AzureBlobContentSource and DocumentBuildMode, calls begin_build_document_model with the request, waits for poller.result(), and surfaces model_id/description from the returned DocumentModelDetails.",
      "max_score": 20
    },
    {
      "name": "Compose request",
      "description": "Constructs a ComposeDocumentModelRequest with ordered ComponentDocumentModelDetails, invokes begin_compose_model, waits for the poller to complete, and uses the composed DocumentModelDetails to return model_id and component ordering.",
      "max_score": 20
    },
    {
      "name": "Model listing",
      "description": "Uses list_models to retrieve DocumentModelDetails objects and maps them into summaries containing model_id and created_date_time for the workflow’s models.",
      "max_score": 15
    },
    {
      "name": "Resource quotas",
      "description": "Calls get_resource_details and reads custom_document_models (and/or custom_neural_document_model_builds) count/limit to populate quota information in the response.",
      "max_score": 10
    },
    {
      "name": "Deletion cleanup",
      "description": "Deletes models via delete_model using the supplied identifier and ensures subsequent list_models calls omit the deleted model.",
      "max_score": 10
    },
    {
      "name": "Operation lookup",
      "description": "Resolves operation status by calling get_operation (or list_operations filtered by ID) to return status, last_updated_date_time, and percent_completed from DocumentIntelligenceOperationDetails.",
      "max_score": 15
    }
  ]
}

Version

Workspace
tessl
Visibility
Public
Created
Last updated
Describes
pypipkg:pypi/azure-ai-documentintelligence@1.0.x
tile.json