rag-search
Search the knowledge base for relevant documents. Use when the user wants to find documents in their indexed corpus, has questions that could be answered by their documents, or needs context from their knowledge base. Triggers on keywords like "search documents", "find in knowledge base", "query index".
소스 정보
- 저장소
- etalab-ia/dragster
- 최근 소스 활동
- 2026년 3월 31일 14:36
- 감지된 SKILL.md 언어
- 영어
- 스타
- 1
- 포크
- 0
설치 방법
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
소스 파일 검토
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
SKILL.md 표시 중
SKILL.md
소스 지침 · 읽기 전용 미리보기- name
- rag-search
- provider
- qmd
- available-providers
- ["qmd","pinecone","weaviate"]
- description
- Search the knowledge base for relevant documents. Use when the user wants to find documents in their indexed corpus, has questions that could be answered by their documents, or needs context from their knowledge base. Triggers on keywords like "search documents", "find in knowledge base", "query index".
- license
- MIT
- allowed-tools
- Bash
# rag-search Skill
Search the qmd index for relevant documents. This skill uses **qmd** under the hood.
## Prerequisites
- qmd installed: `bun install -g @tobilu/qmd`
- Collection set up: Use `/rag-index` first
Verify setup:
```bash
qmd status
```
## Workflow
### 1. Verify Knowledge Base
```bash
qmd status
```
Should show your collection(s) with document counts.
### 2. Run Search
```bash
qmd query "<query>" --json
```
Examples:
```bash
qmd query "authentication flow" --json
qmd query "API design patterns" --json
qmd query "deployment process" --json
```
### 3. Present Results
Parse the JSON output and present:
- Document path
- Relevance score
- Relevant excerpt
## Arguments
| Argument | Type | Default | Description |
|----------|------|---------|-------------|
| `query` | string | required | Search query |
| `mode` | string | query | Search mode: `query`, `vsearch`, `search` |
| `limit` | int | 5 | Number of results |
| `collection` | string | all | Restrict to specific collection |
## Search Modes
| Mode | Description |
|------|-------------|
| `query` | Semantic search (default) |
| `vsearch` | Vector search with scores |
| `search` | Hybrid search |
## Examples
```bash
# Basic search
qmd query "authentication" --json
# Limit results
qmd query "API design" --limit 10 --json
# Search specific collection
qmd query "deployment" --collection api-docs --json
# Vector search with scores
qmd vsearch "configuration" --json
```
## Output Format
JSON output structure:
```json
{
"results": [
{
"path": "docs/guide.md",
"score": 0.89,
"content": "..."
}
]
}
```
## Integration with Agents
When using this skill:
1. Run the search query
2. Parse JSON results
3. Present top results with scores
4. Optionally read full documents for deeper context
## Troubleshooting
If no results:
1. Check collection exists: `qmd status`
2. Verify embeddings generated: `qmd embed`
3. Try broader query terms
## Provider-Specific Notes
### qmd (current)
- Storage: Local SQLite with sqlite-vec extension
- Embeddings: Local model (no API key required)
- Best for: Small to medium corpora, offline usage
### pinecone (planned)
- Storage: Pinecone cloud
- Embeddings: OpenAI or custom embeddings
- Best for: Large-scale production deployments
### weaviate (planned)
- Storage: Weaviate instance (self-hosted or cloud)
- Embeddings: Configurable
- Best for: Enterprise deployments with hybrid search
GitHub에서 보기