agentsclimarketplace
Sign in

Qdrant integration

Skill a5c-ai/babysitter/library/specializations/ai-agents-conversational/skills/qdrant-integration

Qdrant vector database with filtering, payloads, and quantization supportFrom its SKILL.md

Install
npx -y skills add a5c-ai/babysitter --skill qdrant-integration

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.7 KB, 254 tokens by cl100k_base, as published. Nobody here has run it

Qdrant Integration Skill

Capabilities

  • Set up Qdrant (local, cloud, self-hosted)
  • Create collections with configuration
  • Implement advanced filtering with payloads
  • Configure quantization for efficiency
  • Set up sparse vectors for hybrid search
  • Implement batch operations and optimization

Target Processes

  • vector-database-setup
  • rag-pipeline-implementation

Implementation Details

Deployment Modes

  1. Local Memory: For testing
  2. Local Disk: Persistent local storage
  3. Qdrant Cloud: Managed service
  4. Self-Hosted: Docker/Kubernetes deployment

Core Operations

  • Collection management with parameters
  • Point upsert with vectors and payloads
  • Search with filters (must, should, must_not)
  • Scroll for pagination
  • Batch operations

Configuration Options

  • Vector parameters (size, distance)
  • Quantization (scalar, product)
  • Sparse vector configuration
  • Payload indexes
  • Replication and sharding

Best Practices

  • Use quantization for large collections
  • Design payload indexes for filters
  • Implement proper batch sizes
  • Configure appropriate distance metrics

Dependencies

  • qdrant-client
  • langchain-qdrant

What ships with it: 1 file

574 B alongside SKILL.md

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.