Haystack – Production RAG Framework

SkillAI & models

Build production-ready RAG pipelines with Haystack

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Haystack skill

What this skill tells your AI

The instructions your AI receives, as published by bidewio/better-openclaw in skills/haystack-rag/SKILL.md and read by ahel’s review.

Haystack is an open-source framework for building production-ready search and question-answering systems using RAG.

  • GitHub: github.com/deepset-ai/haystack (20 000+ ⭐)
  • License: Apache-2.0
  • Security: Backed by deepset. Enterprise-grade. No malware.

Environment Variables

VariableDescription
{{HAYSTACK_URL}}Base URL of a Haystack pipeline API

Usage Examples

Query a deployed pipeline

curl -s -X POST "{{HAYSTACK_URL}}/query" \
  -H "Content-Type: application/json" \
  -d '{"query": "What is retrieval augmented generation?"}'

AI Agent Tips

  • Modular pipeline architecture: swap retrievers, generators, and stores.
  • Supports hybrid search (BM25 + dense vector retrieval).
  • Built-in evaluation tools for measuring RAG quality.
  • Integrates with Elasticsearch, OpenSearch, Qdrant, Weaviate, and more.

Signals

GitHub stars
58
Forks
6
Last commit
Aug 2026
Advanced
Item type
skill
Key
haystack-rag
Source
github.com/bidewio/better-openclaw