Update app.py

app.py

@@ -1,5 +1,5 @@
 import streamlit as st
-from langchain_community.llms import HuggingFaceHub
+from langchain_huggingface import HuggingFaceEndpoint
 from langchain_community.embeddings import SentenceTransformerEmbeddings
 from langchain_community.vectorstores import FAISS
 
@@ -24,7 +24,7 @@ except Exception as e:
 def answer_question(gemma, temperature, max_length, question):
     # 4. 初始化 Gemma 模型
     try:
-        llm = HuggingFaceHub(repo_id=gemma, model_kwargs={"temperature": temperature, "max_length": max_length})
+        llm = HuggingFaceEndpoint(repo_id=gemma, model_kwargs={"temperature": temperature, "max_length": max_length})
     except Exception as e:
         st.error(f"Gemma 模型加载失败：{e}")
         st.stop()
@@ -33,7 +33,7 @@ def answer_question(gemma, temperature, max_length, question):
     try:
         question_embedding = embeddings.embed_query(question)
         question_embedding_str = " ".join(map(str, question_embedding))
-        print('question_embedding: ' + question_embedding_str)
+        # print('question_embedding: ' + question_embedding_str)
         docs_and_scores = db.similarity_search_with_score(question_embedding_str)
 
         context = "\n".join([doc.page_content for doc, _ in docs_and_scores])
@@ -48,12 +48,12 @@ def answer_question(gemma, temperature, max_length, question):
         st.error(f"问答过程出错：{e}")
         return "An error occurred during the answering process."
 
-# 5. Streamlit 界面
+# 6. Streamlit 界面
 st.title("Gemma 知识库问答系统")
 
-gemma = st.selectbox("模型", ("google/gemma-2-9b-it", "google/gemma-2-2b-it", "google/recurrentgemma-2b-it"), 2)
-temperature = st.text_input("temperature", "1.0")
-max_length = st.text_input("max_length", "1024")
+gemma = st.selectbox("repo-id", ("google/gemma-2-9b-it", "google/gemma-2-2b-it", "google/recurrentgemma-2b-it"), 2)
+temperature = st.number_input("temperature", value=1.0)
+max_length = st.number_input("max_length", value=1024)
 question = st.text_area("请输入问题", "Gemma 有哪些特点？")
 
 if st.button("提交"):