ragstack-core

mukeshnaidu/ragstack-core

★ 0 stars Python 🤖 AI/LLM Updated today

RAGSTACK is an enterprise-ready RAG toolkit/SDK for document ingestion, text extraction, chunking, metadata handling, and scalable pipeline building. It helps developers process PDFs, DOCX, TXT, and other files into clean, structured chunks for embeddings, vector databases, APIs, MCP servers, and AI applications.

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": {
    "ragstack-core": {
      "command": "uvx",
      "args": [
        "ragstack-core"
      ]
    }
  }
}

Or install with pip: pip install ragstack-core

README Excerpt

**Enterprise-grade Python RAG (Retrieval-Augmented Generation) toolkit.** RAGSTACK is a composable, open-source SDK for building document ingestion pipelines. It handles everything between a raw file and a vector database: loading, cleaning, chunking, embedding, and storing — each stage independently usable and swappable.

ragstack-core

Quick Install

README Excerpt

Tools (7)

Related AI/LLM Servers