Semantic Search skills

Pinecone RAG

github

Build RAG pipelines with Pinecone as your vector database.

Paperclip CLI

k-dense-ai

Efficiently search and read biomedical literature and regulatory documents.

Supermemory

supermemoryai

Enhance AI agents with persistent memory and context.

Exa Web Toolkit

k-dense-ai

Powerful web search and content extraction for research.

Store and Query Vectors

aws

Efficiently manage vector embeddings with Amazon S3 Vectors.

Qdrant Vector Search

davila7

High-performance vector similarity search engine for RAG.

RAG Architect

jeffallan

Build efficient retrieval-augmented generation systems.

RAG Implementation

wshobson

Build knowledge-grounded AI systems with RAG.

Chroma

nousresearch

Open-source embedding database for LLM applications.

CLIP

nousresearch

Zero-shot image classification and image-text search.

Memory Management

ruvnet

Enhance learning and knowledge sharing with persistent memory.

AgentDB Vector Search

ruvnet

Fast semantic vector search for intelligent document retrieval.

MemPalace

mempalace

Local AI memory system with high recall and semantic search.

Similarity Search Patterns

wshobson

Efficiently implement similarity search in production systems.

Embedding Strategies

wshobson

Optimize embedding models for effective semantic search.

QMD

nousresearch

Efficient local search for your personal knowledge base.

Vector Embed

ruvnet

Generate and store vector embeddings for semantic tasks.

Pinecone Research

nousresearch

Enhance agent conversations with long-term memory.

ChromaDB CLI

hkuds

Manage vector databases directly from the command line.

Memory Search

davila7

Efficiently recall past conversations and decisions.

RAG Engineer

davila7

Optimize retrieval for better LLM performance.

Wiki Retrieve

agricidaniel

Efficiently retrieve and rank passages from your vault.