---
title: "Deploy Agent Ranking Score"
description: "Measure precision at K for retrieved context"
category: "AI/ML"
url: https://railway.com/deploy/agent-ranking-score
---

# Deploy Agent Ranking Score

Measure precision at K for retrieved context

**[Deploy Agent Ranking Score on Railway](https://railway.com/template/agent-ranking-score)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/agent-ranking-score/manifest.json

- **Creator:** dankeewithtwoes's Projects
- **Category:** AI/ML

## Template content

### Tool

- **Image:** python:3.13-slim
- **Start command:** `python -c "import base64,os;exec(compile(base64.b64decode(os.environ['TOOL_CODE']),'tool.py','exec'))"`
- **Health check:** /health
- **Public domain:** Yes

## Documentation

# Deploy and Host Agent Ranking Score on Railway

Measure precision at K for retrieved context.

## About Hosting Agent Ranking Score

This is a stateless JSON tool. Deploy it, copy TOOL_TOKEN from service variables and send it as an Authorization: Bearer header on POST /run. The /health endpoint is public and returns readiness only. Inputs are limited to 64 KiB. The application does not store requests or call a model.

## Why Deploy Agent Ranking Score

Call a deterministic operation from an agent, workflow or application without an LLM API key.

## Common Use Cases

- Measure precision at K for retrieved context.
- Insert a deterministic check or transformation in a workflow.
- Repeat the documented example in a regression check.

## Dependencies for Agent Ranking Score

- Python 3.13 container and a Railway project.
- An HTTP client with your generated bearer token.

### Example input for POST /run

```json
{"k": 2, "retrieved": ["a", "b"], "relevant": ["a"]}
```

### Expected response

```json
{"result": 0.5}
```

The single process is intended for small internal workloads. Set concurrency and load limits upstream before serving high volume traffic.


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [Weaviate](https://railway.com/deploy/weaviate-1) — Vector database with hybrid search and an API key-protected API
- [Möbius Personal AI OS](https://railway.com/deploy/mobius-v01-personal-ai-os) — Self-hosted AI agent that builds and runs apps for you, with memory.

Open this page in a browser: https://railway.com/deploy/agent-ranking-score