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.
A Node.js library that semantically chunks text and matches it against a user query using cosine similarity for relevant text retrieval. It returns chunks sorted by relevance with similarity scores, and exposes configurable similarity thresholds and chunk sizes. It is built on top of semantic-chunking for the underlying text processing and supports various ONNX embedding models. The main matchChunks(documents, query, options) function takes an array of document objects, a query string, and options such as maxResults, minSimilarity, and detailed chunkingOptions.
Installation
npm install chunk-matchRelated \\
-
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.