The version date for the API of the form YYYY-MM-DD.
Static wxCreate a new watsonx.ai deployment.
Create a new deployment, currently the only supported type is online. If this is a deployment for a prompt tune
then the asset object must exist and the id must be the id of the model that was created after the prompt
training. If this is a deployment for a prompt template then the prompt_template object should exist and the id
must be the id of the prompt template to be deployed.
The parameters to send to the service.
Delete the deployment.
Delete the deployment with the specified identifier.
The parameters to send to the service.
Retrieve the deployment details.
Retrieve the deployment details with the specified identifier.
The parameters to send to the service.
Infer text.
Infer the next tokens for a given deployed model with a set of parameters. If a serving_name is used then it must
match the serving_name that is returned in the inference when the deployment was created.
Note that there is currently a limitation in this operation when using return_options, for input only
input_text will be returned if requested, for output the input_tokens and generated_tokens will not be
returned.
The parameters to send to the service.
Infer text event stream.
Infer the next tokens for a given deployed model with a set of parameters. This operation will return the output
tokens as a stream of events. If a serving_name is used then it must match the serving_name that is returned in
the inference when the deployment was created.
Note that there is currently a limitation in this operation when using return_options, for input only
input_text will be returned if requested, for output the input_tokens and generated_tokens will not be
returned, also the
rank and top_tokens will not be returned.
The parameters to send to the service.
Update the deployment metadata.
Update the deployment metadata. The following parameters of deployment metadata are supported for the patch operation.
/name/description/tags/custom/online/parameters/asset/prompt_template/hardware_specThe PATCH operation with path specified as /online/parameters can be used to update the serving_name.
Patching /asset or /prompt_template should normally be used in the case when these fields already exist.
The parameters to send to the service.
Retrieve the deployments.
Retrieve the list of deployments for the specified space or project.
Optional params: WatsonXAI.ListDeploymentsParamsThe parameters to send to the service.
Generate embeddings.
Generate embeddings from text input.
See the documentation for a description of text embeddings.
The parameters to send to the service.
List the available foundation models.
Retrieve the list of deployed foundation models.
Optional params: WatsonXAI.ListFoundationModelSpecsParamsThe parameters to send to the service.
List the supported tasks.
Retrieve the list of tasks that are supported by the foundation models.
Optional params: WatsonXAI.ListFoundationModelTasksParamsThe parameters to send to the service.
Create a new notebook.
Create a new notebook
To create a notebook from scratch, you need to first upload the notebook content(ipynb format) to the project
Cloud Object Storage (COS) and then reference it with the attribute file_reference. The other required attributes
are name, project and runtime. The attribute runtime is used to specify the environment on which the
notebook runs.
To copy a notebook, you only need to provide name and source_guid in the request body.
The parameters to send to the service.
Delete a particular notebook, including the notebook asset.
Delete a particular notebook, including the notebook asset.
The parameters to send to the service.
Retrieve the details of a large number of notebooks inside a project.
Retrieve the details of a large number of notebooks inside a project.
The parameters to send to the service.
Revert the main notebook to a version.
Revert the main notebook to a version.
The parameters to send to the service.
Create a new version.
Create a version of a given notebook.
The parameters to send to the service.
Delete a notebook version.
Delete a particular version of a given notebook.
The parameters to send to the service.
Retrieve a notebook version.
Retrieve a particular version of a notebook.
The parameters to send to the service.
List the versions of a notebook.
List all versions of a particular notebook.
The parameters to send to the service.
Delete a prompt session.
This deletes a prompt session with the given id.
The parameters to send to the service.
Delete a prompt session entry.
This deletes a prompt session entry with the given id.
The parameters to send to the service.
Get a prompt session.
This retrieves a prompt session with the given id.
The parameters to send to the service.
Get entries for a prompt session.
List entries from a given session.
The parameters to send to the service.
Get a prompt session entry.
This retrieves a prompt session entry with the given id.
The parameters to send to the service.
Get current prompt session lock status.
Retrieves the current locked state of a prompt session.
The parameters to send to the service.
Update a prompt session.
This updates a prompt session with the given id.
