Haystack is an open-source AI orchestration framework by deepset for building customizable, production-ready LLM applications through modular pipelines. With 24.6K GitHub stars and active development since 2019, it is one of the longest-standing AI frameworks, evolving from a question-answering system to a comprehensive pipeline-based orchestration platform.

framework python pipelines rag production orchestration deepset

Haystack was created by deepset (Berlin, Germany) in 2019 as an open-source question-answering framework focused on extractive QA over documents. Over six years, it has evolved through multiple paradigm shifts — from neural search with dense retrievers (2020-2021) to RAG pipelines (2022-2023) to the fully redesigned Haystack 2.0 with component-based architecture and agent workflows (2023-2024). The framework emphasizes production-readiness with built-in observability, async execution, and Kubernetes integration.¹⁾²⁾³⁾

• Modular Pipelines — Directed acyclic graphs (DAGs) of components for RAG, QA, semantic search, and more
• 200+ Components — Document stores, embeddings, LLMs, retrievers, readers, converters, and evaluators
• Production-Ready — OpenTelemetry tracing, retries, caching, error handling, Kubernetes/Docker deployment
• Agent Workflows — Tool-using agents with reasoning loops and conditional logic
• Hybrid Search — Combine sparse (BM25) and dense (DPR) retrieval with reranking
• Component-Based — Stateless, composable components with Pydantic-validated I/O schemas
• Evaluation Metrics — Built-in SquadMetric, ExactMatchMetric, and custom evaluators
• Document Stores — Pluggable backends: Elasticsearch, OpenSearch, Pinecone, Weaviate, Chroma, In-Memory

Haystack's pipeline-centric architecture:

Infrastructure Layer:

Building a RAG pipeline with Haystack 2.x:

from haystack import Pipeline
from haystack.components.generators import OpenAIGenerator
from haystack.components.builders.prompt_builder import PromptBuilder
from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.dataclasses import Document
 
# Set up document store with sample data
doc_store = InMemoryDocumentStore()
doc_store.write_documents([
    Document(content="Haystack is an AI orchestration framework by deepset."),
    Document(content="It supports [[modular|modular]] pipelines for RAG and search."),
    Document(content="Haystack 2.0 introduced component-based architecture."),
])
 
# Build RAG pipeline
template = """
Given these documents, answer the question.
Documents: {% for doc in documents %}{{ doc.content }}{% endfor %}
Question: {{ question }}
"""
 
rag_pipeline = Pipeline()
rag_pipeline.add_component("retriever", InMemoryBM25Retriever(document_store=doc_store))
rag_pipeline.add_component("prompt", PromptBuilder(template=template))
rag_pipeline.add_component("llm", OpenAIGenerator(model="gpt-4o"))
rag_pipeline.connect("retriever", "prompt.documents")
rag_pipeline.connect("prompt", "llm")
 
result = rag_pipeline.run({
    "retriever": {"query": "What is Haystack?"},
    "prompt": {"question": "What is Haystack?"}
})
print(result["llm"]["replies"][0])

• 2019 — Initial release as extractive QA framework
• 2020-2021 — Dense retrievers (DPR), Transformers integration, v1.0 stable
• 2022 — Pivot to RAG amid LLM rise, OpenAI GPT support
• 2023 — Haystack 2.0 overhaul with component-based design, agents, multi-modal
• 2024-2025 — Enterprise features, advanced orchestration, self-improving pipelines
• 2026 — Milestone #2: context-engineered LLM apps, improved agent workflows

• AI Orchestration Layers
• Pipecat
• Tool Use and Orchestration
• OpenAI Swarm
• Agentic Orchestration Platforms Comparison