├── .gitattributes ├── .gitignore ├── LICENSE ├── README.md ├── main.py └── requirements.txt /.gitattributes: -------------------------------------------------------------------------------- 1 | # Auto detect text files and perform LF normalization 2 | * text=auto 3 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow 105 | __pypackages__/ 106 | 107 | # Celery stuff 108 | celerybeat-schedule 109 | celerybeat.pid 110 | 111 | # SageMath parsed files 112 | *.sage.py 113 | 114 | # Environments 115 | .env 116 | .venv 117 | env/ 118 | venv/ 119 | ENV/ 120 | env.bak/ 121 | venv.bak/ 122 | 123 | # Spyder project settings 124 | .spyderproject 125 | .spyproject 126 | 127 | # Rope project settings 128 | .ropeproject 129 | 130 | # mkdocs documentation 131 | /site 132 | 133 | # mypy 134 | .mypy_cache/ 135 | .dmypy.json 136 | dmypy.json 137 | 138 | # Pyre type checker 139 | .pyre/ 140 | 141 | # pytype static type analyzer 142 | .pytype/ 143 | 144 | # Cython debug symbols 145 | cython_debug/ 146 | 147 | # PyCharm 148 | # JetBrains specific template is maintainted in a separate JetBrains.gitignore that can 149 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 150 | # and can be added to the global gitignore or merged into this file. For a more nuclear 151 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 152 | #.idea/ 153 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # AI_Agent 2 | ## LangChain Tutorial 3 3 | ## 动画演示透彻解释 Agent 概念 以及 实现Demo 4 | 5 | ## 涉及工具 6 | * Serper 7 | * Browserless 8 | 9 | ## 使用前 10 | * 运行前，请务必先自行完善 .env文件中的参数。包括但不限于各类 API key\Secret Key等。 11 | * 如果有疑问, 欢迎 email: 798800165@qq.com 12 | 13 | ## .env文件必要参数 list 14 | * OPENAI_API_KEY= 15 | * SERPER_API_KEY= 16 | * BROWSERLESS_API_KEY= 17 | 18 | ## 视频讲解 19 | * B站 https://www.bilibili.com/video/BV1JV411F7Yj/ 20 | * youtube https://youtu.be/_lyE6T0njWQ 21 | 22 | ## 小小声明 23 | 24 | ### 本项目代码均为演示 Demo 和授课讲解用，因为不是生产环境使用且时间仓促原因，代码质量请各位包涵，如果实际应用，请务必按照代码规范完善，谢谢 25 | -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- 1 | 2 | import os 3 | from dotenv import load_dotenv 4 | 5 | from langchain import PromptTemplate 6 | from langchain.agents import initialize_agent, Tool 7 | from langchain.agents import AgentType 8 | from langchain.chat_models import ChatOpenAI 9 | from langchain.prompts import MessagesPlaceholder 10 | from langchain.memory import ConversationSummaryBufferMemory 11 | from langchain.text_splitter import RecursiveCharacterTextSplitter 12 | from langchain.chains.summarize import load_summarize_chain 13 | from langchain.tools import BaseTool 14 | from pydantic import BaseModel, Field 15 | from langchain.schema import SystemMessage 16 | 17 | from typing import Type 18 | from bs4 import BeautifulSoup 19 | import requests 20 | import json 21 | 22 | import streamlit as st 23 | 24 | 25 | # 加载必要的参数 26 | load_dotenv() 27 | serper_api_key=os.getenv("SERPER_API_KEY") 28 | browserless_api_key=os.getenv("BROWSERLESS_API_KEY") 29 | openai_api_key=os.getenv("OPENAI_API_KEY") 30 | 31 | #调用 Google search by Serper 32 | def search(query): 33 | serper_google_url = os.getenv("SERPER_GOOGLE_URL") 34 | print(f"Serper Google Search URL: {serper_google_url}") 35 | 36 | payload = json.dumps({ 37 | "q": query 38 | }) 39 | 40 | headers = { 41 | 'X-API-KEY': serper_api_key, 42 | 'Content-Type': 'application/json' 43 | } 44 | 45 | response = requests.request("POST", serper_google_url, headers=headers, data=payload) 46 | 47 | print(f'Google 搜索结果: \n {response.text}') 48 | return response.text 49 | 50 | 51 | # 根据 url 爬取网页内容，给出最终解答 52 | # target ：分配给 agent 的初始任务 53 | # url ： Agent 在完成以上目标时所需要的URL，完全由Agent自主决定并且选取，其内容或是中间步骤需要，或是最终解答需要 54 | def scrape_website(target: str, url: str): 55 | print(f"开始爬取： {url}...") 56 | 57 | headers = { 58 | 'Cache-Control': 'no-cache', 59 | 'Content-Type': 'application/json', 60 | } 61 | 62 | payload = json.dumps({ 63 | "url": url 64 | }) 65 | 66 | post_url = f"https://chrome.browserless.io/content?token={browserless_api_key}" 67 | response = requests.post(post_url, headers=headers, data=payload) 68 | 69 | #如果返回成功 70 | if response.status_code == 200: 71 | soup = BeautifulSoup(response.content, "html.parser") 72 | text = soup.get_text() 73 | print("爬取的具体内容:", text) 74 | 75 | #控制返回内容长度，如果内容太长就需要切片分别总结处理 76 | if len(text) > 5000: 77 | #总结爬取的返回内容 78 | output = summary(target, text) 79 | return output 80 | else: 81 | return text 82 | else: 83 | print(f"HTTP request failed with status code {response.status_code}") 84 | 85 | # 如果需要处理的内容过长，先切片分别处理，再综合总结 86 | # 使用 Map-Reduce 方式 87 | def summary(target, content): 88 | #model list ： https://platform.openai.com/docs/models 89 | # gpt-4-32k gpt-3.5-turbo-16k-0613 90 | llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-16k-0613") 91 | 92 | #定义大文本切割器 93 | # chunk_overlap 是一个在使用 OpenAI 的 GPT-3 或 GPT-4 API 时可能会遇到的参数，特别是当你需要处理长文本时。 94 | # 该参数用于控制文本块（chunks）之间的重叠量。 95 | # 上下文维护：重叠确保模型在处理后续块时有足够的上下文信息。 96 | # 连贯性：它有助于生成更连贯和一致的输出，因为模型可以“记住”前一个块的部分内容。 