环境准备
-
安装 Llamaindex
pip install llama-index==0.10.38 llama-index-llms-huggingface==0.2.0 "transformers[torch]==4.41.1" "huggingface_hub[inference]==0.23.1" huggingface_hub==0.23.1 sentence-transformers==2.7.0 sentencepiece==0.2.0
-
下载 Sentence Transformer 模型
mkdir llamaindex_demo cd llamaindex_demo touch download_hf.py
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 ./model/sentence-transformer')
python download_hf.py
-
下载 NLTK 相关资源
我们在使用开源词向量模型构建开源词向量的时候,需要用到第三方库 nltk 的一些资源。正常情况下,其会自动从互联网上下载,但可能由于网络原因会导致下载中断,此处我们可以从国内仓库镜像地址下载相关资源,保存到服务器上。
我们用以下命令下载 nltk 资源并解压到服务器上:cd llamaindex_demo 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
LlamaIndex HuggingFaceLLM
-
把 InternLM2 1.8B 软连接出来
cd llamaindex_demo ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b/ ./model/
-
新建llamaindex_internlm.py
from llama_index.llms.huggingface import HuggingFaceLLM
from llama_index.core.llms import ChatMessage
llm = HuggingFaceLLM(
model_name="./model/internlm2-chat-1_8b",
tokenizer_name="./model/internlm2-chat-1_8b",
model_kwargs={"trust_remote_code":True},
tokenizer_kwargs={"trust_remote_code":True}
)
rsp = llm.chat(messages=[ChatMessage(content="xtuner是什么?")])
print(rsp)
- 运行
python llamaindex_internlm.py
回答的效果并不好
LlamaIndex RAG
-
安装 LlamaIndex 词嵌入向量依赖
pip install llama-index-embeddings-huggingface llama-index-embeddings-instructor
-
获取知识库
mkdir data cd data git clone https://github.com/InternLM/xtuner.git mv xtuner/README_zh-CN.md ./
-
新建 llamaindex_RAG.py
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings from llama_index.embeddings.huggingface import HuggingFaceEmbedding from llama_index.llms.huggingface import HuggingFaceLLM #初始化一个HuggingFaceEmbedding对象,用于将文本转换为向量表示 embed_model = HuggingFaceEmbedding( #指定了一个预训练的sentence-transformer模型的路径 model_name="./model/sentence-transformer" ) #将创建的嵌入模型赋值给全局设置的embed_model属性, #这样在后续的索引构建过程中就会使用这个模型。 Settings.embed_model = embed_model llm = HuggingFaceLLM( model_name="./model/internlm2-chat-1_8b", tokenizer_name="./model/internlm2-chat-1_8b", model_kwargs={"trust_remote_code":True}, tokenizer_kwargs={"trust_remote_code":True} ) #设置全局的llm属性,这样在索引查询时会使用这个模型。 Settings.llm = llm #从指定目录读取所有文档,并加载数据到内存中 documents = SimpleDirectoryReader("./data").load_data() #创建一个VectorStoreIndex,并使用之前加载的文档来构建索引。 # 此索引将文档转换为向量,并存储这些向量以便于快速检索。 index = VectorStoreIndex.from_documents(documents) # 创建一个查询引擎,这个引擎可以接收查询并返回相关文档的响应。 query_engine = index.as_query_engine() response = query_engine.query("xtuner是什么?") print(response)
-
运行
python llamaindex_RAG.py
借助RAG技术后,就能获得我们想要的答案了。
LlamaIndex web
-
安装 streamlit
pip install streamlit==1.36.0
-
新建 app.py
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 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/sentence-transformer" ) Settings.embed_model = embed_model llm = HuggingFaceLLM( model_name="/root/model/internlm2-chat-1_8b", tokenizer_name="/root/model/internlm2-chat-1_8b", model_kwargs={"trust_remote_code": True}, tokenizer_kwargs={"trust_remote_code": True} ) 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)
-
运行
streamlit run app.py