汇总文本

信息

本教程演示了使用内置链和 LangGraph 进行文本摘要。

本页的早期版本展示了旧链 StuffDocumentsChain、MapReduceDocumentsChain 和 RefineDocumentsChain。有关使用这些抽象的信息以及与本教程中演示的方法的比较，请参阅此处。

假设您有一组文档（PDF、Notion 页面、客户问题等），并且您想要汇总内容。

鉴于 LLM 在理解和合成文本方面的熟练程度，这是一个很好的工具。

在检索增强生成的上下文中，摘要文本可以帮助提取大量检索文档中的信息，从而为 LLM 提供上下文。

在本演练中，我们将介绍如何使用 LLM 汇总多个文档中的内容。

图片描述

概念

我们将介绍的概念是：

使用语言模型。
使用文档加载器，特别是 WebBaseLoader 从 HTML 网页加载内容。
汇总或以其他方式合并文档的两种方法。
1. Stuff，它只是将文档连接到一个 Prompt;
2. Map-reduce，用于较大的文档集。这会将文档拆分为多个批次，汇总这些批次，然后汇总摘要。

有关这些策略和其他策略（包括迭代优化）的简短、有针对性的指南，请参阅操作指南。

设置

Jupyter 笔记本

本指南（以及文档中的大多数其他指南）使用 Jupyter 笔记本，并假设读者也使用 Jupyter 笔记本。Jupyter 笔记本非常适合学习如何使用 LLM 系统，因为很多时候事情可能会出错（意外输出、API 关闭等），在交互式环境中浏览指南是更好地了解它们的好方法。

本教程和其他教程可能在 Jupyter 笔记本中运行最方便。有关如何安装的说明，请参阅此处。

安装

要安装 LangChain，请运行：

果仁
康达

pip install langchain

conda install langchain -c conda-forge

有关更多详细信息，请参阅我们的安装指南。

LangSmith

您使用 LangChain 构建的许多应用程序将包含多个步骤，其中包含多次调用 LLM 调用。随着这些应用程序变得越来越复杂，能够检查您的链条或代理内部到底发生了什么变得至关重要。最好的方法是使用 LangSmith。

在上面的链接中注册后，请确保设置环境变量以开始记录跟踪：

export LANGSMITH_TRACING="true"
export LANGSMITH_API_KEY="..."

或者，如果在笔记本中，您可以通过以下方式设置它们：

import getpass
import os

os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = getpass.getpass()

概述

构建摘要器的一个核心问题是如何将您的文档传递到 LLM 的上下文窗口。两种常见的方法是：

Stuff：只需将所有文档“塞”到一个提示中即可。这是最简单的方法（请参阅此处有关create_stuff_documents_chainconstructor 的 Constructor 中，用于此方法）。
Map-reduce：在“映射”步骤中单独汇总每个文档，然后将摘要“缩减”为最终摘要（有关以下内容的更多信息，请参阅此处MapReduceDocumentsChain，用于此方法）。

请注意，当对子文档的理解不依赖于前面的上下文时，map-reduce 特别有效。例如，在总结包含许多较短文档的语料库时。在其他情况下，例如使用固有顺序总结小说或文本正文，迭代优化可能更有效。

图片描述

设置

首先设置环境变量并安装软件包：

%pip install --upgrade --quiet tiktoken langchain langgraph beautifulsoup4 langchain-community

# Set env var OPENAI_API_KEY or load from a .env file
# import dotenv

# dotenv.load_dotenv()

import os

os.environ["LANGSMITH_TRACING"] = "true"

首先，我们加载我们的文档。我们将使用 WebBaseLoader 加载一篇博文：

from langchain_community.document_loaders import WebBaseLoader

loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
docs = loader.load()

API 参考：WebBaseLoader

接下来，我们选择一个 LLM：

选择聊天模式：

pip install -qU "langchain[openai]"

import getpass
import os

if not os.environ.get("OPENAI_API_KEY"):
  os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")

from langchain.chat_models import init_chat_model

llm = init_chat_model("gpt-4o-mini", model_provider="openai")

内容：在单个 LLM 调用中总结

我们可以使用 create_stuff_documents_chain，尤其是在使用更大的上下文窗口模型时，例如：

128k 代币 OpenAIgpt-4o
200k 代币 Anthropicclaude-3-5-sonnet-20240620

链将获取一个文档列表，将它们全部插入到一个提示符中，并将该提示符传递给 LLM：

from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain.chains.llm import LLMChain
from langchain_core.prompts import ChatPromptTemplate

# Define prompt
prompt = ChatPromptTemplate.from_messages(
    [("system", "Write a concise summary of the following:\\n\\n{context}")]
)

# Instantiate chain
chain = create_stuff_documents_chain(llm, prompt)

# Invoke chain
result = chain.invoke({"context": docs})
print(result)

API 参考：create_stuff_documents_chain | LLMChain 法 | 聊天提示模板

The article "LLM Powered Autonomous Agents" by Lilian Weng discusses the development and capabilities of autonomous agents powered by large language models (LLMs). It outlines a system architecture that includes three main components: Planning, Memory, and Tool Use. 

