问题背景：

I've searched all over langchain documentation on their official website but I didn't find how to create a langchain doc from a str variable in python so I searched in their GitHub code and I found this :

在 langchain 的官方文档中，我并没有直接找到如何从 Python 中的字符串变量创建 langchain 文档的具体指导。所以，我在 GitHub 代码库中找到了相关的线索。

 doc=Document(page_content="text",metadata={"source": "local"})

PS: I added the metadata attribute
then I tried using that doc with my chain:
Memory and Chain:

PS: 我添加了元数据属性
然后我尝试使用那个文档与我的链进行交互：
内存和链：

memory = ConversationBufferMemory(memory_key="chat_history", input_key="human_input")
chain = load_qa_chain(llm, chain_type="stuff", memory=memory, prompt=prompt
)

the call method:

  chain({"input_documents": doc, "human_input": query})

prompt template:        提示模板

template = """You are a senior financial analyst analyzing the below document and having a conversation with a human.
{context}
{chat_history}
Human: {human_input}
senior financial analyst:"""prompt = PromptTemplate(input_variables=["chat_history", "human_input", "context"], template=template
)

but I am getting the following error:        但我遇到了以下错误：

AttributeError: 'tuple' object has no attribute 'page_content'

when I tried to check the type and the page content of the Document object before using it with the chain I got this

当我试图在使用链之前检查Document对象的类型和页面内容时，我得到了这个

print(type(doc))
<class 'langchain.schema.Document'>
print(doc.page_content)
"text"

问题解决：

This worked for me:        我使用这种方法有效果

from langchain.docstore.document import Documentdoc =  Document(page_content="text", metadata={"source": "local"})