REQUIRED. Input for this feature search. Can be plain text, URL with auto-detection, or base64 content. For text features: Use text mode. For image/video features: Use content mode with URL or base64. Supports template variables: {{INPUT.field_name}}, {{DOC.field_name}}, etc.
| Name | Type | Description | Notes |
|---|---|---|---|
| input_mode | str | Discriminator field. Always 'vector' for raw embedding queries. | [optional] [default to 'vector'] |
| value | Value2 | [optional] | |
| text | str | Legacy text field (DEPRECATED - use 'value' instead). Supports template variables: {{INPUT.field_name}}. | [optional] |
| content | StageDefsContentInput | Legacy content input (DEPRECATED - use 'value' instead). Provide URL or base64 separately via ContentInput model. | [optional] |
| document_ref | StageDefsDocumentReference | Reference to existing document's pre-computed features. The system fetches the document's feature vectors for the specified feature_uri and uses them directly without re-processing. Document must exist and have features for the specified feature_uri. |
from mixpeek.models.query import Query
# TODO update the JSON string below
json = "{}"
# create an instance of Query from a JSON string
query_instance = Query.from_json(json)
# print the JSON string representation of the object
print(Query.to_json())
# convert the object into a dict
query_dict = query_instance.to_dict()
# create an instance of Query from a dict
query_from_dict = Query.from_dict(query_dict)