1. **Planning** involves task decomposition, where complex tasks are broken down into manageable subgoals, and self-reflection, allowing agents to learn from past actions to improve future performance. Techniques like Chain of Thought (CoT) and Tree of Thoughts (ToT) are highlighted for enhancing reasoning and planning.

2. **Memory** is categorized into short-term and long-term memory, with mechanisms for fast retrieval using Maximum Inner Product Search (MIPS) algorithms. This allows agents to retain and recall information effectively.

3. **Tool Use** enables agents to interact with external APIs and tools, enhancing their capabilities beyond the limitations of their training data. Examples include MRKL systems and frameworks like HuggingGPT, which facilitate task planning and execution.

The article also addresses challenges such as finite context length, difficulties in long-term planning, and the reliability of natural language interfaces. It concludes with case studies demonstrating the practical applications of these concepts in scientific discovery and interactive simulations. Overall, the article emphasizes the potential of LLMs as powerful problem solvers in autonomous agent systems.

流

请注意，我们还可以逐个令牌流式传输结果：

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

|The| article| "|LL|M| Powered| Autonomous| Agents|"| by| Lil|ian| W|eng| discusses| the| development| and| capabilities| of| autonomous| agents| powered| by| large| language| models| (|LL|Ms|).| It| outlines| a| system| architecture| that| includes| three| main| components|:| Planning|,| Memory|,| and| Tool| Use|.| 

|1|.| **|Planning|**| involves| task| decomposition|,| where| complex| tasks| are| broken| down| into| manageable| sub|go|als|,| and| self|-ref|lection|,| allowing| agents| to| learn| from| past| actions| to| improve| future| performance|.| Techniques| like| Chain| of| Thought| (|Co|T|)| and| Tree| of| Thoughts| (|To|T|)| are| highlighted| for| enhancing| reasoning| and| planning|.

|2|.| **|Memory|**| is| categorized| into| short|-term| and| long|-term| memory|,| with| mechanisms| for| fast| retrieval| using| Maximum| Inner| Product| Search| (|M|IPS|)| algorithms|.| This| allows| agents| to| retain| and| recall| information| effectively|.

|3|.| **|Tool| Use|**| emphasizes| the| integration| of| external| APIs| and| tools| to| extend| the| capabilities| of| L|LM|s|,| enabling| them| to| perform| tasks| beyond| their| inherent| limitations|.| Examples| include| MR|KL| systems| and| frameworks| like| Hug|ging|GPT|,| which| facilitate| task| planning| and| execution|.

|The| article| also| addresses| challenges| such| as| finite| context| length|,| difficulties| in| long|-term| planning|,| and| the| reliability| of| natural| language| interfaces|.| It| concludes| with| case| studies| demonstrating| the| practical| applications| of| L|LM|-powered| agents| in| scientific| discovery| and| interactive| simulations|.| Overall|,| the| piece| illustrates| the| potential| of| L|LM|s| as| general| problem| sol|vers| and| their| evolving| role| in| autonomous| systems|.||

深入了解

您可以轻松自定义提示。
您可以通过 llm参数。

Map-Reduce：通过并行化总结长文本

让我们解读 map reduce 方法。为此，我们首先使用 LLM 将每个文档映射到单独的摘要。然后，我们将这些摘要缩减或合并到单个全局摘要中。

请注意，映射步骤通常在输入文档上并行化。

LangGraph 构建在langchain-core支持 map-reduce 工作流，非常适合此问题：

LangGraph 允许对单个步骤（例如连续摘要）进行流式处理，从而更好地控制执行;
LangGraph 的检查点支持错误恢复，通过人机协同工作流进行扩展，并更轻松地整合到对话应用程序中。
LangGraph 实现很容易修改和扩展，我们将在下面看到。

地图

让我们首先定义与 map 步骤关联的提示。我们可以使用与stuff方法，如上所示：

from langchain_core.prompts import ChatPromptTemplate

map_prompt = ChatPromptTemplate.from_messages(
    [("system", "Write a concise summary of the following:\\n\\n{context}")]
)

