# haystack

> Builds NLP pipelines with Haystack for document search, QA, and LLM-powered applications.

- Skill: `ssrjkk/haystack` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds add ssrjkk/haystack`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ssrjkk/haystack/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: ssrjkk (https://skillmd.com/u/ssrjkk)
- Updated: 2026-08-19
- Page: https://skillmd.com/skills/ssrjkk/haystack

---

# Haystack
> NLP framework for building search and QA systems.
## Quick Start
```python
from haystack import Pipeline
from haystack.components.retrievers import InMemoryBM25Retriever
from haystack_integrations.components.generators import OpenAIGenerator
pipeline = Pipeline()
pipeline.add_component("retriever", InMemoryBM25Retriever(top_k=3))
pipeline.add_component("llm", OpenAIGenerator())
pipeline.connect("retriever.documents", "llm.documents")
result = pipeline.run({"retriever": {"query": "What is Haystack?"}})
```
## When to Use
- Document retrieval; QA over custom data; Hybrid search; NLP pipelines
## Validation
1. Pipeline compiles; 2. Retrieval returns relevant docs; 3. LLM generates context-based answers