Update app.py

app.py

@@ -1,19 +1,12 @@
 import streamlit as st
 from langchain_community.llms import HuggingFaceHub
 from langchain_community.embeddings import SentenceTransformerEmbeddings
-from langchain.vectorstores import FAISS
+from langchain_community.vectorstores import FAISS
 import numpy as np
 
 # gemma = 'google/gemma-7b-it';
 gemma = 'google/recurrentgemma-2b-it';
 
-# 1. 初始化 Gemma 模型
-try:
-    llm = HuggingFaceHub(repo_id=gemma, model_kwargs={"temperature": 0.5, "max_length": 512})
-except Exception as e:
-    st.error(f"Gemma 模型加载失败：{e}")
-    st.stop()
-
 # 2. 准备知识库数据 (示例)
 knowledge_base = [
     "Gemma 是 Google 开发的大型语言模型。",
@@ -32,7 +25,13 @@ except Exception as e:
     st.stop()
 
 # 4. 问答函数
-def answer_question(question):
+def answer_question(gemma, temperature, max_length, question):
+    # 1. 初始化 Gemma 模型
+    try:
+        llm = HuggingFaceHub(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()
     try:
         question_embedding = embeddings.embed_query(question)
         question_embedding_np = " ".join(map(str, question_embedding))
@@ -53,13 +52,16 @@ def answer_question(question):
 # 5. Streamlit 界面
 st.title("Gemma 知识库问答系统")
 
-question = st.text_area("请输入问题", height=100)
+gemma = st.text_area("模型", "google/gemma-7b-it", height=50)
+temperature = st.text_area("temperature", "1.0", height=50)
+max_length = st.text_area("max_length", "1024", height=50)
+question = st.text_area("请输入问题", "Gemma 有哪些特点？", height=100)
 
 if st.button("提交"):
     if not question:
         st.warning("请输入问题！")
     else:
         with st.spinner("正在查询..."):
-            answer = answer_question(question)
+            answer = answer_question(gemma, temperature, max_length, question)
             st.write("答案：")
             st.write(answer)