API 参考：ChatPromptTemplate

我们还可以使用 Prompt Hub 来存储和获取提示。

这将与您的 LangSmith API 密钥一起使用。

例如，请参阅此处的地图提示。

from langchain import hub

map_prompt = hub.pull("rlm/map-prompt")

API 参考：hub

减少

我们还定义了一个提示，该提示获取文档映射结果并将其缩减为单个输出。

# Also available via the hub: `hub.pull("rlm/reduce-prompt")`
reduce_template = """
The following is a set of summaries:
{docs}
Take these and distill it into a final, consolidated summary
of the main themes.
"""

reduce_prompt = ChatPromptTemplate([("human", reduce_template)])

通过 LangGraph 进行编排

下面我们实现了一个简单的应用程序，它将摘要步骤映射到文档列表上，然后使用上述提示减少它们。

当文本与 LLM 的上下文窗口相比较长时，Map-reduce 流特别有用。对于长文本，我们需要一种机制来确保在 reduce 步骤中要总结的上下文不超过模型的上下文窗口大小。在这里，我们实现了摘要的递归 “折叠”：根据令牌限制对输入进行分区，并生成分区的摘要。重复此步骤，直到摘要的总长度在所需的限制内，从而允许对任意长度的文本进行摘要。

首先，我们将博客文章分块成更小的 “子文档” 进行映射：

from langchain_text_splitters import CharacterTextSplitter

text_splitter = CharacterTextSplitter.from_tiktoken_encoder(
    chunk_size=1000, chunk_overlap=0
)
split_docs = text_splitter.split_documents(docs)
print(f"Generated {len(split_docs)} documents.")

