├── example_image ├── img01.png └── img02.png ├── requirements.txt ├── config.py ├── README.md ├── server └── create_knowledge_base.py ├── webui.py ├── api.py └── LICENSE /example_image/img01.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ZhouhaoJiang/PdfReader-LangChian-LLM/HEAD/example_image/img01.png -------------------------------------------------------------------------------- /example_image/img02.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ZhouhaoJiang/PdfReader-LangChian-LLM/HEAD/example_image/img02.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | fastapi==0.101.1 2 | gradio==3.40.1 3 | langchain==0.0.268 4 | pydantic==1.10.12 5 | Requests==2.31.0 6 | sse_starlette==1.6.1 7 | starlette==0.31.0 8 | torch==2.0.1+cu117 9 | transformers==4.30.2 10 | uvicorn==0.23.2 11 | search_engine_parser 12 | -------------------------------------------------------------------------------- /config.py: -------------------------------------------------------------------------------- 1 | import os 2 | 3 | # 当前目录 4 | # BASE_DIR = os.path.dirname(os.path.abspath(__file__)) 5 | 6 | # LLM_MODEL_PATH = r"D:\Project\ChatPdf\chatglm2-6b-int4" 7 | LLM_MODEL_PATH = "THUDM/chatglm2-6b-int4" # 对话模型 8 | 9 | # EMBEDDING_MODEL_PATH = r'D:\Project\ChatPdf\text2vec-base-chinese' 10 | EMBEDDING_MODEL_PATH = 'shibing624/text2vec-base-multilingual' # 检索模型文件 or huggingface远程仓库 11 | 12 | PDF_FILE_PATH = r"D:\Project\Langchain-LLM-PdfReader\pdf_file" 13 | KNOWLEDGE_FILE_PATH = r"D:\Project\Langchain-LLM-PdfReader\knowledge_base" 14 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 这个项目存在很多需要优化的地方 2 | 跑完这个项目你能学会 本地化部署ChatGLM LangChain基础的使用 3 | 4 | There are a lot of improvements to be made in this project 5 | By the end of this project you will be able to localize the basics of ChatGLM and LangChain 6 | 7 | # PdfReader-LangChian-LLM 8 | Implement PDF parsing based on LangChain and LLM language model 9 | 基于LangChain和LLM语言模型实现PDF解析阅读 10 | #### 参考项目 11 | - [LangChain](https://github.com/langchain-ai/langchain) 12 | - [ChatGLM2-6B](https://github.com/THUDM/ChatGLM2-6B) 13 | ## 1. 项目介绍 14 | 实现了一个简单的基于LangChain和LLM语言模型实现PDF解析阅读, 通过Langchain的Embedding对输入的PDF进行向量化， 15 | 然后通过LLM语言模型对向量化后的PDF进行解码， 得到PDF的文本内容,进而根据用户提问,来匹配PDF具体内容,进而交给语言模型处理,得到答案。 16 | 17 | __项目截图__ 18 | ![项目截图01](./example_image/img01.png) 19 | ![项目截图02](./example_image/img02.png) 20 | __项目使用的模型有__ 21 | text2vec-base-multilingual 22 | chatglm2-6b-int4 23 | 24 | ## 2. 项目启动方法 25 | 26 | ### 2.1 config.py文件 27 | 检查模型文件和文件存放路径 28 | 29 | ### 2.2 环境配置 30 | python3.8 31 | 32 | pip install -r requirements.txt 33 | ### 2.3 启动项目 34 | 需要先启动api再启动webui 35 | 36 | python api.py 37 | python webui.py 38 | 39 | -------------------------------------------------------------------------------- /server/create_knowledge_base.py: -------------------------------------------------------------------------------- 1 | import os 2 | import time 3 | 4 | from langchain.document_loaders import PyPDFLoader, UnstructuredFileLoader 5 | from langchain.embeddings import HuggingFaceEmbeddings 6 | from langchain.text_splitter import RecursiveCharacterTextSplitter 7 | from langchain.vectorstores import Chroma 8 | import config 9 | 10 | 11 | def create_base(file_path, kb_name): 12 | """ 13 | 创建PDF文件向量库 14 | :param kb_name: 15 | :param file_path: 文件路径 16 | :return: 17 | """ 18 | try: 19 | print(f'file: {file_path}') 20 | print("Start building vector database... %s", time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())) 21 | # loader = UnstructuredFileLoader(file_path, model="element") 22 | loader = PyPDFLoader(file_path) 23 | docs = loader.load() 24 | # print(f'docs: {docs}') 25 | 26 | # 文本分割 27 | text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=200) 28 | docs = text_splitter.split_documents(docs) 29 | 30 | # 向量化 31 | embedding = HuggingFaceEmbeddings(model_name=config.EMBEDDING_MODEL_PATH) 32 | # 构造向量库+conversation_id 33 | persist_directory = os.path.join(config.KNOWLEDGE_FILE_PATH, kb_name) 34 | 35 | # 创建向量数据库 36 | vectordb = Chroma.from_documents( 37 | documents=docs, 38 | embedding=embedding, 39 | persist_directory=persist_directory 40 | ) 41 | print("vectordb:", vectordb._collection.count()) 42 | vectordb.persist() 43 | print("Vector database building finished. %s", time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())) 44 | 45 | return {"status": 200, "message": "success"} 46 | 47 | except Exception as e: 48 | return {"status": 500, "message": str(e)} 49 | -------------------------------------------------------------------------------- /webui.py: -------------------------------------------------------------------------------- 1 | import base64 2 | import json 3 | import os 4 | import random 5 | import time 6 | import requests 7 | import config 8 | import gradio as gr 9 | 10 | 11 | # 重置会话 12 | def clear(): 13 | return '', None 14 | 15 | 16 | def create_base(kb_name, filname, pdf_file): 17 | """ 18 | 创建知识库 19 | :param kb_name: 20 | :param filname: 21 | :param pdf_file: 22 | :return: 23 | """ 24 | # 二进制转base64 25 | pdf_file = base64.b64encode(pdf_file) 26 | pdf_file = pdf_file.decode("utf-8") 27 | 28 | params = { 29 | "kb_name": kb_name, 30 | "file_name": filname, 31 | "pdf_file": pdf_file, 32 | } 33 | gr.Info("知识库创建中...") 34 | response = requests.post("http://127.0.0.1:9999/create_knowledge_base", json=params) 35 | if response.status_code == 200: 36 | print("Connection established. Receiving data...") 37 | gr.Info("知识库创建成功") 38 | return kb_name 39 | else: 40 | print("Failed to connect. Status code:", response.status_code) 41 | gr.Error("知识库创建失败") 42 | return None 43 | 44 | 45 | # 请求会话api 46 | def request_chatglm(kb_name, query, chat_history, chat_type): 47 | """ 48 | 请求会话api 49 | :param chat_type: 50 | :param kb_name: 51 | :param query: 52 | :param chat_history: 53 | :return: 54 | """ 55 | print(query) 56 | if chat_type == "知识库对话": 57 | params = { 58 | "kb_name": kb_name, 59 | "query": query, 60 | } 61 | print("params:", params) 62 | response = requests.post("http://127.0.0.1:9999/PdfReader", json=params, stream=True) 63 | if response.status_code == 200: 64 | print("Connection established. Receiving data...") 65 | chat_history = [[query, ""]] 66 | # chat_history.append([query, ""]) 67 | for line in response.iter_lines(decode_unicode=True): 68 | try: 69 | data_dict = json.loads(line[6:]) 70 | chat_response = data_dict["response"] 71 | print("chat_response:", chat_response) 72 | print("chat_history:", chat_history) 73 | chat_history[-1][1] = chat_response 74 | yield chat_history 75 | except Exception as e: 76 | print("Exception in handle_sse_response:", e) 77 | # yield None 78 | else: 79 | print("Failed to connect. Status code:", response.status_code) 80 | gr.Error("Failed to connect") 81 | else: 82 | params = { 83 | "query": query, 84 | } 85 | response = requests.post("http://127.0.0.1:9999/Stream_chat", json=params, stream=True) 86 | if response.status_code == 200: 87 | print("Connection established. Receiving data...") 88 | print("chat_history:", chat_history) 89 | chat_history.append([query, ""]) 90 | for line in response.iter_lines(decode_unicode=True): 91 | try: 92 | data_dict = json.loads(line[6:]) 93 | chat_response = data_dict["response"] 94 | # print("chat_response:", chat_response) 95 | # print("chat_history:", chat_history) 96 | chat_history[-1][1] = chat_response 97 | yield chat_history 98 | except Exception as e: 99 | print("Exception in handle_sse_response:", e) 100 | # yield None 101 | else: 102 | print("Failed to connect. Status code:", response.status_code) 103 | gr.Error("Failed to connect. Status code:", response.status_code) 104 | 105 | 106 | with gr.Blocks(title="PdfReader") as webui: 107 | gr.Markdown( 108 | """ 109 |

PdfReader With LangChain
