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.From its SKILL.md
npx -y skills add zeabur/rag-service --skill zeabur-rag-searchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.3 KB, as published. Nobody here has run it
RAG Search
Search your knowledge base using hybrid retrieval (semantic + BM25 keyword).
Base URL: $ZEABUR_RAG_URL
Auth: Authorization: Bearer $RAG_API_KEY
API
curl -s -X POST "$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: falsewhen you only need raw chunks to read yourself — it's faster and cheaper. - Set
rag: trueonly when you want the service to generate a summarized answer. - The
signal_idin the response can be passed to the feedback API to rate result quality.