Rag Retriever

提供基于文档分块、简单词频嵌入及混合向量+关键词搜索的RAG 2.0检索系统，支持中英文本和来源引用。

This skill is largely coherent with its advertised RAG retriever purpose, but please consider the following before installing: 1) npm install will fetch non-trivial native-heavy packages (transformers, onnxruntime, sharp) — verify you are comfortable with build time and disk usage and run inside a controlled environment if unsure. 2) The code includes an OpenAI embedding provider that will call https://api.openai.com/v1/embeddings if you supply an API key (process.env.OPENAI_API_KEY) — the registry metadata doesn't declare that env var, so only provide keys if you intend to use OpenAI and understand network calls. 3) The skill writes cache and database files under its local data/ directory (embedding-cache.json, LanceDB files) — ensure you trust the documents you add. 4) If you need higher assurance, review package-lock.json for dependency origins, run the skill in a sandbox/container, or audit the few JS files that perform network calls (embeddings.js) and file writes before granting credentials.

Type: OpenClaw Skill Name: rag-retriever Version: 0.1.0 The bundle implements a functional RAG (Retrieval-Augmented Generation) system providing document chunking, hybrid search (BM25 and vector), and citation management. It supports multiple embedding providers, including OpenAI and local models via Transformers.js, and utilizes LanceDB for vector storage. The code logic in files like `src/rag2.js`, `src/hybrid-search.js`, and `src/retriever.js` is consistent with the stated purpose of document retrieval and context augmentation. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found; the network requests to OpenAI and Hugging Face mirrors (hf-mirror.com) are standard for this type of application.