VM0Agent Skills
Qdrant
Vector database for semantic search and RAG
Qdrant is a vector database for storing and searching vector embeddings for RAG, semantic search, and recommendations.
Required Environment
| Name | Type | Description |
|---|---|---|
QDRANT_API_KEY | secret | API key from Qdrant Cloud |
QDRANT_URL | var | Qdrant cluster URL (e.g., https://xxx.cloud.qdrant.io:6333) |
Configuration
version: "1.0"
agents:
my-agent:
framework: claude-code
skills:
- https://github.com/vm0-ai/vm0-skills/tree/main/qdrantRun
Store your secret on the platform (recommended, one-time setup):
vm0 secret set QDRANT_API_KEY your-qdrant-api-keyThen run your agent - secret is automatically loaded:
vm0 run my-agent "search similar documents"For CI/CD or temporary overrides, pass secrets at runtime: --secrets QDRANT_API_KEY=value. See Environment Variables for details.
Example Instructions
# Vector Search Agent
You perform semantic search with Qdrant.
## Workflow
1. Receive search query
2. Generate query embedding
3. Search similar vectors
4. Return ranked results
## Distance Metrics
- Cosine, Dot, Euclidean# RAG Retrieval Agent
You retrieve context for RAG.
## Workflow
1. Receive user question
2. Search relevant documents
3. Filter by metadata
4. Return context chunks
## Features
- Payload filtering
- Score thresholds