Azure AI Document Intelligence client library for Python - a cloud service that uses machine learning to analyze text and structured data from documents
76
{
"context": "Evaluates whether the solution uses azure-ai-documentintelligence to classify documents by classifier_id, including optional page filtering and per-page routing, and derives routing metadata from the service results.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Client setup",
"description": "Creates a DocumentIntelligenceClient (or aio equivalent) from azure.ai.documentintelligence with a proper Azure credential for invoking begin_classify_document.",
"max_score": 15
},
{
"name": "Classification call",
"description": "Invokes begin_classify_document with the provided classifier_id and document source (stream/bytes/path/URL) and waits for poller.result() to obtain an AnalyzeResult.",
"max_score": 30
},
{
"name": "Page filtering",
"description": "Passes the pages argument from input through to begin_classify_document so the service restricts classification to the requested page ranges.",
"max_score": 15
},
{
"name": "Per-page split",
"description": "When per-page routing is requested, sets split_mode to \"perPage\" or SplitMode.PER_PAGE on begin_classify_document to force page-level classifications.",
"max_score": 20
},
{
"name": "Result parsing",
"description": "Builds output doc_type, confidence, and page lists by reading AnalyzeResult.documents entries (and associated pages/spans) returned by begin_classify_document instead of inferring them locally.",
"max_score": 20
}
]
}Install with Tessl CLI
npx tessl i tessl/pypi-azure-ai-documentintelligencedocs
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10