97 | text_splitter = RecursiveCharacterTextSplitter( 98 | separators=["\n\n", "\n"], chunk_size=5000, chunk_overlap=200) 99 | 100 | 101 | docs = text_splitter.create_documents([content]) 102 | map_prompt = """ 103 | Write a summary of the following text for {target}: 104 | "{text}" 105 | SUMMARY: 106 | """ 107 | map_prompt_template = PromptTemplate( 108 | template=map_prompt, input_variables=["text", "target"]) 109 | 110 | summary_chain = load_summarize_chain( 111 | llm=llm, 112 | chain_type='map_reduce', 113 | map_prompt=map_prompt_template, 114 | combine_prompt=map_prompt_template, 115 | verbose=True 116 | ) 117 | 118 | output = summary_chain.run(input_documents=docs, target=target) 119 | 120 | return output 121 | 122 | 123 | class ScrapeWebsiteInput(BaseModel): 124 | """Inputs for scrape_website""" 125 | target: str = Field( 126 | description="The objective & task that users give to the agent") 127 | url: str = Field(description="The url of the website to be scraped") 128 | 129 | 130 | class ScrapeWebsiteTool(BaseTool): 131 | name = "scrape_website" 132 | description = "useful when you need to get data from a website url, passing both url and objective to the function; DO NOT make up any url, the url should only be from the search results" 133 | args_schema: Type[BaseModel] = ScrapeWebsiteInput 134 | 135 | def _run(self, target: str, url: str): 136 | return scrape_website(target, url) 137 | 138 | def _arun(self, url: str): 139 | raise NotImplementedError("error here") 140 | 141 | #初始化 agent 可使用的工具集合 142 | tools = [ 143 | Tool( 144 | name="Search", 145 | func=search, 146 | description="useful for when you need to answer questions about current events, data. You should ask targeted questions" 147 | ), 148 | ScrapeWebsiteTool(), 149 | ] 150 | 151 | #初始话角色详细描述 152 | system_message = SystemMessage( 153 | content="""You are a world class researcher, who can do detailed research on any topic and produce facts based results; 154 | you do not make things up, you will try as hard as possible to gather facts & data to back up the research 155 | 156 | Please make sure you complete the objective above with the following rules: 157 | 1/ You should do enough research to gather as much information as possible about the objective 158 | 2/ If there are url of relevant links & articles, you will scrape it to gather more information 159 | 3/ After scraping & search, you should think "is there any new things i should search & scraping based on the data I collected to increase research quality?" If answer is yes, continue; But don't do this more than 5 iteratins 160 | 4/ You should not make things up, you should only write facts & data that you have gathered 161 | 5/ In the final output, You should include all reference data & links to back up your research; You should include all reference data & links to back up your research 162 | 6/ In the final output, You should include all reference data & links to back up your research; You should include all reference data & links to back up your research""" 163 | ) 164 | #初始化 agent 角色模版 165 | agent_kwargs = { 166 | "extra_prompt_messages": [MessagesPlaceholder(variable_name="memory")], 167 | "system_message": system_message, 168 | } 169 | 170 | #初始化大语言模型 负责决策 171 | llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-16k-0613") 172 | 173 | #初始化记忆类型 174 | memory = ConversationSummaryBufferMemory( 175 | memory_key="memory", return_messages=True, llm=llm, max_token_limit=300) 176 | 177 | #初始化 agent 178 | agent = initialize_agent( 179 | tools, #配置工具集 180 | llm, #配置大语言模型 负责决策 181 | agent=AgentType.OPENAI_FUNCTIONS, #设置 agent 类型 https://python.langchain.com/docs/modules/agents/agent_types/openai_functions_agent 182 | verbose=True, 183 | agent_kwargs=agent_kwargs, #设定 agent 角色 184 | memory=memory, #配置记忆模式 185 | ) 186 | 187 | def main(): 188 | st.set_page_config(page_title="AI Assistant Agent", page_icon=":dolphin:") 189 | 190 | st.header("LangChain 实例讲解 3 -- Agent", divider='rainbow') 191 | st.header("AI Agent :blue[助理] :dolphin:") 192 | 193 | query = st.text_input("请提问题和需求：") 194 | 195 | if query: 196 | st.write(f"开始收集和总结资料 【 {query}】 请稍等") 197 | 198 | result = agent({"input": query}) 199 | 200 | st.info(result['output']) 201 | 202 | 203 | def print_hi(message): 204 | print('===============================================================') 205 | print(f'{message}') 206 | #print(f'OpenAI key: {openai_api_key}') 207 | #print(f'Serper key: {serper_api_key}') 208 | #print(f'Browserless key: {browserless_api_key}') 209 | print('===============================================================') 210 | 211 | if __name__ == '__main__': 212 | print_hi('AI Agent 助手 -- LangChain 实例讲解 3') 213 | main() 214 | 215 | 216 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | 2 | openai 3 | langchain 4 | bs4 5 | python-dotenv 6 | pydantic 7 | tiktoken 8 | --------------------------------------------------------------------------------