Haystack, from deepset, is built around explicit pipelines. You wire components together and can see exactly what happens at each hop, which matters when retrieval quality is the thing you are debugging.
Reach for it when
- You are building search or question answering over a corpus
- You want to inspect and tune each stage of retrieval
- You need a pipeline you can evaluate properly
Look elsewhere when
- You want an agent that mostly calls tools
- You prefer convention over explicit wiring
What the lessons will cover
- 01Install and setup
- 02Components and pipelines
- 03Document stores
- 04Retrievers
- 05Generators
- 06Evaluation
- 07Agents in Haystack
- 08A production pipeline
Others in data and rag
LlamaIndexAgents that reason over your own documents.
DSPyStop writing prompts. Compile them instead.Common questions
Is Haystack free to use?
Haystack is open source and free to run yourself. You still pay whichever model provider you point it at, and this tutorial is free with no signup.
Do I need to know Python to use Haystack?
Basic Python is enough. Functions, dictionaries and imports cover most of what Haystack asks of you.
When should I not use Haystack?
You want an agent that mostly calls tools. You prefer convention over explicit wiring.
Lessons for Haystack are being written. Meanwhile the LangGraph tutorial covers the same ground: state, tools, loops, memory and human approval. Most of it carries straight over.
Start the LangGraph tutorial →