raglite-toolkit
Semantic search, cited answers, an MCP server and agent tools over your documents, in a few lines of TypeScript.
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y [email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add raglite-toolkit -- npx -y raglite-toolkit@2.2.0在終端機中執行。
{ "mcpServers": { "raglite-toolkit": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
RAGLite indexes PDFs, Word files, Markdown, text, JSON, folders and web pages, then searches them and answers questions with any LLM, citing the passages it used.
raglite eval to measure retrieval on your own questionsRequires Node.js 20 or later.
npm install raglite-toolkit
npm install @huggingface/transformers # local embeddings (the default), no API key
npm install @ai-sdk/anthropic # Claude answers; see Providers for the others
import { Document } from "raglite-toolkit";
const doc = new Document("./policy.pdf", {
llm: { provider: "anthropic", apiKey: process.env.ANTHROPIC_API_KEY },
});
await doc.build();
const hits = await doc.search("refund policy", { topK: 3 });
const answer = await doc.ask("What is the refund policy?");
console.log(answer.text); // "Refunds are issued within 30 days [1]."
console.log(answer.citations); // [{ n: 1, source: "policy.pdf", page: 12, text: "..." }]
raglite eval scores recall@k, MRR and hit rate on your questionsasTool() for the Vercel AI SDKThe same library for Python: raglite-toolkit on PyPI (source). Every page of the documentation has TypeScript and Python tabs.
See CONTRIBUTING.md. Security issues: SECURITY.md.
MIT
Build semantic search, multi-provider question answering, and REST APIs over your documents in a few lines of TypeScript.
{ "mcpServers": { "raglite-toolkit": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Raglite Toolkit 透過 stdio 在本機執行。
上次檢查時間:2026-10-28。 Build semantic search, multi-provider question answering, and REST APIs over your documents in a few lines of TypeScript.