embedding-utils
Vector math, similarity search, ANN indexing, clustering, async pipelines, evaluation metrics, and multi-provider embedding generation -- zero dependencies,...
Zero-dependency package bundling search (HNSW, hybrid/RRF), clustering (including HDBSCAN), quantization, random-projection dimensionality reduction, markdown-aware chunking, and evaluation metrics. Provider-agnostic embedding generation across local ONNX, OpenAI, Cohere, and Google Vertex. Targets use cases such as semantic search, RAG, recommendations, duplicate detection, and document clustering.
Related \\
-
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.
-
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.