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.
Exposes a matchChunks(documents, query, options) function that returns chunks sorted by relevance with similarity scores. Chunking thresholds, max token size, and ONNX embedding model are configurable; it is built on top of semantic-chunking. Supports dynamic similarity thresholds and optional chunk recombination.
Related \\
-
embedding-utils
Vector math, similarity search, ANN indexing, clustering, async pipelines, evaluation metrics, and multi-provider embedding generation -- zero dependencies,...
-
extract-topics
Use LDA (Latent Dirichlet Allocation) to extract topics from text
-
fast-topic-analysis
A tool for analyzing text against predefined topics using average weight embeddings and cosine similarity.