本指南回顾了如何让模型在生成响应时添加引用的源文档的哪些部分。
本文介绍了5种方法：
- 使用函数调用来引用文档ID；
- 使用函数调用来引用文档ID并提供文本片段；
- 直接使用提示词；
- 检索后处理（压缩检索到的上下文以使其更具相关性）；
- 生成后处理（再次通过 LLM 来用引文注释生成的答案）。
我们通常建议使用第 1 种方法，也就是说，如果模型支持函数调用，推荐方法 1 或 2；否则，或者如果这些方法失败，可以继续尝试其它方法。
让我们先创建一个简单的 RAG 链，使用 WikipediaRetriever 从 Wikipedia 中进行检索。
llm = ChatOpenAI(
base_url="https://api.zhizengzeng.com/v1/",
api_key="sk-******",
model="gpt-3.5-turbo"
)
system_prompt = (
"You're a helpful AI assistant. Given a user question "
"and some Wikipedia article snippets, answer the user "
"question. If none of the articles answer the question, "
"just say you don't know."
"\n\nHere are the Wikipedia articles: "
"{context}"
)
retriever = WikipediaRetriever(top_k_results=6, doc_content_chars_max=2000)
prompt = ChatPromptTemplate.from_messages(
[
("system", system_prompt),
("human", "{input}"),
]
)现在我们有了模型、检索器和提示词，接下来让我们将它们全部链接在一起。
我们需要添加一些逻辑，将检索到的文档格式化为可以传递给提示词的字符串，我们将使我们的链同时返回答案和检索到的文档。
def format_docs(docs: List[Document]):
return "\n\n".join(doc.page_content for doc in docs)
rag_chain_from_docs = (
RunnablePassthrough.assign(context=(lambda x: format_docs(x["context"])))
| prompt
| llm
| StrOutputParser()
)
retrieve_docs = (lambda x: x["input"]) | retriever
chain = RunnablePassthrough.assign(context=retrieve_docs).assign(
answer=rag_chain_from_docs
)
result = chain.invoke({"input": "How fast are cheetahs?"})print(result.keys())
# dict_keys(['input', 'context', 'answer'])
print(result["context"][0])
# page_content='The cheetah (Acinonyx jubatus) is a large cat and the fastest land animal. It has a tawny to creamy white or pale buff fur that is marked with evenly spaced, solid black spots. The head is small and rounded, with a short snout and black tear-like facial streaks. It reaches 67–94 cm (26–37 in) at the shoulder, and the head-and-body length is between 1.1 and 1.5 m (3 ft 7 in and 4 ft 11 in). Adults weigh between 21 and 72 kg (46 and 159 lb). The cheetah is capable of running at 93 to 104 km/h (58 to 65 mph); it has evolved specialized adaptations for speed, including a light build, long thin legs and a long tail.\nThe cheetah was first described in the late 18th century. Four subspecies are recognised today that are native to Africa and central Iran. An African subspecies was introduced to India in 2022. It is now distributed mainly in small, fragmented populations in northwestern, eastern and southern Africa and central Iran. It lives in a variety of habitats such as savannahs in the Serengeti, arid mountain ranges in the Sahara, and hilly desert terrain.\nThe cheetah lives in three main social groups: females and their cubs, male "coalitions", and solitary males. While females lead a nomadic life searching for prey in large home ranges, males are more sedentary and instead establish much smaller territories in areas with plentiful prey and access to females. The cheetah is active during the day, with peaks during dawn and dusk. It feeds on small- to medium-sized prey, mostly weighing under 40 kg (88 lb), and prefers medium-sized ungulates such as impala, springbok and Thomson\'s gazelles. The cheetah typically stalks its prey within 60–100 m (200–330 ft) before charging towards it, trips it during the chase and bites its throat to suffocate it to death. It breeds throughout the year. After a gestation of nearly three months, females give birth to a litter of three or four cubs. Cheetah cubs are highly vulnerable to predation by other large carnivores. They are weaned a' metadata={'title': 'Cheetah', 'summary': 'The