extract-topics
Use LDA (Latent Dirichlet Allocation) to extract topics from text
An npm package that uses Latent Dirichlet Allocation (LDA) for topic modeling on text inputs. The main extractTopics(text, options) function analyzes input text and returns a Promise resolving to the LDA result, with options for the number of topics to extract and the number of terms per topic. LDA is an unsupervised learning method that discovers topics in documents, viewing each document as a random mixture over latent topics where every topic is characterized by a distribution over words.
Install
Install dependencies:
npm install extractTopicsRelated \\
-
chunk-match
A NodeJS library that semantically chunks text and matches it against a user query using cosine similarity for precise and relevant text retrieval.
-
embedding-utils
Vector math, similarity search, ANN indexing, clustering, async pipelines, evaluation metrics, and multi-provider embedding generation -- zero dependencies,…
-
fast-topic-analysis
A tool for analyzing text against predefined topics using average weight embeddings and cosine similarity.