add: app.py requirements.txt, update: README.md

README.md

@@ -11,3 +11,47 @@ license: apache-2.0
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+
+## Installation of dependencies
+### Sentence Transformer
+```Bash
+touch download_hf.py
+```
+
+download_hf.py
+```python
+import os
+
+# 设置环境变量
+os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'
+
+# 下载模型
+os.system('huggingface-cli download --resume-download sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 --local-dir /root/model/sentence-transformer')
+```
+
+download
+```shell
+python download_hf.py
+```
+
+
+### paraphrase-multilingual-MiniLM-L12-v2
+```shell
+mkdir /root/model
+git lfs install
+git clone https://www.modelscope.cn/Ceceliachenen/paraphrase-multilingual-MiniLM-L12-v2.git
+```
+
+
+### NLTK 
+```shell
+cd /root
+git clone https://gitee.com/yzy0612/nltk_data.git  --branch gh-pages
+cd nltk_data
+mv packages/*  ./
+cd tokenizers
+unzip punkt.zip
+cd ../taggers
+unzip averaged_perceptron_tagger.zip
+```

app.py

@@ -0,0 +1,83 @@
+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 = "api_key"
+
+# api_base_url =  "https://api.siliconflow.cn/v1"
+# model = "internlm/internlm2_5-7b-chat"
+# api_key = "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="/root/model/paraphrase-multilingual-MiniLM-L12-v2"
+    )
+    Settings.embed_model = embed_model
+
+    #用初始化llm
+    Settings.llm = llm
+
+    documents = SimpleDirectoryReader("/root/llamaindex_demo/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)

requirements.txt

@@ -0,0 +1,140 @@
+accelerate==1.1.1
+aiohappyeyeballs==2.4.3
+aiohttp==3.10.10
+aiosignal==1.3.1
+altair==5.4.1
+annotated-types==0.7.0
+anyio==4.6.2.post1
+async-timeout==4.0.3
+attrs==24.2.0
+beautifulsoup4==4.12.3
+blinker==1.9.0
+cachetools==5.5.0
+certifi==2024.8.30
+charset-normalizer==3.4.0
+click==8.1.7
+dataclasses-json==0.6.7
+Deprecated==1.2.14
+dirtyjson==1.0.8
+distro==1.9.0
+einops==0.7.0
+exceptiongroup==1.2.2
+filelock==3.16.1
+filetype==1.2.0
+frozenlist==1.5.0
+fsspec==2024.10.0
+gitdb==4.0.11
+GitPython==3.1.43
+greenlet==3.1.1
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+huggingface-hub==0.23.1
+idna==3.10
+InstructorEmbedding==1.0.1
+Jinja2==3.1.4
+jiter==0.7.0
+joblib==1.4.2
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+llama-cloud==0.1.4
+llama-index==0.10.38
+llama-index-agent-openai==0.2.9
+llama-index-cli==0.1.13
+llama-index-core==0.10.68.post1
+llama-index-embeddings-huggingface==0.3.1
+llama-index-embeddings-instructor==0.2.1
+llama-index-embeddings-openai==0.1.11
+llama-index-indices-managed-llama-cloud==0.1.6
+llama-index-legacy==0.9.48.post4
+llama-index-llms-huggingface==0.2.0
+llama-index-llms-openai==0.1.31
+llama-index-llms-openai-like==0.2.0
+llama-index-llms-replicate==0.3.0
+llama-index-multi-modal-llms-openai==0.1.9
+llama-index-program-openai==0.1.7
+llama-index-question-gen-openai==0.1.3
+llama-index-readers-file==0.1.33
+llama-index-readers-llama-parse==0.1.6
+llama-parse==0.4.9
+llamaindex-py-client==0.1.19
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.23.1
+mdurl==0.1.2
+minijinja==2.5.0
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+narwhals==1.13.3
+nest-asyncio==1.6.0
+networkx==3.4.2
+nltk==3.9.1
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.21.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.1.105
+openai==1.54.3
+openmind-hub==0.9.0
+packaging==24.2
+pandas==2.2.3
+pillow==10.4.0
+propcache==0.2.0
+protobuf==5.26.1
+psutil==6.1.0
+pyarrow==18.0.0
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydeck==0.9.1
+Pygments==2.18.0
+pypdf==4.3.1
+python-dateutil==2.9.0.post0
+pytz==2024.2
+PyYAML==6.0.2
+referencing==0.35.1
+regex==2024.11.6
+requests==2.32.2
+rich==13.9.4
+rpds-py==0.21.0
+safetensors==0.4.5
+scikit-learn==1.5.2
+scipy==1.14.1
+sentence-transformers==2.7.0
+sentencepiece==0.2.0
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+soupsieve==2.6
+SQLAlchemy==2.0.36
+streamlit==1.39.0
+striprtf==0.0.26
+sympy==1.13.1
+tenacity==8.5.0
+text-generation==0.7.0
+threadpoolctl==3.5.0
+tiktoken==0.8.0
+tokenizers==0.19.1
+toml==0.10.2
+torch==2.5.0+cu121
+torchaudio==2.5.0+cu121
+torchvision==0.20.0+cu121
+tornado==6.4.1
+tqdm==4.67.0
+transformers==4.41.1
+triton==3.1.0
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+watchdog==5.0.3
+wrapt==1.16.0
+yarl==1.17.1