RAG：将检索到的整个文档注入到提示中，而不是仅注入 page_content

Question

当使用rag chain时，我意识到整个

Document

都被注入到提示符中。直接传递文档的

page_content

不是更有意义吗？我担心看到

[Document(page_content='

会以意想不到的方式影响结果。

from operator import itemgetter

from langchain_community.vectorstores import FAISS
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnableLambda, RunnablePassthrough
from langchain_openai import ChatOpenAI, OpenAIEmbeddings

vectorstore = FAISS.from_texts(
    ["harrison worked at kensho", "harrison worked for 3 years"], embedding=OpenAIEmbeddings()
)
retriever = vectorstore.as_retriever()

template = """Answer the question based only on the following context:
{context}

Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)

model = ChatOpenAI()

chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | prompt
)

chain.invoke("where did harrison work?")

ChatPromptValue(messages=[HumanMessage(content="Answer the question based only on the following context:\n[Document(page_content='harrison worked for 3 years'), Document(page_content='harrison worked at kensho')]\n\nQuestion: where did harrison work?\n")])

Answer 1

为了解决这个问题，我使用内置的 Jinja 2 模板渲染：

prompt = ChatPromptTemplate.from_template(template, template_format="jinja2")

然后在提示模板中：

CONTEXT: {% for doc in context %}
             {{ doc.page_content }}
         {% endfor %}

USER: {{ question }}