skills.rest
JNZader-Vault
JNZader-VaultOFFICIAL
Explore all skills by this author →
GitHub

vector-db

Create and query vector databases for RAG and semantic search.

Updated Feb 2, 2026
Search Tags:#semantic search#embeddings#rag#vector database#pgvector#chromadb
One-click install
npx skills add https://github.com/JNZader-Vault/project-starter-framework --skill vector-db-jnzader-vault
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-db
Source: https://github.com/JNZader-Vault/project-starter-framework/tree/main/.ai-config/skills/data-ai/vector-db
Command: npx skills add https://github.com/JNZader-Vault/project-starter-framework --skill vector-db-jnzader-vault

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires chromadb, pgvector, openai, sentence-transformers, langchain-text-splitters, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides robust solutions for managing and querying vector embeddings, enabling efficient semantic search and Retrieval-Augmented Generation (RAG) for AI applications.

Core Features & Use Cases

  • Vector Storage: Supports ChromaDB for local persistence and pgvector for PostgreSQL integration.
  • Embedding Generation: Integrates with OpenAI's embedding models.
  • RAG Implementation: Includes a RAGChain class for building question-answering systems over documents.
  • Document Chunking: Provides utilities for splitting documents into manageable chunks for indexing.
  • Use Case: Build a chatbot that can answer questions about your company's internal documentation by leveraging RAG with a vector database.

Quick Start

Use the vector-db skill to add documents to a ChromaDB collection.

Frequently Asked Questions about vector-db

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

FAQPage Schema
How do I build a RAG pipeline for semantic search over internal documents?▼

To build a RAG pipeline for semantic search, this Skill provides utilities to chunk documents, generate OpenAI embeddings, store vectors in ChromaDB or pgvector, and query them using an included RAGChain implementation.

Can I use pgvector with PostgreSQL instead of ChromaDB for vector storage?▼

Yes, you can use pgvector with PostgreSQL for vector storage instead of ChromaDB. This Skill supports both local persistence via ChromaDB and PostgreSQL integration via pgvector to manage your vector embeddings.

How do I split large documents into chunks before generating embeddings?▼

To split large documents into chunks before generating embeddings, this Skill integrates langchain-text-splitters. This ensures your documents are partitioned into manageable chunks for accurate indexing and retrieval.

Does this semantic search implementation support OpenAI embedding models?▼

Yes, this semantic search implementation supports OpenAI embedding models. It directly integrates with OpenAI's models to generate vector embeddings for your data before storing them in the vector database.

What is the best way to add documents to a ChromaDB collection for retrieval?▼

The best way to add documents to a ChromaDB collection is to use the provided chunking utilities to process your text, generate embeddings via OpenAI, and index the resulting vectors directly into your local collection.

Related Skills

Explore More Data & Analytics Skills→
markus41markus41
1

vectordb

Manage vector embeddings for semantic search across Pinecone, Weaviate, Chroma, and pgvector.

Community
Intermediate
lacetolaceto
1

langchain-rag

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

Community
Advanced
helix4uhelix4u

chroma

Manage an open-source embedding database for vector and full-text search.

Community
Intermediate
discountedcookiediscountedcookie

postgres-vectors

Store 384-dimensional embeddings in Postgres and query cosine similarity with pgvector.

Community
Advanced