使用 Langchain+Openai 导入word做本地知识库
"""使用pdf文件读取不全"""
#加载数据
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
#from langchain.embeddings.openai import OpenAIEmbeddings
from langchain_openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
import os
from langchain.chat_models import ChatOpenAI
from langchain.schema import (
SystemMessage,
HumanMessage,
AIMessage
)
from docx import Document as DocxDocument
from langchain.docstore.document import Document
#原始query与检索得到的文本组合起来输入到语言模型,得到最终的回答
def augment_prompt(query: str):
# 获取top3的文本片段
results = vectorstore.similarity_search(query, k=3)
source_knowledge = "\