从 StuffDocumentsChain 迁移

StuffDocumentsChain 通过将文档连接成一个单一的上下文窗口来组合文档。这是一种简单有效的策略，用于问题回答、摘要和其他目的。

create_stuff_documents_chain 是推荐的替代方案。它的功能与 StuffDocumentsChain 相同，但对流式处理和批量功能的支持更好。由于它是 LCEL 原语 的简单组合，因此更容易扩展并融入其他 LangChain 应用程序。

下面我们将通过一个简单的示例来介绍 StuffDocumentsChain 和 create_stuff_documents_chain。

让我们首先加载一个聊天模型：

OpenAI

pip install -qU langchain-openai

import getpass
import os

os.environ["OPENAI_API_KEY"] = getpass.getpass()

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="gpt-4o-mini")

Anthropic

pip install -qU langchain-anthropic

import getpass
import os

os.environ["ANTHROPIC_API_KEY"] = getpass.getpass()

from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(model="claude-3-5-sonnet-20240620")

Azure

pip install -qU langchain-openai

import getpass
import os

os.environ["AZURE_OPENAI_API_KEY"] = getpass.getpass()

from langchain_openai import AzureChatOpenAI

llm = AzureChatOpenAI(
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
    openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
)

Google

pip install -qU langchain-google-vertexai

import getpass
import os

os.environ["GOOGLE_API_KEY"] = getpass.getpass()

from langchain_google_vertexai import ChatVertexAI

llm = ChatVertexAI(model="gemini-1.5-flash")

Cohere

pip install -qU langchain-cohere

import getpass
import os

os.environ["COHERE_API_KEY"] = getpass.getpass()

from langchain_cohere import ChatCohere

llm = ChatCohere(model="command-r-plus")

NVIDIA

pip install -qU langchain-nvidia-ai-endpoints

import getpass
import os

os.environ["NVIDIA_API_KEY"] = getpass.getpass()

from langchain import ChatNVIDIA

llm = ChatNVIDIA(model="meta/llama3-70b-instruct")

FireworksAI

pip install -qU langchain-fireworks

import getpass
import os

os.environ["FIREWORKS_API_KEY"] = getpass.getpass()

from langchain_fireworks import ChatFireworks

llm = ChatFireworks(model="accounts/fireworks/models/llama-v3p1-70b-instruct")

Groq

pip install -qU langchain-groq

import getpass
import os

os.environ["GROQ_API_KEY"] = getpass.getpass()

from langchain_groq import ChatGroq

llm = ChatGroq(model="llama3-8b-8192")

MistralAI

pip install -qU langchain-mistralai

import getpass
import os

os.environ["MISTRAL_API_KEY"] = getpass.getpass()

from langchain_mistralai import ChatMistralAI

llm = ChatMistralAI(model="mistral-large-latest")

TogetherAI

pip install -qU langchain-openai

import getpass
import os

os.environ["TOGETHER_API_KEY"] = getpass.getpass()

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://api.together.xyz/v1",
    api_key=os.environ["TOGETHER_API_KEY"],
    model="mistralai/Mixtral-8x7B-Instruct-v0.1",
)

示例

让我们通过一个示例来分析一组文档。我们首先生成一些简单的文档以作说明：

<!--IMPORTS:[{"imported": "Document", "source": "langchain_core.documents", "docs": "https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html", "title": "Migrating from StuffDocumentsChain"}]-->
from langchain_core.documents import Document

documents = [
    Document(page_content="Apples are red", metadata={"title": "apple_book"}),
    Document(page_content="Blueberries are blue", metadata={"title": "blueberry_book"}),
    Document(page_content="Bananas are yelow", metadata={"title": "banana_book"}),
]

旧版

Details

下面我们展示了一个使用 StuffDocumentsChain 的实现。我们为摘要任务定义了提示词模板，并为此目的实例化了一个 LLMChain 对象。我们定义了文档如何格式化为提示，并确保各种提示中的键保持一致。

