Question

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 :

  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:

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

电话方法:

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

即时模板:

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:

AttributeError:  tuple  object has no attribute  page_content

当我试图在使用文件链条之前检查文件物体的类型和页数时,我就这样做。

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

Answer 1

我也有一个类似的问题,我注意到APIC申请名单,因此试图这样做。

    doc = Document(page_content=input,
            metatdata={
                "source": "userinput"
            }
        )
    #db.add_documents(doc)
    db.add_documents([doc])

Answer 2

这为我工作:

from langchain.docstore.document import Document

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

Answer 3

首先,有些情况。从我迄今学到的内容来看,文件是Document 反对清单。如您操作type(doc[0]),请上langchain.schema.document.。 http://www.un.org/Depts/DGACM/index_french.htm www.un.org/Depts/DGACM/index_french.htm 顺便提一下(登机引述我的话):这是审判和错误的许多内容,正如你提到的那样,没有文件),是“先发”的<代码。包含上述两项关键内容,并在其<代码>metadata:中包含一个关键词:{source:},但仅接受方言。可通过创建<条码>>><>>>>>>>> > > 代码创建多个“网页”文件标。类似物体:

首先,您必须有一个图表清单:text_list,以及一份元数据词表:text_list。 <>你必须确保两份名单的长度相同。

from langchain.docstore.document import Document

document =  []

for item in range(len(text_string)):
    page = Document(page_content=doc_text_splits[item],
    metadata = metadata_string[item])
    doc.append(page)

此外,还可使用从LangChain分离的任何物体创建Document:

from langchain.text_splitter import CharacterTextSplitter

doc_creator = CharacterTextSplitter(parameters)

document = doc_creator.create_documents(texts = text_list, metadatas = metadata_list)

Answer 4

参看以下法典,

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

Answer 5

这是我能够取得的最佳结果。

def str_to_doc(text,name):
   folder_name =  docs 
   if not os.path.exists(folder_name):
       os.makedirs(folder_name)
   file_name = name+ .txt 
   path = os.path.join(folder_name, file_name)
   with open(path, "w") as file:
        file.write(text)
   loader = TextLoader(path)
   return loader.load()

友情链接