API 参考：CharacterTextSplitter

Created a chunk of size 1003, which is longer than the specified 1000
``````output
Generated 14 documents.

接下来，我们定义我们的图形。请注意，我们人为地定义了 1,000 个令牌的最大令牌长度，以说明“折叠”步骤。

import operator
from typing import Annotated, List, Literal, TypedDict

from langchain.chains.combine_documents.reduce import (
    acollapse_docs,
    split_list_of_docs,
)
from langchain_core.documents import Document
from langgraph.constants import Send
from langgraph.graph import END, START, StateGraph

token_max = 1000


def length_function(documents: List[Document]) -> int:
    """Get number of tokens for input contents."""
    return sum(llm.get_num_tokens(doc.page_content) for doc in documents)


# This will be the overall state of the main graph.
# It will contain the input document contents, corresponding
# summaries, and a final summary.
class OverallState(TypedDict):
    # Notice here we use the operator.add
    # This is because we want combine all the summaries we generate
    # from individual nodes back into one list - this is essentially
    # the "reduce" part
    contents: List[str]
    summaries: Annotated[list, operator.add]
    collapsed_summaries: List[Document]
    final_summary: str


# This will be the state of the node that we will "map" all
# documents to in order to generate summaries
class SummaryState(TypedDict):
    content: str


# Here we generate a summary, given a document
async def generate_summary(state: SummaryState):
    prompt = map_prompt.invoke(state["content"])
    response = await llm.ainvoke(prompt)
    return {"summaries": [response.content]}


# Here we define the logic to map out over the documents
# We will use this an edge in the graph
def map_summaries(state: OverallState):
    # We will return a list of `Send` objects
    # Each `Send` object consists of the name of a node in the graph
    # as well as the state to send to that node
    return [
        Send("generate_summary", {"content": content}) for content in state["contents"]
    ]


def collect_summaries(state: OverallState):
    return {
        "collapsed_summaries": [Document(summary) for summary in state["summaries"]]
    }


async def _reduce(input: dict) -> str:
    prompt = reduce_prompt.invoke(input)
    response = await llm.ainvoke(prompt)
    return response.content


# Add node to collapse summaries
async def collapse_summaries(state: OverallState):
    doc_lists = split_list_of_docs(
        state["collapsed_summaries"], length_function, token_max
    )
    results = []
    for doc_list in doc_lists:
        results.append(await acollapse_docs(doc_list, _reduce))

    return {"collapsed_summaries": results}


# This represents a conditional edge in the graph that determines
# if we should collapse the summaries or not
def should_collapse(
    state: OverallState,
) -> Literal["collapse_summaries", "generate_final_summary"]:
    num_tokens = length_function(state["collapsed_summaries"])
    if num_tokens > token_max:
        return "collapse_summaries"
    else:
        return "generate_final_summary"


# Here we will generate the final summary
async def generate_final_summary(state: OverallState):
    response = await _reduce(state["collapsed_summaries"])
    return {"final_summary": response}


# Construct the graph
# Nodes:
graph = StateGraph(OverallState)
graph.add_node("generate_summary", generate_summary)  # same as before
graph.add_node("collect_summaries", collect_summaries)
graph.add_node("collapse_summaries", collapse_summaries)
graph.add_node("generate_final_summary", generate_final_summary)

# Edges:
graph.add_conditional_edges(START, map_summaries, ["generate_summary"])
graph.add_edge("generate_summary", "collect_summaries")
graph.add_conditional_edges("collect_summaries", should_collapse)
graph.add_conditional_edges("collapse_summaries", should_collapse)
graph.add_edge("generate_final_summary", END)

app = graph.compile()

API 参考：acollapse_docs | split_list_of_docs | 文档 | 发送 | StateGraph

LangGraph 允许绘制图形结构以帮助可视化其功能：

from IPython.display import Image

Image(app.get_graph().draw_mermaid_png())

运行应用程序时，我们可以流式传输图形以观察其步骤顺序。下面，我们将简单地打印出步骤的名称。

请注意，由于我们在图中有一个循环，因此在其执行时指定一个 recursion_limit 可能会有所帮助。当超过指定的限制时，这将引发特定错误。

async for step in app.astream(
    {"contents": [doc.page_content for doc in split_docs]},
    {"recursion_limit": 10},
):
    print(list(step.keys()))

['generate_summary']
['generate_summary']
['generate_summary']
['generate_summary']
['generate_summary']
['generate_summary']
['generate_summary']
['generate_summary']
['generate_summary']
['generate_summary']
['generate_summary']
['generate_summary']
['generate_summary']
['generate_summary']
['collect_summaries']
['collapse_summaries']
['collapse_summaries']
['generate_final_summary']

print(step)

{'generate_final_summary': {'final_summary': 'The consolidated summary of the main themes from the provided documents is as follows:\n\n1. **Integration of Large Language Models (LLMs) in Autonomous Agents**: The documents explore the evolving role of LLMs in autonomous systems, emphasizing their enhanced reasoning and acting capabilities through methodologies that incorporate structured planning, memory systems, and tool use.\n\n2. **Core Components of Autonomous Agents**:\n   - **Planning**: Techniques like task decomposition (e.g., Chain of Thought) and external classical planners are utilized to facilitate long-term planning by breaking down complex tasks.\n   - **Memory**: The memory system is divided into short-term (in-context learning) and long-term memory, with parallels drawn between human memory and machine learning to improve agent performance.\n   - **Tool Use**: Agents utilize external APIs and algorithms to enhance problem-solving abilities, exemplified by frameworks like HuggingGPT that manage task workflows.\n\n3. **Neuro-Symbolic Architectures**: The integration of MRKL (Modular Reasoning, Knowledge, and Language) systems combines neural and symbolic expert modules with LLMs, addressing challenges in tasks such as verbal math problem-solving.\n\n4. **Specialized Applications**: Case studies, such as ChemCrow and projects in anticancer drug discovery, demonstrate the advantages of LLMs augmented with expert tools in specialized domains.\n\n5. **Challenges and Limitations**: The documents highlight challenges such as hallucination in model outputs and the finite context length of LLMs, which affects their ability to incorporate historical information and perform self-reflection. Techniques like Chain of Hindsight and Algorithm Distillation are discussed to enhance model performance through iterative learning.\n\n6. **Structured Software Development**: A systematic approach to creating Python software projects is emphasized, focusing on defining core components, managing dependencies, and adhering to best practices for documentation.\n\nOverall, the integration of structured planning, memory systems, and advanced tool use aims to enhance the capabilities of LLM-powered autonomous agents while addressing the challenges and limitations these technologies face in real-world applications.'}}

在相应的 LangSmith 跟踪中，我们可以看到各个 LLM 调用，它们分组在各自的节点下。

深入了解

定制

如上所示，您可以自定义 map 和 reduce 阶段的 LLM 和提示。

真实用例

请参阅这篇关于分析用户交互的博客文章案例研究（有关 LangChain 文档的问题）！
该博客文章和关联的存储库还引入了集群作为摘要的一种方式。
这开辟了另一条超越stuff或map-reduce方法，值得考虑。

图片描述

后续步骤

我们鼓励您查看操作指南，了解有关以下方面的更多详细信息：

其他摘要策略，例如迭代优化
内置文档加载器和文本拆分器
将各种组合文档链集成到 RAG 应用程序中
将检索整合到聊天机器人中

和其他概念。