# RAG Document Search

> Use this tool when you need to build knowledge bases, research assistants, or document Q&A systems that require accurate source attribution. It provides document embedding, semantic search, and citation generation capabilities, solving problems related to information retrieval and source attribution. The tool accepts PDF documents as input and outputs searchable collections with configurable chunking strategies and automatic citation generation.

Canonical page: https://skillsregistry.net/skills/nsantra-rag-document-search  
JSON: https://api.skillsregistry.net/v1/skills/nsantra-rag-document-search

## Description

A RAG server that provides document embedding, semantic search, and citation generation capabilities using ChromaDB as the vector store and HuggingFace models for embeddings and reranking. The implementation supports PDF document ingestion from local files or URLs, creates searchable collections with configurable chunking strategies, and includes cross-encoder reranking for improved retrieval quality. Features include multi-collection search, document metadata management, automatic citation generation for LLM responses, and local model storage for offline operation, making it useful for building knowledge bases, research assistants, and document Q&A systems that require accurate source attribution.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/nsantra-rag-document-search)
- **Repository:** <https://github.com/nsantra/rag-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "nsantra-rag-document-search"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nsantra-rag-document-search` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nsantra-rag-document-search/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt