ZelaxyDocs
Tool Integrations
Tool

Qdrant

Store and search vectors in Qdrant

Qdrant

Store, search, and manage vector embeddings in Qdrant — a high-performance open-source vector database. Supports filtering, payload management, and batch operations.

Overview

PropertyValue
Typeqdrant
CategoryTool — Vector Database
AuthAPI Key

Operations

OperationDescription
UpsertInsert or update vectors with payloads
SearchFind similar vectors
DeleteRemove vectors
List CollectionsGet available collections

Configuration

SettingTypeDescription
API KeyPasswordQdrant API key
URLShort inputQdrant cluster URL
CollectionShort inputCollection name
Top KSliderNumber of results
VectorCode editorQuery vector
FilterCode editorQdrant filter conditions (JSON)

Outputs

FieldTypeDescription
resultsjsonSimilar vectors with scores and payloads
contentstringFormatted results

Workflow:

[Starter: Query + Category] → [OpenAI: Embed] → [Qdrant: Search] → [Agent] → [Response]

Qdrant Filter:

{
  "must": [
    { "key": "category", "match": { "value": "{{starter.input.category}}" } }
  ]
}

Search similar vectors but only within a specific category — combining semantic similarity with metadata filtering.

Tips

  • Payload filters are powerful — combine semantic search with exact match filters
  • Self-hosted option — Qdrant can run locally with Docker
  • Higher dimension support than some alternatives — works with any embedding model