vector-search

Name: vector-search
Availability: InStock
Author: softsystemsstudio

Orchestrate Qdrant vector ingestion and similarity search with workspaceId filters.

Updated Nov 28, 2025

Search Tags:#embeddings #Qdrant #vector-search #similarity-search #tenant-isolation #workspaceId

Ready to run

npx skills add https://github.com/SoftSystemsStudio/Soft-Systems-Studio --skill vector-search

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: vector-search
Source: https://github.com/SoftSystemsStudio/Soft-Systems-Studio/tree/main/.claude/skills/vector-search
Command: npx skills add https://github.com/SoftSystemsStudio/Soft-Systems-Studio --skill vector-search

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables scalable, tenant-isolated vector storage and retrieval using Qdrant, streamlining ingestion, embedding, and similarity search across multiple workspaces.

Core Features & Use Cases

Vector ingestion: upload and upsert embedding vectors into a named collection with workspace scoping.
Similarity search: perform filtered, high-relevance vector queries with workspace-based access control.
Use Case: Build a multi-tenant document search service where each tenant can upload documents and retrieve relevant results without cross-tenant data exposure.

Quick Start

Index a small set of sample documents into a collection and perform a similarity search filtered by workspaceId.

Frequently Asked Questions about vector-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build a multi-tenant vector search with Qdrant?▼

Multi-tenant vector search with Qdrant is achieved by enforcing workspaceId filters during vector ingestion and similarity search, ensuring tenant-scoped retrieval without cross-tenant data exposure across multiple workspaces.

How do I generate and ingest embeddings for similarity search?▼

To generate and ingest embeddings for similarity search, you upload and upsert 1536-dimension OpenAI embedding vectors into a named Qdrant collection, applying workspace scoping and utilizing built-in retry strategies for robust error handling.

Can I use OpenAI embeddings with Qdrant for tenant-isolated document retrieval?▼

Yes, you can use 1536-dimension OpenAI embeddings with Qdrant for tenant-isolated document retrieval. The workflow enforces workspaceId filters to provide robust, tenant-scoped access control during similarity search.

What's the best way to filter similarity search results by workspace?▼

The best way to filter similarity search results by workspace is to apply workspaceId filters during your Qdrant vector queries. This enforces tenant isolation and ensures high-relevance, workspace-based access control.

Does Qdrant vector search support collection management and retry strategies?▼

Yes, Qdrant vector search supports robust collection management and retry strategies. It provides collection management to handle named collections and retry strategies to ensure reliable vector ingestion and similarity search operations.