cheetah (Acinonyx jubatus) is a large cat and the fastest land animal. It has a tawny to creamy white or pale buff fur that is marked with evenly spaced, solid black spots. The head is small and rounded, with a short snout and black tear-like facial streaks. It reaches 67–94 cm (26–37 in) at the shoulder, and the head-and-body length is between 1.1 and 1.5 m (3 ft 7 in and 4 ft 11 in). Adults weigh between 21 and 72 kg (46 and 159 lb). The cheetah is capable of running at 93 to 104 km/h (58 to 65 mph); it has evolved specialized adaptations for speed, including a light build, long thin legs and a long tail.\nThe cheetah was first described in the late 18th century. Four subspecies are recognised today that are native to Africa and central Iran. An African subspecies was introduced to India in 2022. It is now distributed mainly in small, fragmented populations in northwestern, eastern and southern Africa and central Iran. It lives in a variety of habitats such as savannahs in the Serengeti, arid mountain ranges in the Sahara, and hilly desert terrain.\nThe cheetah lives in three main social groups: females and their cubs, male "coalitions", and solitary males. While females lead a nomadic life searching for prey in large home ranges, males are more sedentary and instead establish much smaller territories in areas with plentiful prey and access to females. The cheetah is active during the day, with peaks during dawn and dusk. It feeds on small- to medium-sized prey, mostly weighing under 40 kg (88 lb), and prefers medium-sized ungulates such as impala, springbok and Thomson\'s gazelles. The cheetah typically stalks its prey within 60–100 m (200–330 ft) before charging towards it, trips it during the chase and bites its throat to suffocate it to death. It breeds throughout the year. After a gestation of nearly three months, females give birth to a litter of three or four cubs. Cheetah cubs are highly vulnerable to predation by other large carnivores. They are weaned at around four months and are independent by around 20 months of age.\nThe cheetah is threatened by habitat loss, conflict with humans, poaching and high susceptibility to diseases. In 2016, the global cheetah population was estimated at 7,100 individuals in the wild; it is listed as Vulnerable on the IUCN Red List. It has been widely depicted in art, literature, advertising, and animation. It was tamed in ancient Egypt and trained for hunting ungulates in the Arabian Peninsula and India. It has been kept in zoos since the early 19th century.', 'source': 'https://en.wikipedia.org/wiki/Cheetah'}
print(result["answer"])
# Cheetahs are capable of running at speeds between 93 to 104 km/h (58 to 65 mph).函数调用
如果你选择的 LLM 实现了工具调用功能，则可以用它让模型指定在生成答案时引用提供的文档。
LangChain 工具调用模型实现了一种 .with_structured_output 方法，该方法可以让生成结果强制遵循指定的模式。
引用文档
要使用标识符引用文档，我们将标识符格式化为提示，然后使用 .with_structed_output 强制 LLM 在其输出中引用这些标识符。
首先，我们定义输出的模式，.with_structed_output 支持多种格式，包括 JSON 模式和 Pydantic。
这里我们将使用 Pydantic：
from langchain_core.pydantic_v1 import BaseModel, Field
class CitedAnswer(BaseModel):
"""Answer the user question based only on the given sources, and cite the sources used."""
answer: str = Field(
...,
description="The answer to the user question, which is based only on the given sources.",
)
citations: List[int] = Field(
...,
description="The integer IDs of the SPECIFIC sources which justify the answer.",
)让我们看看当我们传入函数和用户输入时模型输出是什么样的：
structured_llm = llm.with_structured_output(CitedAnswer)
example_q = """What Brian's height?
