基于InternLM和LangChain搭建自己的知识库

bash
/root/share/install_conda_env_internlm_base.sh InternLM

conda activate InternLM

# 升级pip
python -m pip install --upgrade pip

pip install modelscope==1.9.5
pip install transformers==4.35.2
pip install streamlit==1.24.0
pip install sentencepiece==0.1.99
pip install accelerate==0.24.1

mkdir -p /root/data/model/Shanghai_AI_Laboratory
cp -r /root/share/temp/model_repos/internlm-chat-7b /root/data/model/Shanghai_AI_Laboratory/internlm-chat-7b

import torch
from modelscope import snapshot_download, AutoModel, AutoTokenizer
import os
model_dir = snapshot_download('Shanghai_AI_Laboratory/internlm-chat-7b', cache_dir='/root/data/model', revision='v1.0.3')

pip install langchain==0.0.292
pip install gradio==4.4.0
pip install chromadb==0.4.15
pip install sentence-transformers==2.2.2
pip install unstructured==0.10.30
pip install markdown==3.3.7

pip install -U huggingface_hub

import os

# 下载模型
os.system('huggingface-cli download --resume-download sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 --local-dir /root/data/model/sentence-transformer')

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/data/model/sentence-transformer')

python download_hf.py

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

cd /root/data
git clone https://github.com/InternLM/tutorial

# 进入到数据库盘
cd /root/data
# clone 上述开源仓库
git clone https://gitee.com/open-compass/opencompass.git
git clone https://gitee.com/InternLM/lmdeploy.git
git clone https://gitee.com/InternLM/xtuner.git
git clone https://gitee.com/InternLM/InternLM-XComposer.git
git clone https://gitee.com/InternLM/lagent.git
git clone https://gitee.com/InternLM/InternLM.git

import os 
def get_files(dir_path):
    # args：dir_path，目标文件夹路径
    file_list = []
    for filepath, dirnames, filenames in os.walk(dir_path):
        # os.walk 函数将递归遍历指定文件夹
        for filename in filenames:
            # 通过后缀名判断文件类型是否满足要求
            if filename.endswith(".md"):
                # 如果满足要求，将其绝对路径加入到结果列表
                file_list.append(os.path.join(filepath, filename))
            elif filename.endswith(".txt"):
                file_list.append(os.path.join(filepath, filename))
    return file_list

from tqdm import tqdm
from langchain.document_loaders import UnstructuredFileLoader
from langchain.document_loaders import UnstructuredMarkdownLoader

def get_text(dir_path):
    # args：dir_path，目标文件夹路径
    # 首先调用上文定义的函数得到目标文件路径列表
    file_lst = get_files(dir_path)
    # docs 存放加载之后的纯文本对象
    docs = []
    # 遍历所有目标文件
    for one_file in tqdm(file_lst):
        file_type = one_file.split('.')[-1]
        if file_type == 'md':
            loader = UnstructuredMarkdownLoader(one_file)
        elif file_type == 'txt':
            loader = UnstructuredFileLoader(one_file)
        else:
            # 如果是不符合条件的文件，直接跳过
            continue
        docs.extend(loader.load())
    return docs

from langchain.text_splitter import RecursiveCharacterTextSplitter

text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=500, chunk_overlap=150)
split_docs = text_splitter.split_documents(docs)

from langchain.embeddings.huggingface import HuggingFaceEmbeddings

embeddings = HuggingFaceEmbeddings(model_name="/root/data/model/sentence-transformer")

from langchain.vectorstores import Chroma

# 定义持久化路径
persist_directory = 'data_base/vector_db/chroma'
# 加载数据库
vectordb = Chroma.from_documents(
    documents=split_docs,
    embedding=embeddings,
    persist_directory=persist_directory  # 允许我们将persist_directory目录保存到磁盘上
)
# 将加载的向量数据库持久化到磁盘上
vectordb.persist()

# 首先导入所需第三方库
from langchain.document_loaders import UnstructuredFileLoader
from langchain.document_loaders import UnstructuredMarkdownLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
from tqdm import tqdm
import os

