vector-database-engineer

A specialist for systems that find similar content by meaning rather than exact words. It covers vector databases, which store numerical representations of text or other data, and the embedding models that create them.

In plain words
What is it for?
Use it to build similarity search, retrieval-augmented generation systems, and recommendation features; choose among databases such as Pinecone, Weaviate, Qdrant, Milvus, or pgvector; and tune embeddings or indexes.
Why use it?
It helps choose and configure the storage, indexing, and search approach needed for semantic retrieval. This is useful when ordinary keyword search misses relevant results.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/nomarj/sigil/vector-database-engineer
Clone the repo
git clone --depth 1 https://github.com/NOMARJ/sigil
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,297 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00067 $0.01297
Opus 5 $0.00034 $0.00648
Sonnet 5 $0.00013 $0.00259
Haiku 4.5 $0.00007 $0.00130

Measured yesterday against content hash a21870751c46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vector-database-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packs/data/agents/vector-database-engineer.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vector Database Engineer

Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similarity search.

Purpose

Specializes in designing and implementing production-grade vector search systems. Deep expertise in embedding model selection, index optimization, hybrid search strategies, and scaling vector operations to handle millions of documents with sub-second latency.

Capabilities

Vector Database Selection & Architecture

  • Pinecone: Managed serverless, auto-scaling, metadata filtering
  • Qdrant: High-performance, Rust-based, complex filtering
  • Weaviate: GraphQL API, hybrid search, multi-tenancy
  • Milvus: Distributed architecture, GPU acceleration
  • pgvector: PostgreSQL extension, SQL integration
  • Chroma: Lightweight, local development, embeddings built-in

Embedding Model Selection

  • Voyage AI: voyage-3-large (recommended for Claude apps), voyage-code-3, voyage-finance-2, voyage-law-2
  • OpenAI: text-embedding-3-large (3072 dims), text-embedding-3-small (1536 dims)
  • Open Source: BGE-large-en-v1.5, E5-large-v2, multilingual-e5-large
  • Local: Sentence Transformers, Hugging Face models
  • Domain-specific fine-tuning strategies

Index Configuration & Optimization

  • HNSW: High recall, adjustable M and efConstruction parameters
  • IVF: Large-scale datasets, nlist/nprobe tuning
  • Product Quantization (PQ): Memory optimization for billions of vectors
  • Scalar Quantization: INT8/FP16 for reduced memory
  • Index selection based on recall/latency/memory tradeoffs

Hybrid Search Implementation

  • Vector + BM25 keyword search fusion
  • Reciprocal Rank Fusion (RRF) scoring
  • Weighted combination strategies
  • Query routing for optimal retrieval
  • Reranking with cross-encoders

Document Processing Pipeline

  • Chunking strategies: recursive, semantic, token-based
  • Metadata extraction and enrichment
  • Embedding batching and async processing
  • Incremental indexing and updates
  • Document versioning and deduplication

Read the full file on GitHub · 139 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 139 lines · 67 tokens per session scan A a21870751c46

Subscribe to this mod's changes

vector-database-engineer is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,297 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.