skills.rest
pomazanbohdan
pomazanbohdanCOMMUNITY
Explore all skills by this author →
GitHub

surreal-vector-search

Design and optimize SurrealDB vector search pipelines with HNSW, BM25 fusion, and benchmarks.

16|Updated Mar 6, 2026
Search Tags:#recall#quantization#hnsw#surrealdb#knn#vector-search#hybrid-search
One-click install
npx skills add https://github.com/pomazanbohdan/vida-stack --skill surreal-vector-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: surreal-vector-search
Source: https://github.com/pomazanbohdan/vida-stack/tree/main/.agents/skills/surreal-vector-search
Command: npx skills add https://github.com/pomazanbohdan/vida-stack --skill surreal-vector-search

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Surreal-vector-search enables high-performance vector search in SurrealDB 3.0, bridging vector similarity with BM25 and hybrid retrieval.

Core Features & Use Cases

  • HNSW index design with configurable distance metrics and quantization for memory efficiency
  • BM25 full-text fusion to enable hybrid retrieval combining keyword and vector signals
  • Production tuning guidance for Rust MCP projects, including recall, latency, and monitoring benchmarks

Quick Start

Provide a first-class hybrid vector+BM25 search example by running a query that uses a sample vector and a text query to retrieve top-k results from the memories index.

Frequently Asked Questions about surreal-vector-search

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

FAQPage Schema
How do I configure HNSW parameters for SurrealDB vector search?▼

To configure HNSW vector search in SurrealDB, you set the M and efConstruction parameters to balance graph connectivity and search efficiency, directly impacting recall and latency for your specific Rust MCP workload.

What is hybrid retrieval and how does BM25 fusion work with vector search?▼

Hybrid retrieval merges semantic vector similarity with BM25 full-text keyword scoring. Enabling BM25 fusion combines vector and keyword signals to improve search accuracy for queries requiring both exact matches and contextual meaning.

Does SurrealDB support quantization for memory-efficient vector search?▼

Yes, SurrealDB supports quantization for vector search. Enabling quantization compresses vector embeddings to reduce memory consumption while maintaining acceptable recall rates for large-scale semantic search and RAG pipelines.

Can I use SurrealDB for RAG retrieval in a Rust MCP project?▼

Yes, you can use SurrealDB for RAG retrieval in Rust MCP projects. It provides vector similarity search, configurable distance metrics, and hybrid BM25 fusion to build and optimize real-world retrieval pipelines.

What is the best way to benchmark recall and latency for a vector search pipeline?▼

The best way to benchmark vector search pipelines is by validating recall and latency against real-world workloads. This involves tuning HNSW parameters, selecting distance metrics, and testing hybrid BM25 fusion configurations.

Related Skills

Explore More Software Engineering Skills→
RepairYourTechRepairYourTech
6

surrealdb-expert

Guide SurrealDB 3.0 multi-model database design and SurrealQL 3.0 syntax.

Community
Advanced
scanadyscanady

data-ai-ml-rag-architect

Design and evaluate RAG systems with vector databases, chunking pipelines, and embedding strategies.

Community
Advanced
zepdbzepdb
43

zeppelin

Index and search text with Zeppelin vector store and BM25 full-text indexing.

Official
Advanced
ancolemanancoleman
503

using-vector-databases

Implement vector databases for AI/ML semantic search and RAG systems.

Community
Advanced