# rag-eval-pipeline

> rag-eval-pipeline — zenith19-rag-eval-pipeline. Use this tool when you need to evaluate the performance of retrieval-augmented question answering models over a large PDF corpus. It solves problems related to assessing recall, hit rate, and mean reciprocal rank (MRR) of QA systems, taking in PDF files and model outputs as inputs and producing evaluation metrics as outputs. Ideal for use cases requiring thorough evaluation of QA models, such as research and development of information retrieval systems.

Canonical page: https://skillsregistry.net/skills/zenith19-rag-eval-pipeline  
JSON: https://api.skillsregistry.net/v1/skills/zenith19-rag-eval-pipeline

## Description

Retrieval-augmented QA over a PDF corpus, built around a from-scratch recall@k / hit-rate@k / MRR evaluation harness — exposed as MCP tools and orchestrated as a LangGraph agent (Qdrant, FastAPI, AWS S3 + Bedrock).

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/zenith19/rag-eval-pipeline)

## 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": "zenith19-rag-eval-pipeline"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zenith19-rag-eval-pipeline` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zenith19-rag-eval-pipeline/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