Skip to contents

Generate Cluster Label Suggestions (Human-in-the-Loop)

Source: R/semantic_analysis.R
generate_cluster_labels.Rd

Suggests descriptive labels for clusters using AI. Labels are suggestions for human review - users should edit and approve before using. Supports OpenAI, Gemini, or Ollama (local) for AI generation. When running locally, Ollama is preferred for privacy and cost-free operation.

Usage

generate_cluster_labels(
  cluster_keywords,
  provider = "auto",
  model = NULL,
  temperature = 0.3,
  max_tokens = 50,
  api_key = NULL,
  verbose = TRUE
)

Arguments

cluster_keywords

List of keywords for each cluster.

provider

AI provider to use: "auto" (default), "openai", "gemini", or "ollama". "auto" will try Ollama first, then check for OpenAI/Gemini keys.

model

Model name. If NULL, uses provider defaults: "gpt-4o-mini" (OpenAI), "gemini-2.0-flash" (Gemini), or recommended Ollama model.

temperature

Temperature parameter (default: 0.3).

max_tokens

Maximum tokens for response (default: 50).

api_key

API key for OpenAI or Gemini. If NULL, uses environment variable. Not required for Ollama.

verbose

Logical, if TRUE, prints progress messages.

Value

A list of generated labels.

See also

Other semantic: analyze_document_clustering(), analyze_similarity_gaps(), calculate_clustering_metrics(), calculate_cross_similarity(), calculate_document_similarity(), calculate_similarity_robust(), cluster_embeddings(), cross_analysis_validation(), export_document_clustering(), extract_cross_category_similarities(), fit_semantic_model(), generate_cluster_labels_auto(), generate_embeddings(), reduce_dimensions(), semantic_document_clustering(), semantic_similarity_analysis(), temporal_semantic_analysis(), validate_cross_models(), word_co_occurrence_network(), word_correlation_network()

Examples

if (FALSE) { # \dontrun{
keywords <- list("1" = c("machine", "learning", "neural"), "2" = c("data", "analysis"))
labels_ollama <- generate_cluster_labels(keywords, provider = "ollama")
labels_openai <- generate_cluster_labels(keywords, provider = "openai")
labels_gemini <- generate_cluster_labels(keywords, provider = "gemini")
} # }