> ## Documentation Index
> Fetch the complete documentation index at: https://docs.moorcheh.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Delete Data

> Delete specific documents or vectors from a namespace using the Python SDK

## documents.delete / vectors.delete

Deletes specific documents or vectors from a namespace by their IDs. Use `documents.delete` for text data and `vectors.delete` for vector data.

<Warning>
  This operation permanently deletes data and cannot be undone. Deleted items will decrement your total item count.
</Warning>

### Parameters

<ParamField query="namespace_name" type="str" required>
  The name of the target namespace.
</ParamField>

<ParamField query="ids" type="List[Union[str, int]]" required>
  A list of document/vector IDs to delete (max 1000 items per request).
</ParamField>

**Returns:** `Dict[str, Any]` - A dictionary confirming the deletion status.

**Raises:** `NamespaceNotFound`, `InvalidInputError`.

### Examples

```python Delete Documents Example theme={null}
from moorcheh_sdk import MoorchehClient

with MoorchehClient() as client:
    # 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}")
```

```python Delete Vectors Example theme={null}
from moorcheh_sdk import MoorchehClient

with MoorchehClient() as client:
    # 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}")
```

### Response Structure

The response contains:

* `status` (str): "success" or "partial"
* `message` (str): Human-readable confirmation message
* `requested_deletions` (int): Number of items requested to be deleted
* `actual_deletions` (int): Number of items actually deleted
* `remaining_items` (int): Total number of items remaining in namespace
* `unprocessed_ids` (list, optional): IDs that failed to be deleted (for partial success)

### Complete Example

```python Complete Deletion Example theme={null}
from moorcheh_sdk import MoorchehClient

with MoorchehClient() as client:
    namespace = "my-documents"
    
    # Delete multiple documents
    ids_to_delete = ["doc-1", "doc-2", "doc-3", "doc-4", "doc-5"]
    
    result = client.documents.delete(
        namespace_name=namespace,
        ids=ids_to_delete
    )
    
    print(f"Requested deletions: {result.get('requested_deletions', 0)}")
    print(f"Actual deletions: {result.get('actual_deletions', 0)}")
    print(f"Remaining items: {result.get('remaining_items', 0)}")
    
    # Handle partial success
    if result.get('status') == 'partial':
        unprocessed = result.get('unprocessed_ids', [])
        if unprocessed:
            print(f"Failed to delete: {unprocessed}")
```

## Important Notes

* Maximum of 1,000 IDs can be deleted in a single request
* IDs can be strings or numbers - they'll be converted to strings internally
* This operation permanently deletes data and cannot be undone
* Successfully deleted items will decrement your total item count
* Use `documents.delete` for text data, `vectors.delete` for vector data
* Namespace must exist and belong to your account

## Understanding Responses

* **200 Response**: No items failed to process (no unprocessed items)
* **207 Response**: Some items were successfully deleted while others failed
* Check `actual_deletions` vs `requested_deletions` to see if items were found
* If `actual_deletions` is 0, the requested IDs may not exist in the namespace
* The `remaining_items` count reflects the current namespace size

## Best Practices

* Verify document IDs before deletion
* Delete in batches for large operations
* Check the response to confirm successful deletions
* Implement proper error handling for partial failures
* Consider backing up important data before deletion

## Use Cases

* **Data Cleanup**: Remove outdated or temporary documents/vectors
* **Content Management**: Delete specific items by ID
* **Privacy Compliance**: Remove specific user data
* **Storage Management**: Free up space by removing unused content
* **Testing**: Clean specific test data between runs

## Related Operations

* [Get Documents](/python-sdk/data/get-documents) - Retrieve documents before deletion
* [Upload Text Data](/python-sdk/data/upload-text) - Add new text documents
* [Upload Vector Data](/python-sdk/data/upload-vector) - Add new vector data