Update: v1

Dockerfile

@@ -1,16 +1,59 @@
 # Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
 # you will also find guides on how best to write your Dockerfile
 
-FROM python:3.9
+FROM python:3.10
 
+# Install git and git-lfs
+RUN apt-get update && apt-get install -y git git-lfs && rm -rf /var/lib/apt/lists/*
+
+# Create user and set working directory
 RUN useradd -m -u 1000 user
-USER user
+WORKDIR /home/user/app
+
+# Create necessary directories
+RUN mkdir -p /home/user/model /home/user/data
+
+# Set environment variables
+ENV HF_ENDPOINT=https://hf-mirror.com
 ENV PATH="/home/user/.local/bin:$PATH"
 
-WORKDIR /app
+# Install huggingface-cli first for downloading models
+RUN pip install --no-cache-dir huggingface-cli
+
+# Download sentence-transformer model
+RUN huggingface-cli download --resume-download sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 --local-dir /home/user/model/sentence-transformer
+
+# Download paraphrase-multilingual-MiniLM-L12-v2
+RUN cd /home/user/model && \
+    git clone https://www.modelscope.cn/Ceceliachenen/paraphrase-multilingual-MiniLM-L12-v2.git && \
+    cd /home/user/model/paraphrase-multilingual-MiniLM-L12-v2 && \
+    git lfs install && \
+    git lfs pull
 
-COPY --chown=user ./requirements.txt requirements.txt
-RUN pip install --no-cache-dir --upgrade -r requirements.txt
+# Download NLTK data
+RUN cd /home/user && \
+    git clone https://gitee.com/yzy0612/nltk_data.git --branch gh-pages && \
+    cd /home/user/nltk_data && \
+    mv /home/user/nltk_data/packages/* /home/user/nltk_data && \
+    cd /home/user/nltk_data/tokenizers && \
+    unzip punkt.zip && \
+    cd /home/user/nltk_data/taggers && \
+    unzip averaged_perceptron_tagger.zip
+
+# Download demo data
+RUN cd /home/user/data && \
+    git clone https://github.com/Kit-Hung/demos && \
+    cp /home/user/data/demos/k8s/1-deploy/3-k8s_install/2-kubeadm/kubeadm.md /home/user/data
+
+# Install Python dependencies
+COPY --chown=user requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application files
+COPY --chown=user . .
+
+# Switch to non-root user
+USER user
 
-COPY --chown=user . /app
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+# Run streamlit
+CMD ["streamlit", "run", "app.py"]

app.py

@@ -1,7 +1,79 @@
-from fastapi import FastAPI
+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
 
-app = FastAPI()
+# Create an instance of CallbackManager
+callback_manager = CallbackManager()
 
-@app.get("/")
-def greet_json():
-    return {"Hello": "World!"}
+api_base_url =  "https://api.siliconflow.cn/v1"
+model = "internlm/internlm2_5-7b-chat"
+api_key = st.secrets["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="ai_assistant_demo", page_icon="😄")
+st.title("AI Assistant Demo")
+
+# 初始化模型
+@st.cache_resource
+def init_models():
+    embed_model = HuggingFaceEmbedding(
+        model_name="/home/user/model/sentence-transformer"
+    )
+    Settings.embed_model = embed_model
+
+    #用初始化llm
+    Settings.llm = llm
+
+    documents = SimpleDirectoryReader("/home/user/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.response}
+    st.session_state.messages.append(message)

requirements.txt

@@ -1,2 +1,10 @@
-fastapi
-uvicorn[standard]
+einops==0.7.0
+protobuf==5.26.1
+llama-index==0.11.20
+llama-index-llms-replicate==0.3.0
+llama-index-llms-openai-like==0.2.0
+llama-index-embeddings-huggingface==0.3.1
+llama-index-embeddings-instructor==0.2.1
+torch==2.5.0 
+torchvision==0.20.0 
+torchaudio==2.5.0