Class WatsonXAI

constructor

• new WatsonXAI(options): WatsonXAI

• Construct a WatsonxAiMlVml_v1 object.

  Parameters

  • options: UserOptions

    Options for the service.

  Returns WatsonXAI

version

wxServiceUrl

Static wxServiceUrl

createDeployment

• createDeployment(params): Promise<WatsonXAI.Response<WatsonXAI.DeploymentResource>>

• Create 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.

  Parameters

  • params: WatsonXAI.CreateDeploymentParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.DeploymentResource>>

deleteDeployment

• deleteDeployment(params): Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

• Delete the deployment.

  Delete the deployment with the specified identifier.

  Parameters

  • params: WatsonXAI.DeploymentsDeleteParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

deploymentGenerateText

• deploymentGenerateText(params): Promise<WatsonXAI.Response<WatsonXAI.TextGenResponse>>

• 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 section when the deployment was created.

  Return options

  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.

  Parameters

  • params: WatsonXAI.DeploymentsTextGenerationParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.TextGenResponse>>

deploymentGenerateTextStream

• deploymentGenerateTextStream(params): Promise<Stream<string>>

• 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.

  Return options

  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.

  Parameters

  • params: WatsonXAI.DeploymentsTextGenerationStreamParams & {
        returnObject?: false;
    }

    The parameters to send to the service.

  Returns Promise<Stream<string>>

  return - Promise resolving to Stream object. Stream object is AsyncIterable based class. Stream object contains an additional property holding an AbortController, read more below.
• deploymentGenerateTextStream(params): Promise<Stream<ObjectStreamed<WatsonXAI.TextGenResponse>>>

• Parameters

  • params: WatsonXAI.DeploymentsTextGenerationStreamParams & {
        returnObject: true;
    }

  Returns Promise<Stream<ObjectStreamed<WatsonXAI.TextGenResponse>>>

getDeployment

• getDeployment(params): Promise<WatsonXAI.Response<WatsonXAI.DeploymentResource>>

• Retrieve the deployment details.

  Retrieve the deployment details with the specified identifier.

  Parameters

  • params: WatsonXAI.DeploymentsGetParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.DeploymentResource>>

listDeployments

• listDeployments(params?): Promise<WatsonXAI.Response<WatsonXAI.DeploymentResourceCollection>>

• Retrieve the deployments.

  Retrieve the list of deployments for the specified space or project.

  Parameters

  • Optional params: WatsonXAI.ListDeploymentsParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.DeploymentResourceCollection>>

updateDeployment

• updateDeployment(params): Promise<WatsonXAI.Response<WatsonXAI.DeploymentResource>>

• 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 - replace only
  • /prompt_template - replace only
  • /hardware_spec
  • /hardware_request
  • /base_model_id - replace only (applicable only to prompt template deployments referring to IBM base foundation models)

  The PATCH operation with path specified as /online/parameters can be used to update the serving_name.

  Parameters

  • params: WatsonXAI.DeploymentsUpdateParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.DeploymentResource>>

embedText

• embedText(params): Promise<WatsonXAI.Response<WatsonXAI.EmbeddingsResponse>>

• Generate embeddings.

  Generate embeddings from text input.

  See the documentation for a description of text embeddings.

  Parameters

  • params: WatsonXAI.TextEmbeddingsParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.EmbeddingsResponse>>

listFoundationModelSpecs

• listFoundationModelSpecs(params?): Promise<WatsonXAI.Response<WatsonXAI.FoundationModels>>

• List the available foundation models.

  Retrieve the list of deployed foundation models.

  Parameters

  • Optional params: WatsonXAI.ListFoundationModelSpecsParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.FoundationModels>>

listFoundationModelTasks

• listFoundationModelTasks(params?): Promise<WatsonXAI.Response<WatsonXAI.FoundationModelTasks>>

• List the supported tasks.

  Retrieve the list of tasks that are supported by the foundation models.

  Parameters

  • Optional params: WatsonXAI.ListFoundationModelTasksParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.FoundationModelTasks>>

createPromptSession

• createPromptSession(params): Promise<WatsonXAI.Response<WatsonXAI.WxPromptResponse>>

• Create a new prompt session.

  This creates a new prompt session.

  Parameters

  • params: WatsonXAI.PostPromptSessionParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.WxPromptResponse>>

createPromptSessionEntry

• createPromptSessionEntry(params): Promise<WatsonXAI.Response<WatsonXAI.WxPromptSessionEntry>>

• Add a new prompt to a prompt session.

  This creates a new prompt associated with the given session.

  Parameters

  • params: WatsonXAI.PostPromptSessionEntryParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.WxPromptSessionEntry>>

createPromptSessionEntryChatItem

• createPromptSessionEntryChatItem(params): Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

• Add a new chat item to a prompt session entry.

  This adds new chat items to the given entry.

  Parameters

  • params: WatsonXAI.PostPromptSessionEntryChatItemParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

deletePromptSession

• deletePromptSession(params): Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

• Delete a prompt session.

  This deletes a prompt session with the given id.

  Parameters

  • params: WatsonXAI.DeletePromptSessionParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

deletePromptSessionEntry

• deletePromptSessionEntry(params): Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

• Delete a prompt session entry.

