Fast, lightweight text chunking for RAG pipelines. 11 chunker types (Token, Fast, Sentence, Recursive, Semantic, Late, Code, Neural, Slumber, Table, TeraflopAI), Pipeline API for end-to-end ingestion workflows, embeddings refineries, and vector DB integrations (Chroma, Qdrant, Pinecone, Weaviate, and more).
Plugin chonkie from marketplace chonkie-skills in feyninc/skills. Commands read from the repo's manifest — 1 month ago.
chonkieUse Chonkie for fast, lightweight text chunking in RAG pipelines. Covers all 11 chunker types (Token, Fast, Sentence, Recursive, Semantic, Late, Code, Neural, Slumber, Table, TeraflopAI), the Pipeline API for chaining fetch→process→chunk→refine→export→store workflows, embeddings refineries, vector D
Unified embedding API client for 11 providers (OpenAI, VoyageAI, Cohere, Jina, Mistral, Gemini, and more) through a single interface. Built-in retry logic, cost tracking, model discovery, Matryoshka dimension reduction, and async support. Python and Rust.
1 skill
Offline documentation packages for AI agents. Pull searchable docs from CDN, full-text search with BM25 + ONNX semantic reranking, build custom .mandex packages from markdown, and auto-sync project dependency docs. 36+ packages across npm, pip, and cargo ecosystems.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.