110 | """ 111 | ) 112 | with gr.Row(): 113 | with gr.Column(scale=1): 114 | embedding_model = gr.Dropdown(label="Embedding Model", choices=["text2vec"], value="text2vec") 115 | llm_model = gr.Dropdown(label="LLM Model", choices=["chatglm2-6b-int4"], value="chatglm2-6b-int4") 116 | 117 | chat_type = gr.Radio(label="对话方式", choices=["知识库对话", "模型对话"], value="模型对话") 118 | 119 | # kb_name = gr.Radio(choices=[name for name in os.listdir(config.KNOWLEDGE_FILE_PATH) if 120 | # os.path.isdir(os.path.join(config.KNOWLEDGE_FILE_PATH, name))], 121 | # label="知识库", value="无", live=True) 122 | # kb_submit = gr.Button(value="加载知识库", variant="primary") 123 | 124 | pdf_file = gr.File(label="PDF File", file_types=["pdf"], type="binary") 125 | writer_kb_name = gr.Textbox(label="填写知识库名称") 126 | create_button = gr.Button(value="构造知识库", variant="primary") 127 | 128 | with gr.Column(scale=3): 129 | chatbot = gr.Chatbot().style(height=500) 130 | query = gr.Textbox() 131 | with gr.Row(): 132 | submit = gr.Button(value="发送", variant="primary") 133 | clear_btn = gr.Button(value="清空", variant="secondary") 134 | 135 | create_button.click(create_base, [writer_kb_name, writer_kb_name, pdf_file], outputs=[writer_kb_name]) 136 | submit.click(request_chatglm, inputs=[writer_kb_name, query, chatbot, chat_type], outputs=[chatbot]) 137 | clear_btn.click(clear, outputs=[query, chatbot]) 138 | # submit.click(test, inputs=[kb_name, query, chatbot], outputs=[chatbot]) 139 | 140 | if __name__ == '__main__': 141 | webui.launch(inline=False, share=True, debug=True, server_name="0.0.0.0", server_port=7788, 142 | enable_queue=True, show_error=True) 143 | -------------------------------------------------------------------------------- /api.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | import base64 3 | import json 4 | import logging 5 | import os 6 | import sys 7 | import time 8 | from typing import List, Tuple 9 | 10 | import requests 11 | from fastapi import Body 12 | from pydantic import BaseModel 13 | 14 | import config 15 | import fastapi 16 | import uvicorn 17 | import logging 18 | import sys 19 | import torch 20 | from sse_starlette import EventSourceResponse, ServerSentEvent 21 | from langchain.embeddings import HuggingFaceEmbeddings 22 | from langchain.vectorstores import Chroma 23 | from server.create_knowledge_base import create_base 24 | from transformers import AutoTokenizer, AutoModel 25 | from starlette.middleware.cors import CORSMiddleware 26 | 27 | 28 | # get-logger用于记录日志 29 | def getLogger(name, file_name, use_formatter=True): 30 | logger = logging.getLogger(name) 31 | logger.setLevel(logging.INFO) 32 | console_handler = logging.StreamHandler(sys.stdout) 33 | formatter = logging.Formatter('%(asctime)s %(message)s') 34 | console_handler.setFormatter(formatter) 35 | console_handler.setLevel(logging.INFO) 36 | logger.addHandler(console_handler) 37 | if file_name: 38 | handler = logging.FileHandler(file_name, encoding='utf8') 39 | handler.setLevel(logging.INFO) 40 | if use_formatter: 41 | formatter = logging.Formatter('%(asctime)s - %(name)s - %(message)s') 42 | handler.setFormatter(formatter) 43 | logger.addHandler(handler) 44 | return logger 45 | 46 | 47 | class ChatGLM(): 48 | def __init__(self) -> None: 49 | logger.info("Start initialize model...") 50 | self.tokenizer = AutoTokenizer.from_pretrained(config.LLM_MODEL_PATH, trust_remote_code=True) 51 | self.model = AutoModel.from_pretrained(config.LLM_MODEL_PATH, trust_remote_code=True).cuda() 52 | # 多显卡支持，使用下面两行代替上面一行，将num_gpus改为你实际的显卡数量 53 | # from utils import load_model_on_gpus 54 | # self.model = load_model_on_gpus("THUDM/chatglm2-6b", num_gpus=2) 55 | self.model.eval() 56 | logger.info("Model initialization finished.") 