The parameters to send to the service.
Create a new prompt session.
This creates a new prompt session.
The parameters to send to the service.
Add a new prompt to a prompt session.
This creates a new prompt associated with the given session.
The parameters to send to the service.
Add a new chat item to a prompt session entry.
This adds new chat items to the given entry.
The parameters to send to the service.
Prompt session lock modifications.
Modifies the current locked state of a prompt session.
The parameters to send to the service.
Delete a prompt.
This delets a prompt / prompt template with the given id.
The parameters to send to the service.
Get a prompt.
This retrieves a prompt / prompt template with the given id.
The parameters to send to the service.
Get the inference input string for a given prompt.
Computes the inference input string based on state of a prompt. Optionally replaces template params.
The parameters to send to the service.
Get current prompt lock status.
Retrieves the current locked state of a prompt.
The parameters to send to the service.
Update a prompt.
This updates a prompt / prompt template with the given id.
The parameters to send to the service.
Create a new prompt / prompt template.
This creates a new prompt with the provided parameters.
The parameters to send to the service.
Add a new chat item to a prompt.
This adds new chat items to the given prompt.
The parameters to send to the service.
Prompt lock modifications.
Modifies the current locked state of a prompt.
The parameters to send to the service.
Infer text.
Infer the next tokens for a given deployed model with a set of parameters.
The parameters to send to the service.
Infer text event stream.
Infer the next tokens for a given deployed model with a set of parameters. This operation will return the output tokens as a stream of events.
The parameters to send to the service.
Text tokenization.
The text tokenize operation allows you to check the conversion of provided input to tokens for a given model. It splits text into words or sub-words, which then are converted to ids through a look-up table (vocabulary). Tokenization allows the model to have a reasonable vocabulary size.
The parameters to send to the service.
Create a new watsonx.ai training.
Create a new watsonx.ai training in a project or a space.
The details of the base model and parameters for the training must be provided in the prompt_tuning object.
In order to deploy the tuned model you need to follow the following steps:
Create a WML model asset, in a space or a project,
by providing the request.json as shown below:
curl -X POST 'https://{cpd_cluster}/ml/v4/models?version=2024-01-29' \
-H 'Authorization: Bearer <replace with your token>' \
-H 'content-type: application/json' \
--data '{
'name': 'replace_with_a_meaningful_name',
'space_id': 'replace_with_your_space_id',
'type': 'prompt_tune_1.0',
'software_spec': {
'name': 'watsonx-textgen-fm-1.0'
},
'metrics': [ from the training job ],
'training': {
'id': '05859469-b25b-420e-aefe-4a5cb6b595eb',
'base_model': {
'model_id': 'google/flan-t5-xl'
},
'task_id': 'generation',
'verbalizer': 'Input: {{input}} Output:'
},
'training_data_references': [
{
'connection': {
'id': '20933468-7e8a-4706-bc90-f0a09332b263'
},
'id': 'file_to_tune1.json',
'location': {
'bucket': 'wxproject-donotdelete-pr-xeyivy0rx3vrbl',
'path': 'file_to_tune1.json'
},
'type': 'connection_asset'
}
]
}'
Notes:
auto_update_model: true
then you can skip this step as the model will have been saved at
the end of the training job.request.json that was stored in the results_reference
field, look for the path in the field
entity.results_reference.location.model_request_path.type must be prompt_tune_1.0.watsonx-textgen-fm-1.0.Create a tuned model deployment as described in the create deployment documentation.
The parameters to send to the service.
Cancel the training.
Cancel the specified training and remove it.
The parameters to send to the service.
Retrieve the training.
Retrieve the training with the specified identifier.
The parameters to send to the service.
Retrieve the list of trainings.
Retrieve the list of trainings for the specified space or project.
Optional params: WatsonXAI.TrainingsListParamsThe parameters to send to the service.
Static newStatic constructConstructs a service URL by formatting the parameterized service URL.
The parameterized service URL is: 'https://{region}.ml.cloud.ibm.com'
The default variable values are:
The formatted URL with all variable placeholders replaced by values.
Construct a WatsonxAiMlVmlv1 object.