Bootstrap a Taxonomy with AI

from unstructured import UnstructuredClient

client = UnstructuredClient(
    base_url="https://unstructured.your-company.com/rest/unstructured",
    username="your-username",
    password="your-password",
)

# Describe what you want to extract. The AI grounds its suggestions
# in the actual documents behind the data connector.
suggestions = client.taxonomy.suggest(
    data_connector_name="my-documents",
    user_context="""
    I need to analyze legal contracts. Extract key terms, financial obligations, 
    risk indicators, important dates, and anything relevant for compliance.
    Focus on NDAs, MSAs, and employment agreements.
    """,
    taxonomy_name="legal-contracts",
)

# Review the suggestions
print("🤖 AI-Suggested Taxonomy:")
print(suggestions.suggestion)

🤖 AI-Suggested Taxonomy:
{
  "contract_type": {
    "description": "Primary contract classification: NDA, MSA, SLA, SOW, Employment, Lease",
    "type": "string"
  },
  "parties": {
    "description": "All parties to the contract with their legal names",
    "type": "string"
  },
  "effective_date": {
    "description": "Date when the contract becomes legally binding",
    "type": "date"
  },
  "total_value": {
    "description": "Total monetary value of the contract in USD",
    "type": "number"
  }
}

# Option A: save the suggestion in one call
client.taxonomy.suggest(
    data_connector_name="my-documents",
    user_context="Analyze legal contracts for compliance",
    taxonomy_name="legal-contracts",
    auto_save=True,
)

# Option B: review, then create tags from the suggestion
for name, details in suggestions.suggestion.items():
    client.tags.upsert(tag_data={
        "name": name,
        "description": details["description"],
        "output_type": details["type"],
    })

# The AI analyzes your files to suggest the most relevant tags
suggestions = client.taxonomy.suggest(
    data_connector_name="my-s3-bucket",
    user_context="Extract key data from these vendor invoices",
    file_names=[
        "invoices/sample-invoice-1.pdf",
        "invoices/sample-invoice-2.pdf"
    ]
)

# Get suggestions
response = client.taxonomy.suggest(
    data_connector_name="my-docs",
    user_context="Legal contract analysis",
)

# Create tags from the suggestion
for name, details in response.suggestion.items():
    client.tags.upsert(tag_data={
        "name": name,
        "description": details["description"],
        "output_type": details["type"],
    })

# Add a custom tag the AI might have missed
client.tags.upsert(tag_data={
    "name": "reviewed_by_legal",
    "description": "Whether this contract has been reviewed",
    "output_type": "binary",
})