🧲 PackIA: RAG & Vector Databases
Your knowledge, retrievable by any agent
Direct answer: Your knowledge, retrievable by any agent This pack brings together 7 resources for Claude, Claude Code, ChatGPT Codex.
Production-grade RAG architectures: smart chunking, embeddings, hybrid search with Qdrant, reranking, and systematic evaluation so answers are accurate and citable.
Included in the Completo — $50
Plans are cumulative: the Pro Plan includes all Essential Plan packs, and the Complete Plan includes all packs (Essential + Pro). This pack unlocks with the Completo ($50).
Buy with the Completo ($50) Or build your custom plan
Use cases
- Complete RAG pipeline with Qdrant and hybrid search
- Chunking strategy by document type, with tests
- Automated evaluation of retrieval and answer faithfulness
Master prompt: RAG Architect
You are a RAG systems architect. Documents: {documents} ({volume}), use: {use_case}, requirements: latency {latency}, high accuracy. 1) Ingestion: cleaning, chunking (size, overlap, metadata) by document type, 2) retrieval: chosen embeddings, hybrid search with reranking, 3) generation: prompt with mandatory citations and an abstention policy, 4) evaluation: recall@k, faithfulness, test dataset, 5) estimated costs per 1000 queries and optimizations.
Included resources (7)
- qdrant (MCP Server, qdrant/mcp-server-qdrant, ★ 1.5k · official) — Vector storage and semantic search: long-term memory for agents. GitHub
- claude-api (Skill, anthropics/skills, ★ 176.6k · official) — Claude API reference: models, pricing, parameters, streaming, tool use, MCP, and token counting. GitHub
- LangGraph (Agent, langchain-ai/langgraph, ★ 41.8k) — Low-level orchestration for stateful, long-running agents, with deterministic or dynamic flows. GitHub
- Deep Agents (Agent, langchain-ai/deepagents, ★ 29.5k) — LangChain's batteries-included agent: plan, read and write files, and delegate to subagents for long tasks. GitHub
- tavily (MCP Server, tavily-ai/tavily-mcp, ★ 2.4k · official) — Production-ready real-time web search: extraction, sitemaps, and crawling. GitHub
- Prompt Engineering Guide (Prompt collection, dair-ai/Prompt-Engineering-Guide, ★ 78.4k) — Guide, papers, and notebooks on prompt engineering, RAG, and agents: few-shot, CoT, and self-consistency. GitHub
- mcp-builder (Skill, anthropics/skills, ★ 176.6k · official) — Official guide for creating high-quality MCP servers in Python (FastMCP) or TypeScript, with tools and evaluation suites. GitHub
Versions by tool
Related packs
Frequently asked questions
What is the RAG & Vector Databases pack?
Your knowledge, retrievable by any agent Includes 7 resources.
Who is it for?
For professionals and teams working in RAG & Vector Databases who want proven resources for their AI assistant.
What does it include and how much does it cost?
Includes 7 resources (Agent (2), MCP Server (2), Prompt collection (1), Skill (2)) and unlocks with the Complete Plan ($50). Plans are cumulative.