# Zeabur RAG Search

> Search the RAG knowledge base via hybrid search (semantic + BM25). Use whenever answering technical questions that may be covered in your knowledge base — even if the user doesn't explicitly ask you to search. Also use when you need to verify claims or find up-to-date information.

- Skill: `zeabur/zeabur-rag-search` (Agent Skill)
- Install (CLI): `npx skillmds@latest add zeabur/zeabur-rag-search`
- Raw SKILL.md: https://api.skillmd.com/api/skills/zeabur/zeabur-rag-search/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: zeabur (https://skillmd.com/u/zeabur)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/zeabur/zeabur-rag-search

---


# RAG Search

Search your knowledge base using hybrid retrieval (semantic + BM25 keyword).

Base URL: `$ZEABUR_RAG_URL`
Auth: `Authorization: Bearer $RAG_API_KEY`

## API

```bash
curl -s -X POST "$ZEABUR_RAG_URL/api/query" \
  -H "Authorization: Bearer $RAG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "your question", "mode": "hybrid", "rag": false, "top_k": 5, "client": "claude-code"}'
```

| Parameter | Default | Description |
|-----------|---------|-------------|
| `query` | required | Search query (supports multilingual) |
| `mode` | `"hybrid"` | `"hybrid"`, `"semantic"`, or keyword-only `"bm25"` |
| `top_k` | `5` | Number of chunks to return |
| `rag` | `false` | If `true`, also returns LLM-generated `answer` string |
| `keyword_weight` | `0.25` | BM25 weight in hybrid mode |
| `semantic_weight` | `0.75` | Semantic weight in hybrid mode |
| `rerank` | `false` | If `true`, use an LLM to reorder a wider candidate pool |
| `rerank_pool_size` | `30` | Candidate count considered when reranking |
| `decay` | `180` | Temporal decay half-life in days (0 = off) |
| `stream` | `false` | Stream the RAG answer (NDJSON) |
| `sources` | key permissions | Optional source list, intersected with the API key's read permissions |
| `client` | `"api"` | Caller identifier for analytics (e.g. `"claude-code"`, `"web-ui"`, `"mcp"`) |

**Always pass `client: "claude-code"` when calling from Claude Code** so queries are trackable in the dashboard.

Response includes `chunks[]` (each with `id`, `title`, `answer`, `tags`, `similarity` (relevance score), `source`, `verified`) and `signal_id` for linking feedback. Score scales differ between BM25, hybrid RRF, and semantic modes, so do not compare values across modes.

## Tips

- Use `rag: false` when you only need raw chunks to read yourself — it's faster and cheaper.
- Set `rag: true` only when you want the service to generate a summarized answer.
- The `signal_id` in the response can be passed to the feedback API to rate result quality.