Spaces:
Running
Running
File size: 3,275 Bytes
384400d 66ce1a8 384400d 9165ea9 384400d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 |
import streamlit as st
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
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.eyJqdGkiOiI1MDE5NTQyOSIsInJvbCI6IlJPTEVfUkVHSVNURVIiLCJpc3MiOiJPcGVuWExhYiIsImlhdCI6MTczMDIxOTcxMSwiY2xpZW50SWQiOiJlYm1ydm9kNnlvMG5semFlazF5cCIsInBob25lIjoiMTU3NzExODg5NjciLCJ1dWlkIjoiOWM5ZDNkZWQtNDI3ZS00Nzk0LWFlMjYtYjQ5YTQ1Yjk5MDk0IiwiZW1haWwiOiIiLCJleHAiOjE3NDU3NzE3MTF9.Al9Sff9zh5KdUkjqtHyeqSWH0F_kVaV9C-TJJLzhc4LAtt_wULDpBYBnjjrIIjfQNJj3fvr-YnAFKq3d-NCBqg"
# 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")
# 初始化模型
@st.cache_resource
def init_models():
embed_model = HuggingFaceEmbedding(
model_name="model/paraphrase-multilingual-MiniLM-L12-v2"
)
Settings.embed_model = embed_model
#用初始化llm
Settings.llm = llm
documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
return query_engine
# 检查是否需要初始化模型
if 'query_engine' not in st.session_state:
st.session_state['query_engine'] = init_models()
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？"}]
# Display or clear chat messages
for message in st.session_state.messages:
with st.chat_message(message["role"]):
st.write(message["content"])
def clear_chat_history():
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.sidebar.button('Clear Chat History', on_click=clear_chat_history)
# Function for generating LLaMA2 response
def generate_llama_index_response(prompt_input):
return greet2(prompt_input)
# User-provided prompt
if prompt := st.chat_input():
st.session_state.messages.append({"role": "user", "content": prompt})
with st.chat_message("user"):
st.write(prompt)
# Gegenerate_llama_index_response last message is not from assistant
if st.session_state.messages[-1]["role"] != "assistant":
with st.chat_message("assistant"):
with st.spinner("Thinking..."):
response = generate_llama_index_response(prompt)
placeholder = st.empty()
placeholder.markdown(response)
message = {"role": "assistant", "content": response}
st.session_state.messages.append(message) |