← back to the directory
Library / SDK Retrieval & MemoryAgents & Orchestration

Haystack

1Production-ready 2pipelines 3for 4search 5and 6RAG.

the six Ws · specification

W1 Who

Open-source framework from deepset.

W2 What

Builds search, RAG, and question-answering pipelines.

W3 Where

A Python library, self-hosted or on deepset Cloud.

W4 When

When production retrieval and RAG quality matter.

W5 Why

Composable, production-focused pipelines over your data.

W6 With

Document stores, embedding models, and an LLM.

PythonRAGSearchPipelines

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.