← The AI Systems Map
L0 · LabsFramework / toolingNew York, NY

Vector databases

Retrieval substrate for RAG (Pinecone, Milvus, pgvector)

Vector databases (Pinecone, Weaviate, Milvus/Zilliz, Qdrant, Chroma, and pgvector on Postgres) store embeddings and power semantic retrieval for RAG and agent memory. They are the memory tier of the AI application stack, increasingly commoditized into general databases even as specialized players persist.

Players

Pinecone, Milvus, Qdrant, pgvector

Role

embedding retrieval / RAG

How it fits the stack

Vector databases with what it depends on (above) and what it feeds (below). The figure renders as a crawlable diagram and upgrades to an interactive 3D graph as it scrolls into view.

usesdepends onused byused byusesdepends onVector databasesLabsAgent frameworks(LangChain,LlamaIndex, etc.)Agent OrchestrationFrameworksAgentic AI /autonomous workflowsClaude (Opus / Sonnet)LangChain / LangGraphLegal AI
Vector databasesFeeds ↓

Vector databases in the AI stack. Vector databases with its immediate upstream dependencies (top) and downstream dependents (bottom) in the AI value chain. Hover a node in 3D, or read the full relationships below.

Graph data (text) — 7 entities, 6 relationships
  • Agent frameworks (LangChain, LlamaIndex, etc.)usesVector databases
  • Agent Orchestration Frameworksdepends onVector databases
  • Agentic AI / autonomous workflowsused byVector databases
  • Claude (Opus / Sonnet)used byVector databases
  • LangChain / LangGraphusesVector databases
  • Legal AIdepends onVector databases