57 | 58 | def clear(self) -> None: 59 | if torch.cuda.is_available(): 60 | with torch.cuda.device: 61 | torch.cuda.empty_cache() 62 | torch.cuda.ipc_collect() 63 | 64 | def answer(self, query: str, history, prompt): 65 | print("answer:", query, history, prompt) 66 | response, history = self.model.chat(self.tokenizer, query, prompt, history=history, max_length=8192) 67 | history = [list(h) for h in history] 68 | return response, history 69 | 70 | def stream(self, query, history, page, prompt): 71 | if query is None or history is None: 72 | yield {"query": "", "response": "", "history": [], "finished": True} 73 | size = 0 74 | response = "" 75 | for response, history in self.model.eval().stream_chat( 76 | self.tokenizer, 77 | query=query, 78 | history=history, 79 | prompt=prompt, 80 | max_length=8192, 81 | top_p=0.9, 82 | temperature=0.9, 83 | past_key_values=None, 84 | return_past_key_values=False): 85 | this_response = response[size:] 86 | history = [list(h) for h in history] 87 | size = len(response) 88 | yield {"delta": this_response, "response": response, "finished": False} 89 | logger.info("Answer - {}".format(response)) 90 | yield {"response": response, "query": query, "page": page, "delta": "[EOS]", "history": history, 91 | "finished": True} 92 | # yield {"query": query, "delta": "[EOS]", "response": response, "page": page, "finished": True} 93 | 94 | 95 | logger = getLogger('ChatGLM', 'chatlog.log') 96 | MAX_HISTORY = 3 # 最大历史记录数 97 | 98 | 99 | def start_server(): 100 | env = os.environ 101 | app = fastapi.FastAPI() 102 | bot = ChatGLM() 103 | 104 | # 配置 CORS 中间件 105 | app.add_middleware( 106 | CORSMiddleware, 107 | allow_origins=["*"], # 允许所有来源，可以根据需求进行配置 108 | allow_credentials=True, 109 | allow_methods=["*"], # 允许所有请求方法 110 | allow_headers=["*"], # 允许所有请求头 111 | ) 112 | 113 | class CreateKnowledgeBaseRequest(BaseModel): 114 | kb_name: str = fastapi.Form(..., description="知识库名称") 115 | file_name: str = fastapi.Form(..., description="文件名称") 116 | pdf_file: str = fastapi.Form(..., description="base64编码的pdf文件内容") 117 | 118 | @app.post("/create_knowledge_base", tags=["Knowledge Base Management"], summary="创建知识库") 119 | async def create_knowledgebase( 120 | kbRequest: CreateKnowledgeBaseRequest = Body(..., context_type="application/json", 121 | description="创建知识库")): 122 | """ 123 | 创建知识库 124 | :param kbRequest: 125 | :param file_name: 126 | :param kb_name: 127 | :param pdf_file: 128 | :return: 129 | """ 130 | kb_name = kbRequest.kb_name 131 | file_name = kbRequest.file_name 132 | pdf_file = kbRequest.pdf_file 133 | 134 | # 保存文件至pdf_file/conversation_id 135 | file_path = os.path.join(config.PDF_FILE_PATH, kb_name) 136 | if not os.path.exists(file_path): 137 | os.makedirs(file_path) 138 | file_path = os.path.join(file_path, f"{file_name}.pdf") 139 | # 写入base64文件 140 | with open(file_path, "wb") as f: 141 | f.write(base64.b64decode(pdf_file)) 142 | 143 | # 创建知识库 144 | return create_base(file_path, kb_name) 145 | 146 | class SteamChatRequest(BaseModel): 147 | query: str = fastapi.Form(..., description="对话问题") 148 | history: List[Tuple[str, str]] = None 149 | 150 | @app.post("/Stream_chat", tags=["Chat"], summary="与llm模型对话") 151 | async def stream_chat( 152 | chatRequest: SteamChatRequest = Body(..., context_type="application/json", description="对话请求")): 153 | """ 154 | 与ChatGlm对话 155 | :param chatRequest: 156 | :return: 157 | """ 158 | query = chatRequest.query 159 | history = json.dumps(chatRequest.history) 160 | history = json.loads(history) 161 | 162 | def decorate(generator): 163 | print("generator", generator) 164 | for item in generator: 165 | yield ServerSentEvent(json.dumps(item, ensure_ascii=False), event='delta') 166 | 167 | try: 168 | text = query 169 | # ori_history = history 170 | page = [] 171 | prompt = "你是一个助手，负责用中文聊天和解决用户的问题。" 