分类目录：《大模型从入门到应用》总目录
本文介绍如何使用LangChain在文档列表上进行问答。它涵盖了四种不同的链式类型：
stuffmap_reducerefinemap_rerank
首先，我们需要准备数据，我们对一个向量数据库进行相似性搜索，这些文档可以以任何方式获取，我们需要重点关注在获取文档后的步骤：
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.docstore.document import Document
from langchain.prompts import PromptTemplate
from langchain.indexes.vectorstore import VectorstoreIndexCreator
with open("../../state_of_the_union.txt") as f:
state_of_the_union = f.read()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_text(state_of_the_union)
embeddings = OpenAIEmbeddings()
docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{"source": str(i)} for i in range(len(texts))]).as_retriever()
日志输出：
Running Chroma using direct local API.
Using DuckDB in-memory for database. Data will be transient.
输入：
query = "What did the president say about Justice Breyer"
docs = docsearch.get_relevant_documents(query)
from langchain.chains.question_answering import load_qa_chain
from langchain.llms import OpenAI
chain = load_qa_chain(OpenAI(temperature=0), chain_type="stuff")
query = "What did the president say about Justice Breyer"
chain.run(input_documents=docs, question=query)
输出：
' The president said that Justice Breyer has dedicated his life to serve the country and thanked him for his service.'
stuff类型的链
本节展示了使用stuff类型的链进行问答的结果：
chain = load_qa_chain(OpenAI(temperature=0), chain_type="stuff")
query = "What did the president say about Justice Breyer"
chain({"input_documents": docs, "question": query}, return_only_outputs=True)
输出：
{'output_text': ' The president said that Justice Breyer has dedicated his life to serve the country and thanked him for his service.'}
自定义提示
我们可以在stuff类型的链中使用自定义提示，在下面的示例中，我们将用意大利语回答：
prompt_template = """Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.
{context}
Question: {question}
Answer in Italian:"""
PROMPT = PromptTemplate(
template=prompt_template, input_variables=["context", "question"]
)
chain = load_qa_chain(OpenAI(temperature=0), chain_type="stuff", prompt=PROMPT)
chain({"input_documents": docs, "question": query}, return_only_outputs=True)
输出：
{'output_text': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese e ha ricevuto una vasta gamma di supporto.'}
map_reduce类型的链
本部分展示了使用map_reduce链进行问答的结果。
chain = load_qa_chain(OpenAI(temperature=0), chain_type="map_reduce")
query = "What did the president say about Justice Breyer"
chain({"input_documents": docs, "question": query}, return_only_outputs=True)
输出：
{'output_text': ' The president said that Justice Breyer is an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court, and thanked him for his service.'}
中间步骤
我们还可以返回map_reduce链的中间步骤，以供检查。这可以通过设置return_map_steps变量来实现。
chain = load_qa_chain(OpenAI(temperature=0), chain_type="map_reduce", return_map_steps=True)
chain({"input_documents": docs, "question": query}, return_only_outputs=True)
输出：
{'intermediate_steps': [' "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service."',
' A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.',
' None',
' None'],
'output_text': ' The president said that Justice Breyer is an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court, and thanked him for his service.'}
自定义提示
我们可以在map_reduce类型的链中使用自定义提示。在下面的示例中，我们将用意大利语回答：
question_prompt_template = """Use the following portion of a long document to see if any of the text is relevant to answer the question.
Return any relevant text translated into italian.
{context}
Question: {question}
Relevant text, if any, in Italian:"""
QUESTION_PROMPT = PromptTemplate(
template=question_prompt_template, input_variables=["context", "question"]
)
combine_prompt_template = """Given the following extracted parts of a long document and a question, create a final answer italian.
If you don't know the answer, just say that you don't know. Don't try to make up an answer.
