Zvec

ZVec Skill

Alibaba's lightweight in-process vector database - "The SQLite of Vector Databases"

Overview

ZVec is an open-source, in-process vector database from Alibaba's Tongyi Lab. It's lightweight, blazing fast, and embeds directly into your application - no server needed. Built on Proxima (Alibaba's battle-tested vector search engine used in production across Taobao, Ele.me, and more).

Anti-Rationalization Table

When to Use

Trigger phrases:

• "Mikolov et al."
• "Zero-copy vector operations for efficient similarity search and embedding storag"

Use this skill when you need:

• Lightweight vector storage with minimal setup
• Fast local RAG without external services
• Edge AI with on-device embeddings
• Simple API that "just works"
• Production-grade performance in a tiny package

Key Features

• Automated workflow execution with error recovery
• Configurable parameters for different use cases
• Integration with existing tooling and pipelines
• Detailed logging and status reporting

🚀 Blazing Fast

• Searches billions of vectors in milliseconds
• Built on Alibaba's Proxima engine
• Optimized for low latency

📦 Simple, Just Works

• pip install zvec and start searching
• No servers, no config, no daemon
• Runs wherever your code runs

🌍 Runs Anywhere

• macOS (ARM64)
• Linux (x86_64, ARM64)
• Python 3.10-3.12
• Node.js support

🔍 Rich Query Support

• Dense and sparse vectors
• Hybrid search with filters
• Multiple index types (Flat, HNSW, IVF)

Installation

# Python
pip install zvec

# Node.js
npm install @zvec/zvec

Usage Patterns

• Invoke the skill when the matching domain keywords appear
• Combine with related skills for end-to-end workflows
• Use verification steps to confirm successful execution
• Review output quality before finalizing results

Python Example

import zvec

# Define collection schema
schema = zvec.CollectionSchema(
    name="example",
    vectors=zvec.VectorSchema("embedding", zvec.DataType.VECTOR_FP32, 384)
)

# Create collection
collection = zvec.create("my_vectors", schema)

# Add vectors
collection.add(
    ids=["doc1", "doc2"],
    vectors=[[0.1] * 384, [0.2] * 384],
    payloads=[{"text": "AI is great"}, {"text": "Vectors are useful"}]
)

# Search
results = collection.search(
    query_vector=[0.1] * 384,
    top_k=10,
    filter={"text": {"$contains": "AI"}}
)

Node.js Example

const zvec = require('@zvec/zvec');

const collection = await zvec.create('documents', { dimension: 384 });
await collection.add({ id: '1', vector: embedding, payload: { text: 'Hello' } });
const results = await collection.search({ vector: queryEmbedding, topK: 5 });

Index Types

Integration with 1ai-skills

ZVec integrates perfectly with:

• faceless-youtube - Video content embedding
• ai-research-agent - Document similarity search
• content-generator - Content deduplication

When to Choose ZVec vs RuVector

Choose ZVec for: Simple, fast, lightweight vector storage Choose RuVector for: Self-learning memory, graph queries, local LLMs

Files in This Skill

• SKILL.md - This file

See Also

• ZVec GitHub
• ZVec Documentation
• Benchmarks

When NOT to Use

• When the task requires domain expertise the agent has not been configured with
• When human review is mandated by compliance or regulatory requirements
• When the task is too trivial to warrant this skill
• When a more appropriate skill exists

Common Rationalizations

Red Flags

• Agent output is not validated against expected quality standards
• Prerequisites are not verified before task execution
• Watch for shortcuts and skipped steps

Verification

After completing this skill, confirm:

• Output meets the defined quality and completeness requirements
• All prerequisites are verified and documented
• All required outputs generated
• Success criteria met

Process

1. Analyze the task requirements
2. Apply domain expertise
3. Verify output quality