Connect to Milvus vector database · emploidai Marketplace
emploidai Marketplace
Add-onsAppletsPlugins
Search tools, teams, and capabilitiesPublish
MarketplacePluginsConnect to Milvus vector database
Plugin
Limited listing

Connect to Milvus vector database

by siyu_and_xuejia · v0.0.2

Connect to Milvus vector database

626 installsUpdated Nov 6, 2025
Publisher information is incomplete

This community listing does not yet include every recommended support, privacy, pricing, and permission disclosure. Review the available package permissions before installing.

Capabilities

Tools

Available inside your emploidai workspace after installation.

Data sources

Available inside your emploidai workspace after installation.

Category

tool

Version

0.0.2siyu_and_xuejia

Requirements

Maximum memory 256MB

Pricing

Not disclosed by publisher

Security & access

Review before installing

CompatibleRequires emploidai 1.0.1+

Permissions

  • Uses tool capability
  • Requires encrypted tool credentials

Dependencies

No additional dependencies

Resources

Privacy policy
emploidai Marketplace

Discover capabilities. Review access. Install inside your workspace.

DocumentationSecuritySupportPrivacyTerms

Milvus Client README

Overview

A dify tool plugin developed based on the official Milvus SDK, providing integration capabilities with the Milvus vector database. It supports core functions such as vector search, data management, and collection operations.

Description

  1. Plugin Authorization
  1. Create Collection

  • Simplifies the official documentation method Create Collections into dynamic creation based on a JSON structure.

  •  [
     {"field_name": "id", "max_length": 64, "datatype": "VARCHAR", "is_primary": true, "auto_id": true},
     {"field_name": "question", "max_length": 1024, "datatype":"VARCHAR"},
     {"field_name": "answer", "max_length": 4096, "datatype":"VARCHAR"},
     {"field_name": "column1", "max_length": 1024, "datatype":"VARCHAR"},
     {"field_name": "column2", "max_length": 1024, "datatype":"VARCHAR"},
     {"field_name": "question_vector", "dim": 6, "datatype":"FLOAT_VECTOR", "index_type": "HNSW", "metric_type": "L2", "params": {"M": 8, "efConstruction": 64}},
     {"field_name": "answer_vector", "datatype":"SPARSE_FLOAT_VECTOR", "index_type": "SPARSE_INVERTED_INDEX", "metric_type": "IP", "params": {"inverted_index_algo": "DAAT_MAXSCORE"}}
 ]
  1. Insert Data

  • Data insertion format

  • [
    {
      "question": "What is machine learning?",
      "answer": "Machine learning is an AI branch enabling computers to learn from data without explicit programming.",
      "column1": "AI Basics",
      "column2": "Technical Definition",
      "question_vector": [0.15, 0.25, 0.35, 0.45, 0.55, 0.65],
      "answer_vector": [0.12, 0.22, 0.32, 0.42, 0.52, 0.62]
    },
    {
      "question": "What are Python's main features?",
      "answer": "Python features: easy to learn, concise syntax, open-source, cross-platform compatibility.",
      "column1": "Programming Language",
      "column2": "Feature Description",
      "question_vector": [0.25, 0.35, 0.45, 0.55, 0.65, 0.75],
      "answer_vector": [0.22, 0.32, 0.42, 0.52, 0.62, 0.72]
    }
]
  1. Flexible Vector Search
  • L2
  • COSINE
  1. Scalar Query