Haystack
获取企业支持
开始使用
📘 **TELUS Agriculture & Consumer Goods** 如何通过 **Haystack Agents** 转变促销交易

集成：Arize AI

使用 Arize AI 跟踪和监控您的 Haystack 管道

作者
Arize AI
Arize-ai
GitHub Repo PyPI Package

目录

概述

Arize 是一个 AI 可观测性和评估平台，旨在帮助您对 LLM 和 ML 应用程序进行故障排除、评估和实验。开发人员使用 Arize 来快速运行应用程序、评估性能、检测和防止生产问题以及整理数据集。

安装

pip install openinference-instrumentation-haystack haystack-ai arize-otel opentelemetry-sdk opentelemetry-exporter-otlp

使用

要使用 Arize 跟踪任何 Haystack 管道，只需初始化 OpenTelemetry 和 HaystackInstrumentor 即可。在同一环境中运行的 Haystack 管道会将跟踪发送到 Arize。

from openinference.instrumentation.haystack import HaystackInstrumentor
# Import open-telemetry dependencies
from arize_otel import register_otel, Endpoints

# Setup OTEL via our convenience function
register_otel(
    endpoints = Endpoints.ARIZE,
    space_id = "<your-space-id>", # from the space settings page
    api_key = "<your-api-key>", # from the space settings page
    model_id = "<your-haystack-app-name>", # name this to whatever you would like
)

现在，您可以在同一环境中运行 Haystack 管道，从而产生以下跟踪

要运行下面的示例，请将您的 OpenAI Key 导出到 OPENAI_API_KEY 环境变量。

Arize Demo 

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

document_store = InMemoryDocumentStore()
document_store.write_documents([
    Document(content="My name is Jean and I live in Paris."),
    Document(content="My name is Mark and I live in Berlin."),
    Document(content="My name is Giorgio and I live in Rome.")
])

prompt_template = """
Given these documents, answer the question.
Documents:
{% for doc in documents %}
    {{ doc.content }}
{% endfor %}
Question: {{question}}
Answer:
"""

retriever = InMemoryBM25Retriever(document_store=document_store)
prompt_builder = PromptBuilder(template=prompt_template)
llm = OpenAIGenerator()

rag_pipeline = Pipeline()
rag_pipeline.add_component("retriever", retriever)
rag_pipeline.add_component("prompt_builder", prompt_builder)
rag_pipeline.add_component("llm", llm)
rag_pipeline.connect("retriever", "prompt_builder.documents")
rag_pipeline.connect("prompt_builder", "llm")

question = "Who lives in Paris?"
results = rag_pipeline.run(
    {
        "retriever": {"query": question},
        "prompt_builder": {"question": question},
    }
)