Source: 1
Information: Suzy is 6'2"
Source: 2
Information: Jeremiah is blonde
Source: 3
Information: Brian is 3 inches shorter than Suzy"""
result = structured_llm.invoke(example_q)
result.dict(){'answer': 'Brian\'s height is 5\'11".', 'citations': [1, 3]}现在，我们要将源标识符构建到提示词中：
- 更新提示词以包含源标识符；
- 使用
structured_llm； - 删除
StrOutputParser，以保留输出中的 Pydantic 对象。
def format_docs_with_id(docs: List[Document]) -> str:
formatted = [
f"Source ID: {i}\nArticle Title: {doc.metadata['title']}\nArticle Snippet: {doc.page_content}"
for i, doc in enumerate(docs)
]
return "\n\n" + "\n\n".join(formatted)
rag_chain_from_docs = (
RunnablePassthrough.assign(context=(lambda x: format_docs_with_id(x["context"])))
| prompt
| structured_llm
)
retrieve_docs = (lambda x: x["input"]) | retriever
chain = RunnablePassthrough.assign(context=retrieve_docs).assign(
answer=rag_chain_from_docs
)print(result["answer"])
# answer='Cheetahs can run at speeds of 93 to 104 km/h (58 to 65 mph). They are known as the fastest land animals.' citations=[0]
print(result["context"][0])
# page_content='The cheetah (Acinonyx jubatus) is a large cat and the fastest land animal. It has a tawny to creamy white or pale buff fur that is marked with evenly spaced, solid black spots. The head is small and rounded, with a short snout and black tear-like facial streaks. It reaches 67–94 cm (26–37 in) at the shoulder, and the head-and-body length is between 1.1 and 1.5 m (3 ft 7 in and 4 ft 11 in). Adults weigh between 21 and 72 kg (46 and 159 lb). The cheetah is capable of running at 93 to 104 km/h (58 to 65 mph); it has evolved specialized adaptations for speed, including a light build, long thin legs and a long tail.\nThe cheetah was first described in the late 18th century. Four subspecies are recognised today that are native to Africa and central Iran. An African subspecies was introduced to India in 2022. It is now distributed mainly in small, fragmented populations in northwestern, eastern and southern Africa and central Iran. It lives in a variety of habitats such as savannahs in the Serengeti, arid mountain ranges in the Sahara, and hilly desert terrain.\nThe cheetah lives in three main social groups: females and their cubs, male "coalitions", and solitary males. While females lead a nomadic life searching for prey in large home ranges, males are more sedentary and instead establish much smaller territories in areas with plentiful prey and access to females. The cheetah is active during the day, with peaks during dawn and dusk. It feeds on small- to medium-sized prey, mostly weighing under 40 kg (88 lb), and prefers medium-sized ungulates such as impala, springbok and Thomson\'s gazelles. The cheetah typically stalks its prey within 60–100 m (200–330 ft) before charging towards it, trips it during the chase and bites its throat to suffocate it to death. It breeds throughout the year. After a gestation of nearly three months, females give birth to a litter of three or four cubs. Cheetah cubs are highly vulnerable to predation by other large carnivores. They are weaned a' metadata={'title': 'Cheetah', 'summary': 'The cheetah (Acinonyx jubatus) is a large cat and the fastest land animal. It has a tawny to creamy white or pale buff fur that is marked with evenly spaced, solid black spots. The head is small and rounded, with a short snout and black tear-like facial streaks. It reaches 67–94 cm (26–37 in) at the shoulder, and the head-and-body length is between 1.1 and 1.5 m (3 ft 7 in and 4 ft 11 in). Adults weigh between 21 and 72 kg (46 and 159 lb). The cheetah is capable of running at 93 to 104 km/h (58 to 65 mph); it has evolved specialized adaptations for speed, including a light build, long thin legs and a long tail.