# 获取文件路径函数
def get_files(dir_path):
    # args：dir_path，目标文件夹路径
    file_list = []
    for filepath, dirnames, filenames in os.walk(dir_path):
        # os.walk 函数将递归遍历指定文件夹
        for filename in filenames:
            # 通过后缀名判断文件类型是否满足要求
            if filename.endswith(".md"):
                # 如果满足要求，将其绝对路径加入到结果列表
                file_list.append(os.path.join(filepath, filename))
            elif filename.endswith(".txt"):
                file_list.append(os.path.join(filepath, filename))
    return file_list

# 加载文件函数
def get_text(dir_path):
    # args：dir_path，目标文件夹路径
    # 首先调用上文定义的函数得到目标文件路径列表
    file_lst = get_files(dir_path)
    # docs 存放加载之后的纯文本对象
    docs = []
    # 遍历所有目标文件
    for one_file in tqdm(file_lst):
        file_type = one_file.split('.')[-1]
        if file_type == 'md':
            loader = UnstructuredMarkdownLoader(one_file)
        elif file_type == 'txt':
            loader = UnstructuredFileLoader(one_file)
        else:
            # 如果是不符合条件的文件，直接跳过
            continue
        docs.extend(loader.load())
    return docs

# 目标文件夹
tar_dir = [
    "/root/data/InternLM",
    "/root/data/InternLM-XComposer",
    "/root/data/lagent",
    "/root/data/lmdeploy",
    "/root/data/opencompass",
    "/root/data/xtuner"
]

# 加载目标文件
docs = []
for dir_path in tar_dir:
    docs.extend(get_text(dir_path))

# 对文本进行分块
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=500, chunk_overlap=150)
split_docs = text_splitter.split_documents(docs)

# 加载开源词向量模型
embeddings = HuggingFaceEmbeddings(model_name="/root/data/model/sentence-transformer")

# 构建向量数据库
# 定义持久化路径
persist_directory = 'data_base/vector_db/chroma'
# 加载数据库
vectordb = Chroma.from_documents(
    documents=split_docs,
    embedding=embeddings,
    persist_directory=persist_directory  # 允许我们将persist_directory目录保存到磁盘上
)
# 将加载的向量数据库持久化到磁盘上
vectordb.persist()

from langchain.llms.base import LLM
from typing import Any, List, Optional
from langchain.callbacks.manager import CallbackManagerForLLMRun
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

class InternLM_LLM(LLM):
    # 基于本地 InternLM 自定义 LLM 类
    tokenizer : AutoTokenizer = None
    model: AutoModelForCausalLM = None

    def __init__(self, model_path :str):
        # model_path: InternLM 模型路径
        # 从本地初始化模型
        super().__init__()
        print("正在从本地加载模型...")
        self.tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
        self.model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True).to(torch.bfloat16).cuda()
        self.model = self.model.eval()
        print("完成本地模型的加载")

    def _call(self, prompt : str, stop: Optional[List[str]] = None,
                run_manager: Optional[CallbackManagerForLLMRun] = None,
                **kwargs: Any):
        # 重写调用函数
        system_prompt = """You are an AI assistant whose name is InternLM (书生·浦语).
        - InternLM (书生·浦语) is a conversational language model that is developed by Shanghai AI Laboratory (上海人工智能实验室). It is designed to be helpful, honest, and harmless.
        - InternLM (书生·浦语) can understand and communicate fluently in the language chosen by the user such as English and 中文.
        """
        
        messages = [(system_prompt, '')]
        response, history = self.model.chat(self.tokenizer, prompt , history=messages)
        return response
        
    @property
    def _llm_type(self) -> str:
        return "InternLM"

from langchain.vectorstores import Chroma
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
import os

# 定义 Embeddings
embeddings = HuggingFaceEmbeddings(model_name="/root/data/model/sentence-transformer")

# 向量数据库持久化路径
persist_directory = 'data_base/vector_db/chroma'

# 加载数据库
vectordb = Chroma(
    persist_directory=persist_directory, 
    embedding_function=embeddings
)

from LLM import InternLM_LLM
llm = InternLM_LLM(model_path = "/root/data/model/Shanghai_AI_Laboratory/internlm-chat-7b")
llm.predict("你是谁")

from langchain.prompts import PromptTemplate

# 我们所构造的 Prompt 模板
template = """使用以下上下文来回答用户的问题。如果你不知道答案，就说你不知道。总是使用中文回答。
问题: {question}
可参考的上下文：
···
{context}
···
如果给定的上下文无法让你做出回答，请回答你不知道。
有用的回答:"""

