import os
from graphora import GraphoraClient

client = GraphoraClient(
    auth_token=os.environ["GRAPHORA_AUTH_TOKEN"],
)

# Use a previously registered ontology
ontology_id = "ont_123456789"

# Prepare a list of document files to transform
document_paths = [
    "document1.pdf",
    "document2.docx",
    "document3.txt"
]

# Transform the documents
response = client.transform(ontology_id, document_paths)
print(f"Transformation started with ID: {response.id}")

# Check the status of the transformation
status = client.get_transform_status(response.id)
print(f"Transformation status: {status.status}")
print(f"Progress: {status.progress:.2%}")

import os
from graphora import GraphoraClient, DocumentMetadata, DocumentType

client = GraphoraClient(
    auth_token=os.environ["GRAPHORA_AUTH_TOKEN"],
)

# Use a previously registered ontology
ontology_id = "ont_123456789"

# Prepare document paths and metadata
document_paths = [
    "document1.pdf",
    "document2.docx"
]

metadata = [
    DocumentMetadata(
        source="Annual Report 2024",
        document_type=DocumentType.PDF,
        tags=["finance", "annual", "report"],
        custom_metadata={
            "department": "Finance",
            "confidentiality": "Internal"
        }
    ),
    DocumentMetadata(
        source="Product Specifications",
        document_type=DocumentType.DOCX,
        tags=["product", "specifications", "technical"],
        custom_metadata={
            "department": "Engineering",
            "product_id": "PRD-2024-001"
        }
    )
]

# Transform the documents with metadata
response = client.transform(ontology_id, document_paths, metadata=metadata)
print(f"Transformation started with ID: {response.id}")

import os
import time
from graphora import GraphoraClient, TransformRunStatus

client = GraphoraClient(
    auth_token=os.environ["GRAPHORA_AUTH_TOKEN"],
)

# Start a transformation (assuming you have already set up the ontology and documents)
transform_response = client.transform(ontology_id, document_paths)
transform_id = transform_response.id

# Monitor the transformation progress
completed = False
while not completed:
    status = client.get_transform_status(transform_id)
    print(
        f"{status.current_stage} | {status.overall_status} | "
        f"{status.percentage_complete:.1f}%"
    )

    if status.overall_status in (
        TransformRunStatus.COMPLETED,
        TransformRunStatus.FAILED,
    ):
        completed = True
        if status.overall_status == TransformRunStatus.COMPLETED:
            print("Transformation completed successfully!")
        else:
            failure = status.error_summary.error_message if status.error_summary else "Unknown error"
            print(f"Transformation failed: {failure}")
    else:
        # Wait for 5 seconds before checking again
        time.sleep(5)

# If transformation was successful, you can proceed to merging
if status.status == "COMPLETED":
    print("Ready to merge the transformed data into a graph")

import os
from graphora import GraphoraClient

client = GraphoraClient(
    auth_token=os.environ["GRAPHORA_AUTH_TOKEN"],
)

# Start a transformation
transform_response = client.transform(ontology_id, document_paths)
transform_id = transform_response.id

# Wait for completion (with timeout)
try:
    final_status = client.wait_for_transform(transform_id, timeout=300)  # 5 minutes
    print(f"Transformation completed with status: {final_status.overall_status}")
except Exception as e:
    print(f"Transformation failed or timed out: {e}")

import os
from graphora import GraphoraClient

client = GraphoraClient(
    auth_token=os.environ["GRAPHORA_AUTH_TOKEN"],
)

# Use a previously registered ontology
ontology_id = "ont_123456789"

# Prepare a list of different document types
documents = [
    "text_document.txt",      # Plain text
    "word_document.docx",     # Microsoft Word
    "pdf_document.pdf",       # PDF
    "data.csv",               # CSV
    "config.json",            # JSON
    "schema.yaml"             # YAML
]

# Transform the documents
response = client.transform(ontology_id, documents)
print(f"Transformation started with ID: {response.id}")