172 | logger.info("Query - {}".format(text)) 173 | # if len(ori_history) > 0: 174 | # logger.info("History - {}".format(ori_history)) 175 | # history = ori_history[-MAX_HISTORY:] 176 | # history = [tuple(h) for h in history] 177 | # return EventSourceResponse(decorate(bot.stream(text, history))) 178 | 179 | return EventSourceResponse(decorate(bot.stream(query=query, history=history, page=page, prompt=prompt))) 180 | except Exception as e: 181 | logger.error(f"error: {e}") 182 | return EventSourceResponse(decorate(bot.stream(None, None, None, None))) 183 | 184 | class PdfReaderRequest(BaseModel): 185 | kb_name: str = fastapi.Form(..., description="知识库名称") 186 | query: str = fastapi.Form(..., description="对话问题") 187 | history: List[Tuple[str, str]] = None 188 | 189 | @app.post("/PdfReader", tags=["Chat"], summary="与llm模型对话PDF") 190 | async def chatpdf( 191 | PdfRequest: PdfReaderRequest = Body(..., context_type="application/json", description="对话请求")): 192 | """ 193 | 与ChatGlm对话PDF 194 | :param PdfRequest: 195 | :param kb_name: 196 | :param history: [[问题,回答],[问题,回答],......] 空为[] 197 | :param query: 对话问题 198 | :return: 199 | """ 200 | kb_name = PdfRequest.kb_name 201 | query = PdfRequest.query 202 | history = json.dumps(PdfRequest.history) 203 | history = json.loads(history) 204 | print("history:", history) 205 | 206 | persist_directory = os.path.join(config.KNOWLEDGE_FILE_PATH, kb_name) 207 | print(persist_directory) 208 | 209 | # 联网搜索 210 | # try: 211 | # from search_engine_parser.core.engines.bing import Search as BingSearch 212 | # bsearch = BingSearch() 213 | # search_args = (query, 1) 214 | # results = await bsearch.async_search(*search_args) 215 | # web_content = results["description"][:5] 216 | # logger.info("Web_Search - {}".format(web_content)) 217 | # except Exception as e: 218 | # logger.error("Web_Search - {}".format(e)) 219 | # web_content = "" 220 | web_content = "" 221 | 222 | # 从目录加载向量 223 | logger.info("Start load vector database... %s", time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())) 224 | embedding = HuggingFaceEmbeddings(model_name=config.EMBEDDING_MODEL_PATH) 225 | vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding) 226 | print(vectordb._collection.count()) 227 | logger.info("Load database building finished. %s", time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())) 228 | 229 | # docs = vectordb.similarity_search(query, k=3) 230 | docs = vectordb.similarity_search(query, k=5) 231 | 232 | page = list(set([docs.metadata['page'] for docs in docs])) 233 | page.sort() 234 | 235 | context = [docs.page_content for docs in docs] 236 | prompt = f"已知PDF内容：\n{context}\n根据已知信息回答问题：\n{query}\n网络检索内容：\n{web_content}" 237 | 238 | def decorate(generator): 239 | print("generator", generator) 240 | for item in generator: 241 | yield ServerSentEvent(json.dumps(item, ensure_ascii=False), event='delta') 242 | 243 | try: 244 | text = query 245 | query = f"内容为：{context}\n根据已知信息回答问题：{query}" 246 | # 使用Langchain处理PDF去除历史记录 247 | history = [] 248 | # 给历史记录加上问题 249 | # new_message = [f"这是我提供的文章内容{context}", "收到"] 250 | # history.append(new_message) 251 | # history = json.dumps(history, ensure_ascii=False) 252 | ori_history = history 253 | logger.info("Query - {}".format(text)) 254 | if len(ori_history) > 0: 255 | logger.info("History - {}".format(ori_history)) 256 | history = ori_history[-MAX_HISTORY:] 257 | history = [tuple(h) for h in history] 258 | # return EventSourceResponse(decorate(bot.stream(text, history))) 259 | 260 | return EventSourceResponse(decorate(bot.stream(query, history, page=page, prompt=prompt))) 261 | except Exception as e: 262 | logger.error(f"error: {e}") 263 | return EventSourceResponse(decorate(bot.stream(None, None, None, None))) 264 | 265 | @app.get("/free_gc", tags=["GPU"], summary="释放GPU缓存") 266 | def free_gpu_cache(): 267 | try: 268 | bot.clear() 269 | return {"success": True} 270 | except Exception as e: 271 | logger.error(f"error: {e}") 272 | return {"success": False} 273 | 274 | host = env.get("HOST") if env.get("HOST") is not None else "0.0.0.0" 275 | port = int(env.get("PORT")) if env.get("PORT") is not None else 9999 276 | # uvicorn.run(app=app, host=host, port=port, reload=True) 277 | uvicorn.run(app=app, host=host, port=port) 278 | 279 | 280 | if __name__ == '__main__': 281 | start_server() 282 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------