Haystack Has a Free API — Build Production AI Pipelines

#ai #llm #machinelearning #python

Haystack: Industrial-Strength AI Pipelines

Haystack by deepset builds production-ready RAG and LLM apps. Pipeline-first architecture, type-safe, debuggable.

Why Haystack

Pipeline-first — explicit data flow
Type-safe component connections
Built-in evaluation metrics
Production-focused design

The Free API

from haystack import Pipeline, Document
from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
from haystack.components.generators import OpenAIGenerator
from haystack.components.builders.prompt_builder import PromptBuilder
from haystack.document_stores.in_memory import InMemoryDocumentStore

store = InMemoryDocumentStore()
store.write_documents([Document(content="Refund policy: 30 days.")])

template = "Context: {% for d in documents %}{{d.content}}{% endfor %}\nQ: {{question}}"

pipe = Pipeline()
pipe.add_component("retriever", InMemoryBM25Retriever(document_store=store))
pipe.add_component("prompt", PromptBuilder(template=template))
pipe.add_component("llm", OpenAIGenerator(model="gpt-4o"))
pipe.connect("retriever", "prompt.documents")
pipe.connect("prompt", "llm")

result = pipe.run({"retriever": {"query": "refund?"}, "prompt": {"question": "refund?"}})
print(result["llm"]["replies"][0])