\nThe cheetah was first described in the late 18th century. Four subspecies are recognised today that are native to Africa and central Iran. An African subspecies was introduced to India in 2022. It is now distributed mainly in small, fragmented populations in northwestern, eastern and southern Africa and central Iran. It lives in a variety of habitats such as savannahs in the Serengeti, arid mountain ranges in the Sahara, and hilly desert terrain.\nThe cheetah lives in three main social groups: females and their cubs, male "coalitions", and solitary males. While females lead a nomadic life searching for prey in large home ranges, males are more sedentary and instead establish much smaller territories in areas with plentiful prey and access to females. The cheetah is active during the day, with peaks during dawn and dusk. It feeds on small- to medium-sized prey, mostly weighing under 40 kg (88 lb), and prefers medium-sized ungulates such as impala, springbok and Thomson\'s gazelles. The cheetah typically stalks its prey within 60–100 m (200–330 ft) before charging towards it, trips it during the chase and bites its throat to suffocate it to death. It breeds throughout the year. After a gestation of nearly three months, females give birth to a litter of three or four cubs. Cheetah cubs are highly vulnerable to predation by other large carnivores. They are weaned at around four months and are independent by around 20 months of age.\nThe cheetah is threatened by habitat loss, conflict with humans, poaching and high susceptibility to diseases. In 2016, the global cheetah population was estimated at 7,100 individuals in the wild; it is listed as Vulnerable on the IUCN Red List. It has been widely depicted in art, literature, advertising, and animation. It was tamed in ancient Egypt and trained for hunting ungulates in the Arabian Peninsula and India. It has been kept in zoos since the early 19th century.', 'source': 'https://en.wikipedia.org/wiki/Cheetah'}引用片段
要返回文本范围（也许除了源标识符之外），我们可以使用相同的方法。唯一的变化是构建一个更复杂的输出模式，这里使用 Pydantic，其中包括一个“引用”和一个源标识符。
class Citation(BaseModel):
source_id: int = Field(
...,
description="The integer ID of a SPECIFIC source which justifies the answer.",
)
quote: str = Field(
...,
description="The VERBATIM quote from the specified source that justifies the answer.",
)
class QuotedAnswer(BaseModel):
"""Answer the user question based only on the given sources, and cite the sources used."""
answer: str = Field(
...,
description="The answer to the user question, which is based only on the given sources.",
)
citations: List[Citation] = Field(
..., description="Citations from the given sources that justify the answer."
)
rag_chain_from_docs = (
RunnablePassthrough.assign(context=(lambda x: format_docs_with_id(x["context"])))
| prompt
| llm.with_structured_output(QuotedAnswer)
)
retrieve_docs = (lambda x: x["input"]) | retriever
chain = RunnablePassthrough.assign(context=retrieve_docs).assign(
answer=rag_chain_from_docs
)
result = chain.invoke({"input": "How fast are cheetahs?"})在这里我们看到模型从源 0 中提取了相关的文本片段：
result["answer"]
# QuotedAnswer(answer='Cheetahs can run at speeds of 93 to 104 km/h (58 to 65 mph).', citations=[Citation(source_id=0, quote='The cheetah is capable of running at 93 to 104 km/h (58 to 65 mph); it has evolved specialized adaptations for speed, including a light build, long thin legs and a long tail.')])直接使用提示词
许多模型不支持函数调用。我们可以通过直接提示词获得类似的结果。让我们尝试指示模型为其输出生成结构化 XML：
xml_system = """You're a helpful AI assistant. Given a user question and some Wikipedia article snippets, \
answer the user question and provide citations. If none of the articles answer the question, just say you don't know.
Remember, you must return both an answer and citations. A citation consists of a VERBATIM quote that \
justifies the answer and the ID of the quote article. Return a citation for every quote across all articles \
that justify the answer. Use the following format for your final output:
<cited_answer>
<answer></answer>
<citations>
<citation><source_id></source_id><quote></quote></citation>
<citation><source_id></source_id><quote></quote></citation>
...
