Class WatsonXAI

Hierarchy

  • BaseService
    • WatsonXAI

Constructors

constructor

Properties

version wxServiceUrl wxServiceUrl

Methods - Deployments

createDeployment deleteDeployment deploymentGenerateText deploymentGenerateTextStream deploymentsTextChat deploymentsTextChatStream getDeployment listDeployments updateDeployment

Methods - Embeddings

embedText

Methods - Foundation Model Specs

listFoundationModelSpecs listFoundationModelTasks

Methods - Prompt Sessions

createPromptSession createPromptSessionEntry createPromptSessionEntryChatItem deletePromptSession deletePromptSessionEntry getPromptSession getPromptSessionEntry getPromptSessionLock listPromptSessionEntries updatePromptSession updatePromptSessionLock

Methods - Prompts / Prompt Templates

createPrompt createPromptChatItem deletePrompt getPrompt getPromptInput getPromptLock updatePrompt updatePromptLock

Methods - Text Chat

textChat textChatStream

Methods - Text Generation

generateText generateTextStream

Methods - Text Rerank

textRerank

Methods - Tokenization

tokenizeText

Methods - Trainings

createTraining deleteTraining getTraining listTrainings

Methods - constructor

newInstance

Methods - Other

cancelDocumentExtractions cancelSyntheticDataGeneration createDocumentExtraction createFineTuning createSyntheticDataGeneration createTaxonomy deleteFineTuning deleteTaxonomy getDocumentExtraction getFineTuning getSyntheticDataGeneration getTaxonomy listDocumentExtractions listFineTunings listSyntheticDataGenerations listTaxonomies timeSeriesForecast constructServiceUrl

Constructors

constructor

Properties

version

version: string

The version date for the API of the form YYYY-MM-DD.

wxServiceUrl

wxServiceUrl: string

Static wxServiceUrl

wxServiceUrl: string

Methods - Deployments

createDeployment

deleteDeployment

deploymentGenerateText

deploymentGenerateTextStream

deploymentsTextChat

deploymentsTextChatStream

getDeployment

listDeployments

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

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

Methods - Embeddings

embedText

Methods - Foundation Model Specs

listFoundationModelSpecs

listFoundationModelTasks

Methods - Prompt Sessions

createPromptSession

createPromptSessionEntry

createPromptSessionEntryChatItem

deletePromptSession

deletePromptSessionEntry

getPromptSession

getPromptSessionEntry

getPromptSessionLock

listPromptSessionEntries

updatePromptSession

updatePromptSessionLock

Methods - Prompts / Prompt Templates

createPrompt

createPromptChatItem

deletePrompt

getPrompt

getPromptInput

getPromptLock

updatePrompt

updatePromptLock

Methods - Text Chat

textChat

textChatStream

  • textChatStream(params, callbacks?): 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 | WatsonxAiMlVml_v1.ObjectStreamed<WatsonxAiMlVml_v1.TextGenResponse>> represents a source of streaming data. If request performed successfully Stream<string | WatsonxAiMlVml_v1.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

    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, callbacks?): Promise<Stream<WatsonXAI.ObjectStreamed<WatsonXAI.TextChatStreamResponse>>>

  • Parameters

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

Methods - Text Generation

generateText

generateTextStream

  • generateTextStream(params, callbacks?): 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 | WatsonxAiMlVml_v1.ObjectStreamed<WatsonxAiMlVml_v1.TextGenResponse>> represents a source of streaming data. If request performed successfully Stream<string | WatsonxAiMlVml_v1.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

    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, callbacks?): Promise<Stream<WatsonXAI.ObjectStreamed<WatsonXAI.TextGenResponse>>>

  • Parameters

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

Methods - Text Rerank

textRerank

Methods - Tokenization

tokenizeText

Methods - Trainings

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"
             }
           ]
         }'

      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

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

deleteTraining

getTraining

listTrainings

Methods - constructor

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

Methods - Other

cancelDocumentExtractions

cancelSyntheticDataGeneration

createDocumentExtraction

createFineTuning

createSyntheticDataGeneration

createTaxonomy

deleteFineTuning

deleteTaxonomy

getDocumentExtraction

getFineTuning

getSyntheticDataGeneration

getTaxonomy

listDocumentExtractions

listFineTunings

listSyntheticDataGenerations

listTaxonomies

timeSeriesForecast

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.

Settings

Member Visibility

Theme

On This Page

constructorversionwxServiceUrlwxServiceUrlcreateDeploymentdeleteDeploymentdeploymentGenerateTextdeploymentGenerateTextStreamdeploymentsTextChatdeploymentsTextChatStreamgetDeploymentlistDeploymentsupdateDeploymentembedTextlistFoundationModelSpecslistFoundationModelTaskscreatePromptSessioncreatePromptSessionEntrycreatePromptSessionEntryChatItemdeletePromptSessiondeletePromptSessionEntrygetPromptSessiongetPromptSessionEntrygetPromptSessionLocklistPromptSessionEntriesupdatePromptSessionupdatePromptSessionLockcreatePromptcreatePromptChatItemdeletePromptgetPromptgetPromptInputgetPromptLockupdatePromptupdatePromptLocktextChattextChatStreamgenerateTextgenerateTextStreamtextReranktokenizeTextcreateTrainingdeleteTraininggetTraininglistTrainingsnewInstancecancelDocumentExtractionscancelSyntheticDataGenerationcreateDocumentExtractioncreateFineTuningcreateSyntheticDataGenerationcreateTaxonomydeleteFineTuningdeleteTaxonomygetDocumentExtractiongetFineTuninggetSyntheticDataGenerationgetTaxonomylistDocumentExtractionslistFineTuningslistSyntheticDataGenerationslistTaxonomiestimeSeriesForecastconstructServiceUrl