如何解决AttributeError: 'bytes'对象无'page_content'属性问题

错误原因 #

Chroma.from_documents()要求传入LangChain Document对象的列表，但你的代码中直接将文件读取的bytes内容传入，bytes对象没有page_content属性，导致触发该错误。

修复步骤 #

1. 导入LangChain的Document类，用于包装文本内容
2. 修改文件读取函数，将bytes内容转成字符串，并封装为Document对象
3. 确保传入Chroma的是Document对象列表

修改后的完整代码 #

from langchain.prompts import ChatPromptTemplate
from langchain_community.chat_models import ChatOllama
from langchain.embeddings import SentenceTransformerEmbeddings
import streamlit as st 
from langchain.vectorstores import Chroma
from langchain_core.runnables import RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
# 新增导入Document类
from langchain_core.documents.base import Document


# Initialize the chat model
model_local = ChatOllama(model="mistral")

# 修改load_document函数，返回Document对象
def load_document(c_file):
    if c_file is not None:
        # 读取bytes并转成字符串，编码可根据实际C文件编码调整
        file_contents = c_file.read().decode("utf-8")
        # 封装为Document对象，page_content字段存储文本内容
        return Document(page_content=file_contents)
    else:
        return None

# Define function to generate response
def generate_response(query, document):
    if document:
        # 传入单个Document对象组成的列表
        documents = [document]
        embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
        vectorstore = Chroma.from_documents(documents, embeddings)
        retriever = vectorstore.as_retriever()

        after_rag_template = """Answer the question based only on the following context:
        {context}
        Question: {question}
        """
        after_rag_prompt = ChatPromptTemplate.from_template(after_rag_template)
        after_rag_chain = (
            {"context": retriever, "question": RunnablePassthrough()}
            | after_rag_prompt
            | model_local
            | StrOutputParser()
        )

        response = after_rag_chain.invoke(query)
        return response
    else:
        return "Please upload a C file."

# Define the Streamlit app
def main():
    st.set_page_config(page_title="Unit Test Case Generator",
                       layout="centered")
    #st.title("Unit Test Case Generator")
    
    # Sidebar for uploading C file
    st.sidebar.title("Upload C File")
    c_file = st.sidebar.file_uploader("Choose a C file", type=["c"])
    
    # Text box for entering query
    query = st.text_area("Enter your query:")
    
    # Submit button
    if st.button("Submit") and query:
        document = load_document(c_file)
        response = generate_response(query, document)
        
        st.subheader("Generated Output C File:")
        if response:
            st.code(response, language='c')
        else:
            st.warning("No response generated.")

if __name__ == "__main__":
    main()

关键修改说明 #

• 新增from langchain_core.documents.base import Document导入语句，引入LangChain标准的文档包装类
• 修改load_document函数：将文件读取的bytes数据转为字符串，再封装成Document对象，满足Chroma的输入要求
• 保持后续逻辑不变，因为现在传入的已经是符合要求的Document对象列表

内容的提问来源于stack exchange，提问作者Anjali Kumari