Class Sensemaker

Index

Constructors

Methods

categorizeComments getModel learnTopics summarize

Constructors

constructor

new Sensemaker(modelSettings): Sensemaker
Creates a Sensemaker object
Parameters
- modelSettings: ModelSettings
  what models to use for what tasks, a default model can be set.
Returns Sensemaker
- Defined in src/sensemaker.ts:45

Methods

categorizeComments

categorizeComments(comments, includeSubtopics, topics?, additionalInstructions?): Promise<Comment[]>
Categorize the comments by topics using a LLM on Vertex.
Parameters
- comments: Comment[]
  The data to summarize
- includeSubtopics: boolean
  Whether to include subtopics in the categorization.
- Optionaltopics: ({
      name: string;
  } | {
      name: string;
      subtopics: {
          name: string;
      }[];
  })[]
  The user provided topics (and optionally subtopics).
- OptionaladditionalInstructions: string
  Optional. Context to add to the LLM prompt. @returns: The LLM's categorization.
Returns Promise<Comment[]>
- Defined in src/sensemaker.ts:135

getModel

getModel(modelSetting): Model
Get corresponding model from modelSettings object, or defaultModel if none specified.
Parameters
- modelSetting: keyof ModelSettings
  the key of the modelSettings options you want the Model for (corresponding to task)
Returns Model
The model to use for the corresponding ModelSetting key
- Defined in src/sensemaker.ts:54

learnTopics

learnTopics(comments, includeSubtopics, topics?, additionalInstructions?): Promise<({
    name: string;
} | {
    name: string;
    subtopics: {
        name: string;
    }[];
})[]>
Extracts topics from the comments using a LLM on Vertex AI. Retries if the LLM response is invalid.
Parameters
- comments: Comment[]
  The comments data for topic modeling
- includeSubtopics: boolean
  Whether to include subtopics in the topic modeling
- Optionaltopics: ({
      name: string;
  } | {
      name: string;
      subtopics: {
          name: string;
      }[];
  })[]
  Optional. The user provided top-level topics, if these are specified only subtopics will be learned.
- OptionaladditionalInstructions: string
  Optional. Context to add to the LLM prompt. @returns: Topics (optionally containing subtopics) representing what is discussed in the comments.
Returns Promise<({
    name: string;
} | {
    name: string;
    subtopics: {
        name: string;
    }[];
})[]>
- Defined in src/sensemaker.ts:96

summarize

summarize(comments, summarizationType?, topics?, additionalInstructions?): Promise<Summary>
Summarize a set of comments using all available metadata.
Parameters
- comments: Comment[]
  the text and (optional) vote data to consider
- summarizationType: SummarizationType = SummarizationType.VOTE_TALLY
  what summarization method to use
- Optionaltopics: ({
      name: string;
  } | {
      name: string;
      subtopics: {
          name: string;
      }[];
  })[]
  the set of topics that should be present in the final summary
- OptionaladditionalInstructions: string
  additional context to give the model as part of the prompt
Returns Promise<Summary>
a summary of the information.
- Defined in src/sensemaker.ts:68