</citations>
</cited_answer>
Here are the Wikipedia articles:{context}"""
xml_prompt = ChatPromptTemplate.from_messages(
[("system", xml_system), ("human", "{input}")]
)现在对我们的链进行类似的小更新：
- 更新格式化函数以将检索到的上下文包装在 XML 标签中；
- 不使用
.with_structed_output； - 使用 XMLOutputParser 代替 StrOutputParser 将答案解析为字典。
from langchain_core.output_parsers import XMLOutputParser
def format_docs_xml(docs: List[Document]) -> str:
formatted = []
for i, doc in enumerate(docs):
doc_str = f"""\
<source id=\"{i}\">
<title>{doc.metadata['title']}</title>
<article_snippet>{doc.page_content}</article_snippet>
</source>"""
formatted.append(doc_str)
return "\n\n<sources>" + "\n".join(formatted) + "</sources>"
rag_chain_from_docs = (
RunnablePassthrough.assign(context=(lambda x: format_docs_xml(x["context"])))
| xml_prompt
| llm
| XMLOutputParser()
)
retrieve_docs = (lambda x: x["input"]) | retriever
chain = RunnablePassthrough.assign(context=retrieve_docs).assign(
answer=rag_chain_from_docs
)
result = chain.invoke({"input": "How fast are cheetahs?"})引用再次被组织到答案中：
result["answer"]
"""
{'cited_answer': [{'answer': 'Cheetahs are capable of running at 93 to 104 km/h (58 to 65 mph).'},
{'citations': [{'citation': [{'source_id': '0'},
{'quote': 'The cheetah is capable of running at 93 to 104 km/h (58 to 65 mph); it has evolved specialized adaptations for speed, including a light build, long thin legs and a long tail.'}]}]}]}
"""检索后处理
另一种方法是对检索到的文档进行后处理以压缩内容，以便源内容已经足够小，我们不需要模型来引用特定的源或跨度。
例如，我们可以将每个文档分解为一两个句子，嵌入它们并仅保留最相关的句子。
LangChain 为此内置了一些组件。在这里，我们将使用 RecursiveCharacterTextSplitter，它通过分割分隔符子字符串来创建分隔大小的块，以及 EmbeddingsFilter，它仅保留具有最相关嵌入的文本。
这种方法有效地将我们的原始检索器替换为压缩文档的更新检索器。
首先，我们构建检索器：
from langchain.retrievers.document_compressors import EmbeddingsFilter
from langchain_core.runnables import RunnableParallel
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
splitter = RecursiveCharacterTextSplitter(
chunk_size=400,
chunk_overlap=0,
separators=["\n\n", "\n", ".", " "],
keep_separator=False,
)
compressor = EmbeddingsFilter(embeddings=OpenAIEmbeddings(), k=10)
def split_and_filter(input) -> List[Document]:
docs = input["docs"]
question = input["question"]
split_docs = splitter.split_documents(docs)
stateful_docs = compressor.compress_documents(split_docs, question)
return [stateful_doc for stateful_doc in stateful_docs]
new_retriever = (
RunnableParallel(question=RunnablePassthrough(), docs=retriever) | split_and_filter
)
docs = new_retriever.invoke("How fast are cheetahs?")接下来，我们像以前一样将其组装到我们的链中：
rag_chain_from_docs = (
RunnablePassthrough.assign(context=(lambda x: format_docs(x["context"])))
| prompt
| llm
| StrOutputParser()
)
chain = RunnablePassthrough.assign(
context=(lambda x: x["input"]) | new_retriever
).assign(answer=rag_chain_from_docs)
result = chain.invoke({"input": "How fast are cheetahs?"})
print(result["answer"])
# Cheetahs are capable of running at speeds between 93 to 104 km/h (58 to 65 mph), making them the fastest land animals.请注意，尽管文档对象在其元数据中的“摘要”键中保留了原始内容，但文档内容现在已被压缩。这些摘要不会传递给模型；只有浓缩的内容。
result["context"][0].page_content # passed to model
# 'Adults weigh between 21 and 72 kg (46 and 159 lb). The cheetah is capable of running at 93 to 104 km/h (58 to 65 mph); it has evolved specialized adaptations for speed, including a light build, long thin legs and a long tail'
result["context"][0].metadata["summary"] # original document
