Cookbook: Langchain 集成（Python）

本 cookbook 提供了 Litefuse 与 Langchain（Python）集成的示例。

请按照集成指南将该集成添加到你的 Langchain 项目中。该集成也支持 Langchain JS。

设置

%pip install langfuse langchain langchain_openai langchain_community --upgrade

在 Litefuse UI 的项目设置中获取 API key，用它们初始化 Langfuse 客户端，并设置到环境变量中。

import os
 
# Get keys for your project from the project settings page: https://litefuse.cloud
os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..." 
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..." 
os.environ["LANGFUSE_BASE_URL"] = "https://litefuse.cloud"
 
# Your openai key
os.environ["OPENAI_API_KEY"] = "sk-proj-.."

from langfuse.langchain import CallbackHandler
 
# Initialize Langfuse CallbackHandler for Langchain (tracing)
langfuse_handler = CallbackHandler()

示例

使用 Langchain Expression Language (LCEL) 的串行 Chain

Langchain LCEL 的 trace

Litefuse 中的示例 trace

from operator import itemgetter
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langchain.schema import StrOutputParser
 
langfuse_handler = CallbackHandler()
 
prompt1 = ChatPromptTemplate.from_template("what is the city {person} is from?")
prompt2 = ChatPromptTemplate.from_template(
    "what country is the city {city} in? respond in {language}"
)
model = ChatOpenAI()
chain1 = prompt1 | model | StrOutputParser()
chain2 = (
    {"city": chain1, "language": itemgetter("language")}
    | prompt2
    | model
    | StrOutputParser()
)
 
chain2.invoke({"person": "obama", "language": "spanish"}, config={"callbacks":[langfuse_handler]})

'Barack Obama es de la ciudad de Chicago, Illinois, en los Estados Unidos.'

Runnable 方法

Runnable 是可调用、可批处理、可流式处理、可转换、可组合的工作单元。

下面的示例演示了如何在 Litefuse 中使用以下方法：

invoke/ainvoke：将单个输入转换为输出。
batch/abatch：高效地将多个输入转换为多个输出。
stream/astream：从单个输入开始，边产生边流式输出。

# Async Invoke
await chain2.ainvoke({"person": "biden", "language": "german"}, config={"callbacks":[langfuse_handler]})
 
# Batch
chain2.batch([{"person": "elon musk", "language": "english"}, {"person": "mark zuckerberg", "language": "english"}], config={"callbacks":[langfuse_handler]})
 
# Async Batch
await chain2.abatch([{"person": "jeff bezos", "language": "english"}, {"person": "tim cook", "language": "english"}], config={"callbacks":[langfuse_handler]})
 
# Stream
for chunk in chain2.stream({"person": "steve jobs", "language": "english"}, config={"callbacks":[langfuse_handler]}):
    print("Streaming chunk:", chunk)
 
# Async Stream
async for chunk in chain2.astream({"person": "bill gates", "language": "english"}, config={"callbacks":[langfuse_handler]}):
    print("Async Streaming chunk:", chunk)

RetrievalQA

Litefuse 中 Langchain QA Retrieval 的 trace

Litefuse 中的示例 trace

import os
os.environ["SERPAPI_API_KEY"] = "..."

%pip install unstructured selenium langchain-chroma --upgrade

from langchain_community.document_loaders import SeleniumURLLoader
from langchain_chroma import Chroma
from langchain_text_splitters import CharacterTextSplitter
from langchain_openai import OpenAIEmbeddings
from langchain.chains import RetrievalQA
 
langfuse_handler = CallbackHandler()
 
urls = [
    "https://raw.githubusercontent.com/litefuse/litefuse-docs/main/public/state_of_the_union.txt",
]
loader = SeleniumURLLoader(urls=urls)
llm = OpenAI()
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
docsearch = Chroma.from_documents(texts, embeddings)
query = "What did the president say about Ketanji Brown Jackson"
chain = RetrievalQA.from_chain_type(
    llm,
    retriever=docsearch.as_retriever(search_kwargs={"k": 1}),
)
 
chain.invoke(query, config={"callbacks":[langfuse_handler]})

{'query': 'What did the president say about Ketanji Brown Jackson',
 'result': " The president nominated her to serve on the United States Supreme Court and praised her as one of the nation's top legal minds who will continue the legacy of retiring Justice Stephen Breyer."}

AzureOpenAI

os.environ["AZURE_OPENAI_ENDPOINT"] = "<Azure OpenAI endpoint>"
os.environ["AZURE_OPENAI_API_KEY"] = "<Azure OpenAI API key>"
os.environ["OPENAI_API_TYPE"] = "azure"
os.environ["OPENAI_API_VERSION"] = "2023-09-01-preview"

from langchain_openai import AzureChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langfuse.langchain import CallbackHandler
 
# Initialize Langfuse CallbackHandler for Langchain (tracing)
langfuse_handler = CallbackHandler()
 
prompt = ChatPromptTemplate.from_template("what is the city {person} is from?")
model = AzureChatOpenAI(
    deployment_name="gpt-4o",
    model_name="gpt-4o",
)
chain = prompt | model
 
chain.invoke({"person": "Satya Nadella"}, config={"callbacks":[langfuse_handler]})

Databricks LangGraph 的开源可观测性

这个页面对你有帮助吗？

支持