  This deletes a prompt session entry with the given id.

  Parameters

  • params: WatsonXAI.DeletePromptSessionEntryParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

getPromptSession

• getPromptSession(params): Promise<WatsonXAI.Response<WatsonXAI.WxPromptSession>>

• Get a prompt session.

  This retrieves a prompt session with the given id.

  Parameters

  • params: WatsonXAI.GetPromptSessionParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.WxPromptSession>>

getPromptSessionEntry

• getPromptSessionEntry(params): Promise<WatsonXAI.Response<WatsonXAI.WxPromptResponse>>

• Get a prompt session entry.

  This retrieves a prompt session entry with the given id.

  Parameters

  • params: WatsonXAI.GetPromptSessionEntryParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.WxPromptResponse>>

getPromptSessionLock

• getPromptSessionLock(params): Promise<WatsonXAI.Response<WatsonXAI.PromptLock>>

• Get current prompt session lock status.

  Retrieves the current locked state of a prompt session.

  Parameters

  • params: WatsonXAI.GetPromptSessionLockParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.PromptLock>>

listPromptSessionEntries

• listPromptSessionEntries(params): Promise<WatsonXAI.Response<WatsonXAI.WxPromptSessionEntryList>>

• Get entries for a prompt session.

  List entries from a given session.

  Parameters

  • params: WatsonXAI.GetPromptSessionEntriesParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.WxPromptSessionEntryList>>

updatePromptSession

• updatePromptSession(params): Promise<WatsonXAI.Response<WatsonXAI.WxPromptSession>>

• Update a prompt session.

  This updates a prompt session with the given id.

  Parameters

  • params: WatsonXAI.PatchPromptSessionParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.WxPromptSession>>

updatePromptSessionLock

• updatePromptSessionLock(params): Promise<WatsonXAI.Response<WatsonXAI.PromptLock>>

• Prompt session lock modifications.

  Modifies the current locked state of a prompt session.

  Parameters

  • params: WatsonXAI.PutPromptSessionLockParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.PromptLock>>

createPrompt

• createPrompt(params): Promise<WatsonXAI.Response<WatsonXAI.WxPromptResponse>>

• Create a new prompt / prompt template.

  This creates a new prompt with the provided parameters.

  Parameters

  • params: WatsonXAI.PostPromptParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.WxPromptResponse>>

createPromptChatItem

• createPromptChatItem(params): Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

• Add a new chat item to a prompt.

  This adds new chat items to the given prompt.

  Parameters

  • params: WatsonXAI.PostPromptChatItemParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

deletePrompt

• deletePrompt(params): Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

• Delete a prompt.

  This delets a prompt / prompt template with the given id.

  Parameters

  • params: WatsonXAI.DeletePromptParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

getPrompt

• getPrompt(params): Promise<WatsonXAI.Response<WatsonXAI.WxPromptResponse>>

• Get a prompt.

  This retrieves a prompt / prompt template with the given id.

  Parameters

  • params: WatsonXAI.GetPromptParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.WxPromptResponse>>

getPromptInput

• getPromptInput(params): Promise<WatsonXAI.Response<WatsonXAI.GetPromptInputResponse>>

• Get the inference input string for a given prompt.

  Computes the inference input string based on state of a prompt. Optionally replaces template params.

  Parameters

  • params: WatsonXAI.GetPromptInputParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.GetPromptInputResponse>>

getPromptLock

• getPromptLock(params): Promise<WatsonXAI.Response<WatsonXAI.PromptLock>>

• Get current prompt lock status.

  Retrieves the current locked state of a prompt.

  Parameters

  • params: WatsonXAI.GetPromptLockParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.PromptLock>>

updatePrompt

• updatePrompt(params): Promise<WatsonXAI.Response<WatsonXAI.WxPromptResponse>>

• Update a prompt.

  This updates a prompt / prompt template with the given id.

  Parameters

  • params: WatsonXAI.PatchPromptParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.WxPromptResponse>>

updatePromptLock

• updatePromptLock(params): Promise<WatsonXAI.Response<WatsonXAI.PromptLock>>

• Prompt lock modifications.

  Modifies the current locked state of a prompt.

  Parameters

  • params: WatsonXAI.PutPromptLockParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.PromptLock>>

textChat

• textChat(params): Promise<WatsonXAI.Response<WatsonXAI.TextChatResponse>>

• Infer text.

  Infer the next tokens for a given deployed model with a set of parameters.

  Parameters

  • params: WatsonXAI.TextChatParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.TextChatResponse>>

textChatStream

• textChatStream(params): Promise<Stream<string>>

• 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

  Response

  Stream<string | ObjectStreamed<WatsonxAiMlVml_v1.TextGenResponse>> represents a source of streaming data. If request performed successfully Stream<string | ObjectStreamed<WatsonxAiMlVml_v1.TextGenResponse>> returns either stream line by line. Output will stream as follow:

  • id: 1
  • event: message
  • data: {data}
  • empty line which separates the next Event Message

  or stream of objects. Output will stream as follow: { id: 2, event: 'message', data: {data} } Here is one of the possibilities to read streaming output:

  const stream = await watsonxAiMlService.generateTextStream(parameters); for await (const line of stream) { console.log(line); }.

