Update app.py

app.py

@@ -1,7 +1,23 @@
 import streamlit as st
 from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-from llama_index.llms.huggingface import HuggingFaceLLM
+from llama_index.legacy.callbacks import CallbackManager
+from llama_index.llms.openai_like import OpenAILike
+
+# Create an instance of CallbackManager
+callback_manager = CallbackManager()
+
+api_base_url =  "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"
+model = "internlm2.5-latest"
+api_key = "eyJ0eXBlIjoiSldUIiwiYWxnIjoiSFM1MTIifQ.eyJqdGkiOiI1MDIxNzY4OSIsInJvbCI6IlJPTEVfUkVHSVNURVIiLCJpc3MiOiJPcGVuWExhYiIsImlhdCI6MTczMDM4MDY2MSwiY2xpZW50SWQiOiJlYm1ydm9kNnlvMG5semFlazF5cCIsInBob25lIjoiMTU3MjYzNjM5ODAiLCJ1dWlkIjoiZWFkYTY5ZDUtYjllNC00ZWM3LTk5OWUtZGY5OGQ0OGQwNjBiIiwiZW1haWwiOiIiLCJleHAiOjE3NDU5MzI2NjF9.hmpE8L-WDXmFMCnQag-rGMW1YDeU0cU9M2StKQBUKAsYUNxmodtOO_YbHoTyHBDRbRMx8rDooWCznebk9l6rWA"
+
+# api_base_url =  "https://api.siliconflow.cn/v1"
+# model = "internlm/internlm2_5-7b-chat"
+# api_key = "请填写 API Key"
+
+llm =OpenAILike(model=model, api_base=api_base_url, api_key=api_key, is_chat_model=True,callback_manager=callback_manager)
+
+
 
 st.set_page_config(page_title="llama_index_demo", page_icon="🦜🔗")
 st.title("llama_index_demo")
@@ -10,16 +26,11 @@ st.title("llama_index_demo")
 @st.cache_resource
 def init_models():
     embed_model = HuggingFaceEmbedding(
-        model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
+        model_name="/root/model/paraphrase-multilingual-MiniLM-L12-v2"
     )
     Settings.embed_model = embed_model
 
-    llm = HuggingFaceLLM(
-        model_name="internlm/internlm2_5-1_8b-chat",
-        tokenizer_name="internlm/internlm2_5-1_8b-chat",
-        model_kwargs={"trust_remote_code": True},
-        tokenizer_kwargs={"trust_remote_code": True}
-    )
+    #用初始化llm
     Settings.llm = llm
 
     documents = SimpleDirectoryReader("/root/llamaindex_demo/data").load_data()
@@ -36,10 +47,10 @@ def greet2(question):
     response = st.session_state['query_engine'].query(question)
     return response
 
-
+      
 # Store LLM generated responses
 if "messages" not in st.session_state.keys():
-    st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]
+    st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]    
 
     # Display or clear chat messages
 for message in st.session_state.messages: