RAG-In-A-Box

DevNexsler/RAG-In-A-Box
★ 4 stars Python 🤖 AI/LLM Updated 1d ago
RAG pipeline for documents (Markdown, PDF, images). 10-step hybrid search, LLM enrichment, taxonomy, MCP server. Cloud or local.
View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "rag-in-a-box": {
      "command": "uvx",
      "args": [
        "rag-in-a-box"
      ]
    }
  }
}

Or install with pip: pip install rag-in-a-box

README Excerpt

Drop your documents into a folder, run the indexer, and get a production-grade RAG pipeline with an **MCP server** — any MCP-compatible AI assistant (Claude Code, OpenClaw, Claude Desktop, Cursor, etc.) can search your documents with a single config entry. No infrastructure to manage. No GPU required. Works with **cloud APIs** out of the box or **fully self-hosted**.

Tools (20)

API_KEYDOCUMENTS_ROOTINDEX_ROOTPORTfile_facetsfile_foldersfile_get_chunkfile_get_doc_chunksfile_index_updatefile_list_documentsfile_recentfile_searchfile_statusfile_taxonomy_addfile_taxonomy_deletefile_taxonomy_getfile_taxonomy_importfile_taxonomy_listfile_taxonomy_searchfile_taxonomy_update

Topics

bm25claudedocument-indexerembeddingshybrid-searchknowledge-baselancedbllmmarkdownmcpmcp-serveropenrouterpdfragsemantic-search