QUESTION: {question}
=========
{summaries}
=========
Answer in Italian:"""
COMBINE_PROMPT = PromptTemplate(
template=combine_prompt_template, input_variables=["summaries", "question"]
)
chain = load_qa_chain(OpenAI(temperature=0), chain_type="map_reduce", return_map_steps=True, question_prompt=QUESTION_PROMPT, combine_prompt=COMBINE_PROMPT)
chain({"input_documents": docs, "question": query}, return_only_outputs=True)
输出：
{'intermediate_steps': ["\nStasera vorrei onorare qualcuno che ha dedicato la sua vita a servire questo paese: il giustizia Stephen Breyer - un veterano dell'esercito, uno studioso costituzionale e un giustizia in uscita della Corte Suprema degli Stati Uniti. Giustizia Breyer, grazie per il tuo servizio.",
'\nNessun testo pertinente.',
' Non ha detto nulla riguardo a Justice Breyer.',
" Non c'è testo pertinente."],
'output_text': ' Non ha detto nulla riguardo a Justice Breyer.'}
批处理大小
在使用map_reduce类型的链时，要注意的一点是在映射步骤中使用的批处理大小。如果批处理大小过大，可能会导致速率限制错误。我们可以通过设置所使用的LLM的批处理大小来控制此参数。需要注意的是，这仅适用于具有此参数的LLM。以下是一个设置批处理大小的示例：
llm = OpenAI(batch_size=5, temperature=0)
refine类型的链
本节展示了使用refine类型的链进行问答的结果。
chain = load_qa_chain(OpenAI(temperature=0), chain_type="refine")
query = "What did the president say about Justice Breyer"
chain({"input_documents": docs, "question": query}, return_only_outputs=True)
输出：
{'output_text': '\n\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his support of the Equality Act and his commitment to protecting the rights of LGBTQ+ Americans. He also praised Justice Breyer for his role in helping to pass the Bipartisan Infrastructure Law, which he said would be the most sweeping investment to rebuild America in history and would help the country compete for the jobs of the 21st Century.'}
中间步骤
我们还可以返回refine类型的链的中间步骤，以供检查。这可以通过设置return_refine_steps变量来实现。
chain = load_qa_chain(OpenAI(temperature=0), chain_type="refine", return_refine_steps=True)
chain({"input_documents": docs, "question": query}, return_only_outputs=True)
输出：
{'intermediate_steps': ['\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country and his legacy of excellence.',
'\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice.',
'\n\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his support of the Equality Act and his commitment to protecting the rights of LGBTQ+ Americans.',
'\n\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his support of the Equality Act and his commitment to protecting the rights of LGBTQ+ Americans. He also praised Justice Breyer for his role in helping to pass the Bipartisan Infrastructure Law, which is the most sweeping investment to rebuild America in history.'],
'output_text': '\n\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his support of the Equality Act and his commitment to protecting the rights of LGBTQ+ Americans. He also praised Justice Breyer for his role in helping to pass the Bipartisan Infrastructure Law, which is the most sweeping investment to rebuild America in history.'}
自定义提示
我们还可以在refine类型的链中使用自定义提示。在下面的示例中，我们将用意大利语回答：
refine_prompt_template = (
"The original question is as follows: {question}\n"
"We have provided an existing answer: {existing_answer}\n"
"We have the opportunity to refine the existing answer"
"(only if needed) with some more context below.\n"
"------------\n"
"{context_str}\n"
"------------\n"
"Given the new context, refine the original answer to better "
"answer the question. "
"If the context isn't useful, return the original answer. Reply in Italian."
)
refine_prompt = PromptTemplate(
input_variables=["question", "existing_answer", "context_str"],
template=refine_prompt_template,
)
initial_qa_template = (
"Context information is below. \n"
"---------------------\n"
"{context_str}"
"\n---------------------\n"
"Given the context information and not prior knowledge, "
"answer the question: {question}\nYour answer should be in Italian.\n"
)
initial_qa_prompt = PromptTemplate(
input_variables=["context_str", "question"], template=initial_qa_template
)
chain = load_qa_chain(OpenAI(temperature=0), chain_type="refine", return_refine_steps=True,
question_prompt=initial_qa_prompt, refine_prompt=refine_prompt)
chain({"input_documents": docs, "question": query}, return_only_outputs=True)
输出：
{'intermediate_steps': ['\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha reso omaggio al suo servizio.',
"\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese, ha reso omaggio al suo servizio e ha sostenuto la nomina di una top litigatrice in pratica privata, un ex difensore pubblico federale e una famiglia di insegnanti e agenti di polizia delle scuole pubbliche. Ha anche sottolineato l'importanza di avanzare la libertà e la giustizia attraverso la sicurezza delle frontiere e la risoluzione del sistema di immigrazione.",