# 'The cheetah (Acinonyx jubatus) is a large cat and the fastest land animal. It has a tawny to creamy white or pale buff fur that is marked with evenly spaced, solid black spots. The head is small and rounded, with a short snout and black tear-like facial streaks. It reaches 67–94 cm (26–37 in) at the shoulder, and the head-and-body length is between 1.1 and 1.5 m (3 ft 7 in and 4 ft 11 in). Adults weigh between 21 and 72 kg (46 and 159 lb). The cheetah is capable of running at 93 to 104 km/h (58 to 65 mph); it has evolved specialized adaptations for speed, including a light build, long thin legs and a long tail.\nThe cheetah was first described in the late 18th century. Four subspecies are recognised today that are native to Africa and central Iran. An African subspecies was introduced to India in 2022. It is now distributed mainly in small, fragmented populations in northwestern, eastern and southern Africa and central Iran. It lives in a variety of habitats such as savannahs in the Serengeti, arid mountain ranges in the Sahara, and hilly desert terrain.\nThe cheetah lives in three main social groups: females and their cubs, male "coalitions", and solitary males. While females lead a nomadic life searching for prey in large home ranges, males are more sedentary and instead establish much smaller territories in areas with plentiful prey and access to females. The cheetah is active during the day, with peaks during dawn and dusk. It feeds on small- to medium-sized prey, mostly weighing under 40 kg (88 lb), and prefers medium-sized ungulates such as impala, springbok and Thomson\'s gazelles. The cheetah typically stalks its prey within 60–100 m (200–330 ft) before charging towards it, trips it during the chase and bites its throat to suffocate it to death. It breeds throughout the year. After a gestation of nearly three months, females give birth to a litter of three or four cubs. Cheetah cubs are highly vulnerable to predation by other large carnivores. They are weaned at around four months and are independent by around 20 months of age.\nThe cheetah is threatened by habitat loss, conflict with humans, poaching and high susceptibility to diseases. In 2016, the global cheetah population was estimated at 7,100 individuals in the wild; it is listed as Vulnerable on the IUCN Red List. It has been widely depicted in art, literature, advertising, and animation. It was tamed in ancient Egypt and trained for hunting ungulates in the Arabian Peninsula and India. It has been kept in zoos since the early 19th century.'生成后处理
另一种方法是对模型生成进行后处理。在此示例中，我们将首先生成一个答案，然后要求模型用引用来注释它自己的答案。这种方法的缺点当然是速度较慢且成本较高，因为需要进行两次模型调用。
class Citation(BaseModel):
source_id: int = Field(
...,
description="The integer ID of a SPECIFIC source which justifies the answer.",
)
quote: str = Field(
...,
description="The VERBATIM quote from the specified source that justifies the answer.",
)
class AnnotatedAnswer(BaseModel):
"""Annotate the answer to the user question with quote citations that justify the answer."""
citations: List[Citation] = Field(
..., description="Citations from the given sources that justify the answer."
)
structured_llm = llm.with_structured_output(AnnotatedAnswer)
from langchain_core.prompts import MessagesPlaceholder
prompt = ChatPromptTemplate.from_messages(
[
("system", system_prompt),
("human", "{question}"),
MessagesPlaceholder("chat_history", optional=True),
]
)
answer = prompt | llm
annotation_chain = prompt | structured_llm
chain = (
RunnableParallel(
question=RunnablePassthrough(), docs=(lambda x: x["input"]) | retriever
)
.assign(context=format)
.assign(ai_message=answer)
.assign(
chat_history=(lambda x: [x["ai_message"]]),
answer=(lambda x: x["ai_message"].content),
)
.assign(annotations=annotation_chain)
.pick(["answer", "docs", "annotations"])
)
result = chain.invoke({"input": "How fast are cheetahs?"})print(result["answer"])
# Cheetahs are capable of running at speeds between 93 to 104 km/h (58 to 65 mph). Their specialized adaptations for speed, such as a light build, long thin legs, and a long tail, allow them to be the fastest land animals.
result["annotations"]
# AnnotatedAnswer(citations=[Citation(source_id=0, quote='The cheetah is capable of running at 93 to 104 km/h (58 to 65 mph); it has evolved specialized adaptations for speed, including a light build, long thin legs and a long tail.')])
