Update app_utils.py

app_utils.py

@@ -13,6 +13,7 @@ from langchain.chains import RetrievalQA #  RetrievalQA is a class in the langch
 from langchain.vectorstores import Chroma # Chroma is a class in the langchain.vectorstores module that can be used to store vectors.
 from langchain.document_loaders import DirectoryLoader #       
 from langchain.embeddings.openai import OpenAIEmbeddings # OpenAIGPTEmbeddings
+from langchain.embeddings import HuggingFaceInstructEmbeddings
 from langchain.text_splitter import CharacterTextSplitter #     CharacterTextSplitter is a class in the langchain.text_splitter module that can be used to split text into chunks.
 #import streamlit as st
 from langchain.indexes import VectorstoreIndexCreator #导入向量存储索引创建器
@@ -75,9 +76,9 @@ def initialize_knowledge_base():
     #    embeddings.append(embedding)
     
     #vStore = np.concatenate(embeddings, axis=0)
-
-    openAI_embeddings = OpenAIEmbeddings()
-    vStore = Chroma.from_documents(doc_texts, openAI_embeddings) #Chroma是一个类，用于存储向量,from_documents是一个方法，用于从文档中创建向量存储器,openAI_embeddings是一个类，用于将文本转换为向量
+    embedding = HuggingFaceInstructEmbeddings()
+    #openAI_embeddings = OpenAIEmbeddings()
+    vStore = Chroma.from_documents(doc_texts, embedding) #Chroma是一个类，用于存储向量,from_documents是一个方法，用于从文档中创建向量存储器,openAI_embeddings是一个类，用于将文本转换为向量
 
     conv_model = RetrievalQA.from_chain_type(
         llm=OpenAI(model_name="gpt-3.5-turbo-16k"),