skills.rest
richfrem
richfremCOMMUNITY
Explore all skills by this author →
GitHub

vector-db-search

Perform semantic search against ChromaDB to retrieve contextually relevant code and documentation.

5|3|Updated Feb 21, 2026
Search Tags:#langchain#retrieval#semantic-search#code-search#vector-store#chromadb#documentation-search
One-click install
npx skills add https://github.com/richfrem/agent-plugins-skills --skill vector-db-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-db-search
Source: https://github.com/richfrem/agent-plugins-skills/tree/main/plugins/vector-db/skills/vector-db-search
Command: npx skills add https://github.com/richfrem/agent-plugins-skills --skill vector-db-search

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires chromadb, langchain, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Semantic search against the ChromaDB vector store retrieves contextually relevant code and documentation across a project, enabling faster understanding and navigation.

Core Features & Use Cases

  • Semantic retrieval of code snippets and documentation using a high-precision Parent-Child architecture.
  • Phase-2 focused search within the 3-phase protocol to surface context-rich chunks for reasoning.
  • Safe, repeatable queries via the provided scripts to avoid direct raw database access.

Quick Start

Ask it to perform a semantic search across the vector store to retrieve context-rich code and documentation chunks for a given question.

Frequently Asked Questions about vector-db-search

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

FAQPage Schema
How do I perform semantic search across my code and documentation using LangChain?▼

Semantic search across code and documentation uses a ChromaDB vector store and LangChain to retrieve contextually relevant chunks based on conceptual queries rather than exact keyword matches during software development.

What is the best way to retrieve high-context code snippets from a vector store?▼

Retrieving high-context code snippets uses a Parent-Child architecture within the vector store to surface larger, context-rich parent chunks, providing better surrounding logic for software reasoning tasks.

Do I need ChromaDB installed to run semantic code search queries?▼

Yes, ChromaDB is a required dependency alongside LangChain, serving as the underlying vector store that holds the embedded code and documentation chunks for profile-based retrieval.

Can I query the vector database directly to find relevant project documentation?▼

Direct raw database access is intentionally prevented; you must run semantic search queries via the provided scripts to ensure safe, repeatable, and profile-based retrieval of project documentation and code.

When should I use this semantic retrieval approach during software development?▼

Use this semantic retrieval approach when you need concept-based search to navigate large codebases or documentation, specifically during Phase-2 focused search tasks to surface context-rich chunks for reasoning.

Related Skills

Explore More Software Engineering Skills→
richfremrichfrem
5

vector-db-ingest

Index repository files into ChromaDB using ingest.py with full or incremental modes.

Community
Intermediate
rudometkinrudometkin
1

chunker

Split long text into labeled semantic chunks for language model context.

Community
Intermediate
patornpatorn

langchain-rag

Build end-to-end RAG pipelines with LangChain document loaders, embeddings, and vector stores.

Community
Advanced
zilliztechzilliztech
3

hybrid-search

Combine BM25 keyword matching with vector semantic similarity in Milvus.

Official
Advanced