# 调用 LangChain 的方法来实例化一个 Template 对象，该对象包含了 context 和 question 两个变量，在实际调用时，这两个变量会被检索到的文档片段和用户提问填充
QA_CHAIN_PROMPT = PromptTemplate(input_variables=["context","question"],template=template)

from langchain.chains import RetrievalQA

qa_chain = RetrievalQA.from_chain_type(llm,retriever=vectordb.as_retriever(),return_source_documents=True,chain_type_kwargs={"prompt":QA_CHAIN_PROMPT})

# 检索问答链回答效果
question = "什么是InternLM"
result = qa_chain({"query": question})
print("检索问答链回答 question 的结果：")
print(result["result"])

# 仅 LLM 回答效果
result_2 = llm(question)
print("大模型回答 question 的结果：")
print(result_2)

from langchain.vectorstores import Chroma
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
import os
from LLM import InternLM_LLM
from langchain.prompts import PromptTemplate
from langchain.chains import RetrievalQA

def load_chain():
    # 加载问答链
    # 定义 Embeddings
    embeddings = HuggingFaceEmbeddings(model_name="/root/data/model/sentence-transformer")

    # 向量数据库持久化路径
    persist_directory = 'data_base/vector_db/chroma'

    # 加载数据库
    vectordb = Chroma(
        persist_directory=persist_directory,  # 允许我们将persist_directory目录保存到磁盘上
        embedding_function=embeddings
    )

    # 加载自定义 LLM
    llm = InternLM_LLM(model_path = "/root/data/model/Shanghai_AI_Laboratory/internlm-chat-7b")

    # 定义一个 Prompt Template
    template = """使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答
    案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。
    {context}
    问题: {question}
    有用的回答:"""

    QA_CHAIN_PROMPT = PromptTemplate(input_variables=["context","question"],template=template)

    # 运行 chain
    qa_chain = RetrievalQA.from_chain_type(llm,retriever=vectordb.as_retriever(),return_source_documents=True,chain_type_kwargs={"prompt":QA_CHAIN_PROMPT})
    
    return qa_chain

class Model_center():
    """
    存储检索问答链的对象 
    """
    def __init__(self):
        # 构造函数，加载检索问答链
        self.chain = load_chain()

    def qa_chain_self_answer(self, question: str, chat_history: list = []):
        """
        调用问答链进行回答
        """
        if question == None or len(question) < 1:
            return "", chat_history
        try:
            chat_history.append(
                (question, self.chain({"query": question})["result"]))
            # 将问答结果直接附加到问答历史中，Gradio 会将其展示出来
            return "", chat_history
        except Exception as e:
            return e, chat_history

import gradio as gr

# 实例化核心功能对象
model_center = Model_center()
# 创建一个 Web 界面
block = gr.Blocks()
with block as demo:
    with gr.Row(equal_height=True):   
        with gr.Column(scale=15):
            # 展示的页面标题
            gr.Markdown("""<h1><center>InternLM</center></h1>
                <center>书生浦语</center>
                """)

    with gr.Row():
        with gr.Column(scale=4):
            # 创建一个聊天机器人对象
            chatbot = gr.Chatbot(height=450, show_copy_button=True)
            # 创建一个文本框组件，用于输入 prompt。
            msg = gr.Textbox(label="Prompt/问题")

            with gr.Row():
                # 创建提交按钮。
                db_wo_his_btn = gr.Button("Chat")
            with gr.Row():
                # 创建一个清除按钮，用于清除聊天机器人组件的内容。
                clear = gr.ClearButton(
                    components=[chatbot], value="Clear console")
                
        # 设置按钮的点击事件。当点击时，调用上面定义的 qa_chain_self_answer 函数，并传入用户的消息和聊天历史记录，然后更新文本框和聊天机器人组件。
        db_wo_his_btn.click(model_center.qa_chain_self_answer, inputs=[
                            msg, chatbot], outputs=[msg, chatbot])

    gr.Markdown("""提醒：<br>
    1. 初始化数据库时间可能较长，请耐心等待。
    2. 使用中如果出现异常，将会在文本输入框进行展示，请不要惊慌。 <br>
    """)
gr.close_all()
# 直接启动
demo.launch()

ssh-keygen -t rsa

cat ~\.ssh\id_rsa.pub

ssh -CNg -L 7860:127.0.0.1:7860 root@ssh.intern-ai.org.cn -p 33090