what models to use for what tasks, a default model can be set.
Categorize the comments by topics using a LLM on Vertex.
The data to summarize
Whether to include subtopics in the categorization.
Optionaltopics: ({ name: string } | { name: string; subtopics: { name: string }[] })[]The user provided topics (and optionally subtopics).
OptionaladditionalContext: stringOptional additional context to provide to the LLM for categorization. The context will be appended verbatim to the prompt. This should be 1-2 sentences on what the conversation is about and where it takes place.
OptionaltopicDepth: 1 | 2 | 3how many levels of topics to learn, from topic to sub-sub-topic @returns: The LLM's categorization.
Get corresponding model from modelSettings object, or defaultModel if none specified.
the key of the modelSettings options you want the Model for (corresponding to task)
The model to use for the corresponding ModelSetting key
Extracts topics from the comments using a LLM on Vertex AI. Retries if the LLM response is invalid.
The comments data for topic modeling
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.
OptionaladditionalContext: stringOptional additional context to provide to the LLM for topic learning. The context will be appended verbatim to the prompt. This should be 1-2 sentences on what the conversation is about and where it takes place.
OptionaltopicDepth: 1 | 2 | 3how many levels of topics to learn, from topic to sub-sub-topic @returns: Topics (optionally containing subtopics) representing what is discussed in the comments.
Generates a conversation summary, optionally incorporating vote data.
It offers flexibility in how topics for the summary are determined:
comments are already categorized (i.e., they have a
topics property), those topics are used directly for the summary structure.topics are explicitly provided, they are used to categorize the
comments before summarization. This ensures the summary has statistics based on the
specified topics (like comments count per topic).The function supports different summarization types (e.g., basic summarization, vote-tally-based summarization), and allows for additional instructions to guide the summarization process. The generated summary is then grounded in the original comments to ensure accuracy and relevance.
An array of Comment objects representing the public conversation comments. If
these comments are already categorized (have a topics property), the summarization will be
based on those existing categories.
The type of summarization to perform (e.g.,
SummarizationType.GROUP_INFORMED_CONSENSUS).
Optionaltopics: ({ name: string } | { name: string; subtopics: { name: string }[] })[]An optional array of Topic objects. If provided, these topics will be used for
comment categorization before summarization, ensuring that the summary addresses the specified
topics. If comments are already categorized, this parameter is ignored.
OptionaladditionalContext: stringOptional additional context to provide to the LLM for summarization. The context will be appended verbatim to the summarization prompt. This should be 1-2 sentences on what the conversation is about and where it takes place.
A Promise that resolves to a Summary object, containing the generated summary text
and metadata.
Creates a Sensemaker object