Skills tagged "RAG"

pinecone - Managed vector database for production RAG and search
Pinecone Vector Database RAG Serverless
★ 0 · Updated 2026-09-20
Pinecone provides serverless vector database operations including index creation, vector upserting, similarity querying, metadata filtering, and hybrid search.
⚙ Create vector indices ⚙ Upsert vector data ⚙ Query similar vectors
rag-ingestion-auditor - RAG Knowledge Base Ingestion and Retrieval Quality Auditor
RAG Knowledge Base Document Parsing Text Chunking
★ 1 · Updated 2026-09-15
Audits, designs, and refines document parsing, text chunking, vector ingestion, and retrieval quality governance in RAG pipelines.
⚙ Audit document parsing logic ⚙ Optimize text chunking strategies ⚙ Review vector ingestion strategies
plant-care-card - Plant Care Card
plant care care card RAG markdown
★ 0 · Updated 2026-09-13
Generates a structured care card for a flower using Smart Sprout's RAG corpus.
⚙ Query plant_lookup tool for information ⚙ Fill template.md with lookup results ⚙ Present completed care card to user
pinecone-research - Pinecone Research — Agent RAG & Long-Term Memory
RAG Pinecone Memory Research
★ 5 · Updated 2026-09-12
Use Pinecone as a RAG backend for agent conversations to persist embeddings, retrieve context, and build long-term memory.
⚙ Persist embeddings ⚙ Retrieve relevant context ⚙ Build long-term memory
cost-allocation - RAG Cost Allocation and Tracking
cost tracking RAG budgeting token counting
★ 33 · Updated 2026-06-15
Track per-tenant RAG costs with token counting and metadata aggregation
⚙ count tokens ⚙ log metadata ⚙ aggregate cost data
agent-frameworks - Build AI Agents with Frameworks
AI agent framework LangChain CrewAI
★ 602 · Updated 2026-06-15
Develop autonomous AI agents using LangChain, CrewAI, AutoGen with tools and multi-agent collaboration
⚙ create agent ⚙ define tools ⚙ execute agent
mem0-2-0-1 - Self-improving memory layer for LLM agents
memory context LLM RAG
★ 2 · Updated 2026-06-15
Self-improving memory layer enabling persistent context across sessions with hybrid search and entity linking
⚙ add memory ⚙ search memory ⚙ update memory
pinecone - Pinecone vector database for semantic search
vector database similarity search RAG embeddings
★ 4 · Updated 2026-06-15
Store embeddings and query by semantic meaning for RAG and similarity search
⚙ create index ⚙ list indexes ⚙ delete index
stacks-ai - Stacks AI Integration
AI LLM RAG vector search
★ 2 · Updated 2026-05-28
AI/LLM integration with multiple providers, RAG, image generation, and personalization features
⚙ configure ⚙ chat ⚙ stream
stacks-ai - Stacks AI Integration
AI integration LLM image generation RAG
★ 2 · Updated 2026-05-28
Integrate AI capabilities into Stacks applications with multiple provider drivers, image generation, vision analysis, RAG, and personalization.
⚙ generate chat responses ⚙ stream chat messages ⚙ generate text prompts
stacks-ai - Stacks AI Integration
AI LLM Chat Image
★ 2 · Updated 2026-05-28
Comprehensive AI/LLM integration with multiple provider drivers for Stacks applications
⚙ configure anthropic ⚙ send chat message ⚙ stream chat message
chroma - Open-source embedding database
RAG Chroma Vector Database Embeddings
★ 0 · Updated 2026-05-28
Store embeddings and metadata with metadata-filtered vector search
⚙ create collection ⚙ add documents ⚙ query documents
stacks-ai - Integrate AI into Stacks applications
AI LLM RAG image generation
★ 628 · Updated 2026-05-28
Integrate AI capabilities into Stacks apps with multiple drivers, image generation, RAG, embeddings, and personalization features
⚙ configure driver ⚙ send chat message ⚙ stream chat response
rag-manager - RAG Index Manager
RAG semantic search BigQuery index management
★ 18 · Updated 2026-05-28
Manage RAG indices for BTDP infrastructure
⚙ list indices ⚙ create index ⚙ delete index
rag-manager - RAG Index Management
RAG semantic search BigQuery vector embeddings
★ 602 · Updated 2026-05-28
Manage RAG indices for BigQuery tables with list, search, create, and delete operations
⚙ list RAG indices ⚙ search RAG index ⚙ create RAG index
raon-os - AI Startup Companion for Korean Founders
startup business plan funding investor
★ 0 · Updated 2026-05-11
Evaluate business plans, match government funding programs, and connect with investors for Korean startups
⚙ evaluate business plan ⚙ match funding program ⚙ draft application document
AgentDB Vector Search - AgentDB Semantic Vector Search
vector search vector database semantic search embeddings
★ 18 · Updated 2026-05-11
Implement semantic vector search with AgentDB for document retrieval and similarity matching
⚙ Store vectors ⚙ Search similar vectors ⚙ Export vectors
AgentDB Vector Search - Semantic Vector Search with AgentDB
vector database semantic search RAG embeddings
★ 602 · Updated 2026-05-11
Implements vector-based semantic search using AgentDB for document retrieval and similarity matching
⚙ Initialize vector database ⚙ Store document vectors ⚙ Query vector similarity
smart-memory-system - RAG-based Smart Memory for OpenClaw
semantic search memory management RAG vector embedding
★ 33 · Updated 2026-05-09
Provides semantic search, memory optimization, and conversation enhancement for OpenClaw using RAG technology.
⚙ perform semantic search ⚙ enhance conversations ⚙ cluster similar memories
dba-vectordb - Vector Database Administration Agent
vector database pgvector semantic search RAG
★ 0 · Updated 2026-05-09
Design and optimize vector databases for semantic search and RAG applications with pgvector
⚙ create pgvector extension ⚙ design embedding schemas ⚙ create HNSW indexes

Scroll to load more