  Parameters

  • params: WatsonXAI.TextChatStreamParams & {
        returnObject?: false;
    }

    The parameters to send to the service.

  Returns Promise<Stream<string>>

  return - Promise resolving to Stream object. Stream object is AsyncIterable based class. Stream object contains an additional property holding an AbortController, read more below.
• textChatStream(params): Promise<Stream<ObjectStreamed<WatsonXAI.TextChatResponse>>>

• Parameters

  • params: WatsonXAI.TextChatStreamParams & {
        returnObject: true;
    }

  Returns Promise<Stream<ObjectStreamed<WatsonXAI.TextChatResponse>>>

generateText

• generateText(params): Promise<WatsonXAI.Response<WatsonXAI.TextGenResponse>>

• Infer text.

  Infer the next tokens for a given deployed model with a set of parameters.

  Parameters

  • params: WatsonXAI.TextGenerationParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.TextGenResponse>>

generateTextStream

• generateTextStream(params): Promise<Stream<string>>

• 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.

  Response

  Stream<string | ObjectStreamed<WatsonxAiMlVml_v1.TextGenResponse>> represents a source of streaming data. If request performed successfully Stream<string | ObjectStreamed<WatsonxAiMlVml_v1.TextGenResponse>> returns either stream line by line. Output will stream as follow:

  • id: 1
  • event: message
  • data: {data}
  • empty line which separates the next Event Message

  or stream of objects. Output will stream as follow: { id: , event: 'message', data: {data} }

  Here is one of the possibilities to read streaming output:

  const stream = await watsonxAiMlService.generateTextStream(parameters); for await (const line of stream) { console.log(line); }

  Parameters

  • params: WatsonXAI.TextGenerationStreamParams & {
        returnObject?: false;
    }

    The parameters to send to the service.

  Returns Promise<Stream<string>>

  return - Promise resolving to Stream object. Stream object is AsyncIterable based class. Stream object contains an additional property holding an AbortController, read more below.
• generateTextStream(params): Promise<Stream<ObjectStreamed<WatsonXAI.TextGenResponse>>>

• Parameters

  • params: WatsonXAI.TextGenerationStreamParams & {
        returnObject: true;
    }

  Returns Promise<Stream<ObjectStreamed<WatsonXAI.TextGenResponse>>>

textRerank

• textRerank(params): Promise<WatsonXAI.Response<WatsonXAI.RerankResponse>>

• Generate rerank.

  Rerank texts based on some queries.

  Parameters

  • params: WatsonXAI.TextRerankParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.RerankResponse>>

tokenizeText

• tokenizeText(params): Promise<WatsonXAI.Response<WatsonXAI.TextTokenizeResponse>>

• 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.

  Parameters

  • params: WatsonXAI.TextTokenizationParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.TextTokenizeResponse>>

createTraining

• createTraining(params): Promise<WatsonXAI.Response<WatsonXAI.TrainingResource>>

• 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:

  1. 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"
            }
          ]
        }'
     Copy

     Notes:

     1. If you used the training request field auto_update_model: true then you can skip this step as the model will have been saved at the end of the training job.
     2. Rather than creating the payload for the model you can use the generated request.json that was stored in the results_reference field, look for the path in the field entity.results_reference.location.model_request_path.
     3. The model type must be prompt_tune_1.0.
     4. The software spec name must be watsonx-textgen-fm-1.0.

  2. Create a tuned model deployment as described in the create deployment documentation.

  Parameters

  • params: WatsonXAI.TrainingsCreateParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.TrainingResource>>

deleteTraining

• deleteTraining(params): Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

• Cancel or delete the training.

  Cancel the specified training and remove it.

  Parameters

  • params: WatsonXAI.TrainingsDeleteParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.EmptyObject>>

getTraining

• getTraining(params): Promise<WatsonXAI.Response<WatsonXAI.TrainingResource>>

• Retrieve the training.

  Retrieve the training with the specified identifier.

  Parameters

  • params: WatsonXAI.TrainingsGetParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.TrainingResource>>

listTrainings

• listTrainings(params?): Promise<WatsonXAI.Response<WatsonXAI.TrainingResourceCollection>>

• Retrieve the list of trainings.

  Retrieve the list of trainings for the specified space or project.

  Parameters

  • Optional params: WatsonXAI.TrainingsListParams

    The parameters to send to the service.

  Returns Promise<WatsonXAI.Response<WatsonXAI.TrainingResourceCollection>>

Static newInstance

• newInstance(options?): WatsonXAI

• Constructs an instance of WatsonxAiMlVml_v1 with passed in options and external configuration.

  Parameters

  • Optional options: UserOptions

    The parameters to send to the service.

  Returns WatsonXAI

Static constructServiceUrl

• constructServiceUrl(providedUrlVariables): string

• Constructs 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:

  • 'region': 'us-south'

  Parameters

  • providedUrlVariables: Map<string, string>

  Returns string

  The formatted URL with all variable placeholders replaced by values.