Update app.py

app.py

@@ -1,5 +1,5 @@
 import streamlit as st
-from langchain_huggingface import HuggingFaceEndpoint
+from langchain_community.llms import HuggingFaceHub
 from langchain_community.embeddings import SentenceTransformerEmbeddings
 from langchain_community.vectorstores import FAISS
 
@@ -24,12 +24,7 @@ except Exception as e:
 def answer_question(repo_id, temperature, max_length, question):
     # 4. 初始化 Gemma 模型
     try:
-        llm = HuggingFaceEndpoint(
-            repo_id=repo_id, 
-            temperature=temperature, 
-            max_length=max_length,
-            huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN
-        )
+        llm = HuggingFaceHub(repo_id=repo_id, 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()
@@ -47,7 +42,7 @@ def answer_question(repo_id, temperature, max_length, question):
         prompt = f"请根据以下知识库回答问题：\n{context}\n问题：{question}"
         print('prompt: ' + prompt)
 
-        answer = llm.invoke(prompt)
+        answer = llm(prompt)
         return answer
     except Exception as e:
         st.error(f"问答过程出错：{e}")
@@ -56,7 +51,7 @@ def answer_question(repo_id, temperature, max_length, question):
 # 6. Streamlit 界面
 st.title("Gemma 知识库问答系统")
 
-gemma = st.selectbox("repo-id", ("google/gemma-7b-it", "google/gemma-2b-it", "google/recurrentgemma-2b-it"), 2)
+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？")