<!--IMPORTS:[{"imported": "LLMChain", "source": "langchain.chains", "docs": "https://python.langchain.com/api_reference/langchain/chains/langchain.chains.llm.LLMChain.html", "title": "Migrating from StuffDocumentsChain"}, {"imported": "StuffDocumentsChain", "source": "langchain.chains", "docs": "https://python.langchain.com/api_reference/langchain/chains/langchain.chains.combine_documents.stuff.StuffDocumentsChain.html", "title": "Migrating from StuffDocumentsChain"}, {"imported": "ChatPromptTemplate", "source": "langchain_core.prompts", "docs": "https://python.langchain.com/api_reference/core/prompts/langchain_core.prompts.chat.ChatPromptTemplate.html", "title": "Migrating from StuffDocumentsChain"}, {"imported": "PromptTemplate", "source": "langchain_core.prompts", "docs": "https://python.langchain.com/api_reference/core/prompts/langchain_core.prompts.prompt.PromptTemplate.html", "title": "Migrating from StuffDocumentsChain"}]-->
from langchain.chains import LLMChain, StuffDocumentsChain
from langchain_core.prompts import ChatPromptTemplate, PromptTemplate

# This controls how each document will be formatted. Specifically,
# it will be passed to `format_document` - see that function for more
# details.
document_prompt = PromptTemplate(
    input_variables=["page_content"], template="{page_content}"
)
document_variable_name = "context"
# The prompt here should take as an input variable the
# `document_variable_name`
prompt = ChatPromptTemplate.from_template("Summarize this content: {context}")

llm_chain = LLMChain(llm=llm, prompt=prompt)
chain = StuffDocumentsChain(
    llm_chain=llm_chain,
    document_prompt=document_prompt,
    document_variable_name=document_variable_name,
)

我们现在可以调用我们的链：

result = chain.invoke(documents)
result["output_text"]

'This content describes the colors of different fruits: apples are red, blueberries are blue, and bananas are yellow.'

for chunk in chain.stream(documents):
    print(chunk)

{'input_documents': [Document(metadata={'title': 'apple_book'}, page_content='Apples are red'), Document(metadata={'title': 'blueberry_book'}, page_content='Blueberries are blue'), Document(metadata={'title': 'banana_book'}, page_content='Bananas are yelow')], 'output_text': 'This content describes the colors of different fruits: apples are red, blueberries are blue, and bananas are yellow.'}

LCEL

Details

下面我们展示了一个使用 create_stuff_documents_chain 的实现：

<!--IMPORTS:[{"imported": "create_stuff_documents_chain", "source": "langchain.chains.combine_documents", "docs": "https://python.langchain.com/api_reference/langchain/chains/langchain.chains.combine_documents.stuff.create_stuff_documents_chain.html", "title": "Migrating from StuffDocumentsChain"}, {"imported": "ChatPromptTemplate", "source": "langchain_core.prompts", "docs": "https://python.langchain.com/api_reference/core/prompts/langchain_core.prompts.chat.ChatPromptTemplate.html", "title": "Migrating from StuffDocumentsChain"}]-->
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_template("Summarize this content: {context}")
chain = create_stuff_documents_chain(llm, prompt)

调用链后，我们获得了与之前类似的结果：

result = chain.invoke({"context": documents})
result

'This content describes the colors of different fruits: apples are red, blueberries are blue, and bananas are yellow.'

请注意，此实现支持输出令牌的流式处理：

for chunk in chain.stream({"context": documents}):
    print(chunk, end=" | ")

 | This |  content |  describes |  the |  colors |  of |  different |  fruits | : |  apples |  are |  red | , |  blue | berries |  are |  blue | , |  and |  bananas |  are |  yellow | . |  |

下一步

查看 LCEL 概念文档 以获取更多背景信息。

查看这些 操作指南 以获取有关使用 RAG 进行问答任务的更多信息。

请查看这个教程以获取更多基于大型语言模型的摘要策略。