"\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese, ha reso omaggio al suo servizio e ha sostenuto la nomina di una top litigatrice in pratica privata, un ex difensore pubblico federale e una famiglia di insegnanti e agenti di polizia delle scuole pubbliche. Ha anche sottolineato l'importanza di avanzare la libertà e la giustizia attraverso la sicurezza delle frontiere, la risoluzione del sistema di immigrazione, la protezione degli americani LGBTQ+ e l'approvazione dell'Equality Act. Ha inoltre sottolineato l'importanza di lavorare insieme per sconfiggere l'epidemia di oppiacei.",
"\n\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese, ha reso omaggio al suo servizio e ha sostenuto la nomina di una top litigatrice in pratica privata, un ex difensore pubblico federale e una famiglia di insegnanti e agenti di polizia delle scuole pubbliche. Ha anche sottolineato l'importanza di avanzare la libertà e la giustizia attraverso la sicurezza delle frontiere, la risoluzione del sistema di immigrazione, la protezione degli americani LGBTQ+ e l'approvazione dell'Equality Act. Ha inoltre sottolineato l'importanza di lavorare insieme per sconfiggere l'epidemia di oppiacei e per investire in America, educare gli americani, far crescere la forza lavoro e costruire l'economia dal"],
'output_text': "\n\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese, ha reso omaggio al suo servizio e ha sostenuto la nomina di una top litigatrice in pratica privata, un ex difensore pubblico federale e una famiglia di insegnanti e agenti di polizia delle scuole pubbliche. Ha anche sottolineato l'importanza di avanzare la libertà e la giustizia attraverso la sicurezza delle frontiere, la risoluzione del sistema di immigrazione, la protezione degli americani LGBTQ+ e l'approvazione dell'Equality Act. Ha inoltre sottolineato l'importanza di lavorare insieme per sconfiggere l'epidemia di oppiacei e per investire in America, educare gli americani, far crescere la forza lavoro e costruire l'economia dal"}
map-rerank类型的链
本节展示了使用map-rerank类型的链进行带来源的问答的结果。
chain = load_qa_chain(OpenAI(temperature=0), chain_type="map_rerank", return_intermediate_steps=True)
query = "What did the president say about Justice Breyer"
results = chain({"input_documents": docs, "question": query}, return_only_outputs=True)
results["output_text"]
输出：
' The President thanked Justice Breyer for his service and honored him for dedicating his life to serve the country.'
输入：
results["intermediate_steps"]
输出：
[{'answer': ' The President thanked Justice Breyer for his service and honored him for dedicating his life to serve the country.',
'score': '100'},
{'answer': ' This document does not answer the question', 'score': '0'},
{'answer': ' This document does not answer the question', 'score': '0'},
{'answer': ' This document does not answer the question', 'score': '0'}]
自定义提示
我们可以在此map-rerank类型的链中使用自定义提示。在下面的示例中，我们将用意大利语回答：
from langchain.output_parsers import RegexParser
output_parser = RegexParser(
regex=r"(.*?)\nScore: (.*)",
output_keys=["answer", "score"],
)
prompt_template = """Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.
In addition to giving an answer, also return a score of how fully it answered the user's question. This should be in the following format:
Question: [question here]
Helpful Answer In Italian: [answer here]
Score: [score between 0 and 100]
Begin!
Context:
---------
{context}
---------
Question: {question}
Helpful Answer In Italian:"""
PROMPT = PromptTemplate(
template=prompt_template,
input_variables=["context", "question"],
output_parser=output_parser,
)
chain = load_qa_chain(OpenAI(temperature=0), chain_type="map_rerank", return_intermediate_steps=True, prompt=PROMPT)
query = "What did the president say about Justice Breyer"
chain({"input_documents": docs, "question": query}, return_only_outputs=True)
输出：
{'intermediate_steps': [{'answer': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese.',
'score': '100'},
{'answer': ' Il presidente non ha detto nulla sulla Giustizia Breyer.',
'score': '100'},
{'answer': ' Non so.', 'score': '0'},
{'answer': ' Non so.', 'score': '0'}],
'output_text': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese.'}
参考文献：
[1] LangChain官方网站：https://www.langchain.com/
[2] LangChain 🦜️🔗 中文网，跟着LangChain一起学LLM/GPT开发：https://www.langchain.com.cn/
[3] LangChain中文网 - LangChain 是一个用于开发由语言模型驱动的应用程序的框架：http://www.cnlangchain.com/
