load_model

Use the load model operation to load an embedding or reranking model into the database.

Imports a model from object storage (ONNX format) for use in embedding generation and reranking operations. Once loaded, the model can be used for integrated table embeddings or standalone inference.

Parameters

Parameter	Type	Value Range	Required	Default	Description	Notes
model_name	str	Valid model identifier	Yes	No default	Unique name to assign to the loaded model.	Must not already exist in the database schema.
url	str	Cloud URI or public URL	Yes	No default	Object storage URL where the model file is located. Supports Oracle Object Storage URLs and public URLs.	Required.
model_params	dict	Object or NULL	No	None	Optional model loading settings for object storage access and model metadata.	Use credential when the model URL requires a database credential. Use metadata to pass model metadata, such as {"function": "regression"} for a reranking model.
debug_flags	dict	Object or NULL	No	None	Debug or tracing flags for detailed logging.	Optional; omit unless diagnostics are needed.

model_params fields

Field	Type	Value Range	Required	Description	Notes
credential	str	Valid credential name	No	Database credential used to access the object storage URL.	Provide when the model URL is private or requires object storage authentication. Omit for public or pre-authenticated URLs.
metadata	dict	Object or NULL	No	A JSON description of the metadata describing the model. The metadata must, at minimum, describe the machine learning function supported by the model. The model’s metadata parameters are described in JSON Metadata Parameters for ONNX Models.	For reranking models, include "function": "regression" in metadata.

Raises Exception – InvalidModelNameFormatError may be raised when the model name is invalid. The operation can also fail if the model already exists or the URL is inaccessible.

Load an embedding model from Oracle Object Storage

response = client.load_model(
    model_name='all-MiniLM-L6-v2',
    url='https://objectstorage.us-phoenix-1.oraclecloud.com/n/namespace/b/bucket/o/model.onnx'
)
print(response)

Load a reranking model from Oracle Object Storage

response = client.load_model(
    model_name='reranker_model',
    url='https://objectstorage.example.com/models/reranker_quantized.onnx',
    model_params={'metadata': {'function': 'regression'}}
)
print(response)

Verify model was loaded

models = client.list_models()
print([item.model_name for item in models.items or []])

Return type ModelResponse

Returns JSON response confirming model was loaded successfully. Example response:

{
    "model_name": "SAMPLE_MODEL",
    "algorithm": "ONNX",
    "mining_function": "EMBEDDING",
    "creation_date": "2026-03-12T11:27:21Z",
    "attributes": [
        {
            "name": "DATA",
            "value": "TEXT",
            "data_type": "VARCHAR2",
            "data_length": 32767
        },
        {
            "name": "ORA$ONNXTARGET",
            "value": "VECTOR",
            "data_type": "VECTOR",
            "data_length": 1593,
            "vector_info": "VECTOR(384,FLOAT32)"
        }
    ]
}