Data Management

documents_to_upload = [
    {"id": "faq-1", "text": "To reset your password, go to the account settings page.", "category": "account"},
    {"id": "faq-2", "text": "Our return policy allows returns within 30 days of purchase.", "category": "shipping"}
]

status = client.documents.upload(
    namespace_name="my-faq-documents",
    documents=documents_to_upload
)
print(status)

vectors_to_upload = [
    {"id": "image_001.jpg", "vector": [0.12, -0.45, ...], "metadata": {"source": "product_database"}},
    {"id": "image_002.jpg", "vector": [-0.22, 0.81, ...], "metadata": {"source": "product_database"}}
]

status = client.vectors.upload(
    namespace_name="my-image-embeddings",
    vectors=vectors_to_upload
)
print(status)

# Delete specific documents by ID
result = client.documents.delete(
    namespace_name="my-faq-documents",
    ids=["faq-1", "faq-3", "faq-5"]
)
print(f"Deletion result: {result}")

# Delete specific vectors by ID
result = client.vectors.delete(
    namespace_name="my-image-embeddings",
    ids=["image_001.jpg", "image_002.jpg"]
)
print(f"Deletion result: {result}")

from moorcheh_sdk import MoorchehClient
import time

with MoorchehClient() as client:
    # 1. Create a namespace
    client.namespaces.create("my-data", type="text")

    # 2. Upload documents
    docs = [
        {
            "id": "doc-1",
            "text": "This is the first document",
            "category": "tutorial",
            "author": "John Doe"
        },
        {
            "id": "doc-2",
            "text": "This is the second document",
            "category": "guide",
            "author": "Jane Smith"
        }
    ]

    upload_result = client.documents.upload(namespace_name="my-data", documents=docs)
    print(f"Upload status: {upload_result}")

    # 3. Wait for processing (text documents need time to be embedded)
    print("Waiting for document processing...")
    time.sleep(5)

    # 4. Delete specific documents if needed
    delete_result = client.documents.delete(namespace_name="my-data", ids=["doc-1"])
    print(f"Delete result: {delete_result}")

documents = [
    {
        "id": "article-123",
        "text": "Full article content here...",
        # Metadata fields : The other kwargs are considered as metadata
        "title": "Introduction to Machine Learning",
        "author": "Dr. Smith",
        "category": "education",
        "publish_date": "2024-01-15",
        "tags": ["ml", "ai", "tutorial"],
        "difficulty": "beginner"
    }
]

vectors = [
    {
        "id": "embedding-1",
        "vector": [0.1, 0.2, 0.3, ...],  # Must match namespace dimension
        # Optional metadata
        "source": "image_database",
        "category": "product",
        "confidence": 0.95
    }
]