Initial commit with blog generation code

app.py

@@ -0,0 +1,217 @@
+import os
+import asyncio
+import json
+import re
+import requests
+import streamlit as st
+
+from lagent.agents import Agent
+from lagent.prompts.parsers import PluginParser
+from lagent.agents.stream import PLUGIN_CN, get_plugin_prompt
+from lagent.schema import AgentMessage
+from lagent.actions import ArxivSearch
+from lagent.hooks import Hook
+from lagent.llms import GPTAPI
+
+YOUR_TOKEN_HERE = os.getenv("token")
+if not YOUR_TOKEN_HERE:
+    raise EnvironmentError("未找到环境变量 'token'，请设置后再运行程序。")
+
+# Hook类，用于对消息添加前缀
+class PrefixedMessageHook(Hook):
+    def __init__(self, prefix, senders=None):
+        """
+        初始化Hook
+        :param prefix: 消息前缀
+        :param senders: 指定发送者列表
+        """
+        self.prefix = prefix
+        self.senders = senders or []
+
+    def before_agent(self, agent, messages, session_id):
+        """
+        在代理处理消息前修改消息内容
+        :param agent: 当前代理
+        :param messages: 消息列表
+        :param session_id: 会话ID
+        """
+        for message in messages:
+            if message.sender in self.senders:
+                message.content = self.prefix + message.content
+
+class AsyncBlogger:
+    """博客生成类，整合写作者和批评者。"""
+
+    def __init__(self, model_type, api_base, writer_prompt, critic_prompt, critic_prefix='', max_turn=2):
+        """
+        初始化博客生成器
+        :param model_type: 模型类型
+        :param api_base: API 基地址
+        :param writer_prompt: 写作者提示词
+        :param critic_prompt: 批评者提示词
+        :param critic_prefix: 批评消息前缀
+        :param max_turn: 最大轮次
+        """
+        self.model_type = model_type
+        self.api_base = api_base
+        self.llm = GPTAPI(
+            model_type=model_type,
+            api_base=api_base,
+            key=YOUR_TOKEN_HERE,
+            max_new_tokens=4096,
+        )
+        self.plugins = [dict(type='lagent.actions.ArxivSearch')]
+        self.writer = Agent(
+            self.llm,
+            writer_prompt,
+            name='写作者',
+            output_format=dict(
+                type=PluginParser,
+                template=PLUGIN_CN,
+                prompt=get_plugin_prompt(self.plugins)
+            )
+        )
+        self.critic = Agent(
+            self.llm,
+            critic_prompt,
+            name='批评者',
+            hooks=[PrefixedMessageHook(critic_prefix, ['写作者'])]
+        )
+        self.max_turn = max_turn
+
+    async def forward(self, message: AgentMessage, update_placeholder):
+        """
+        执行多阶段博客生成流程
+        :param message: 初始消息
+        :param update_placeholder: Streamlit占位符
+        :return: 最终优化的博客内容
+        """
+        step1_placeholder = update_placeholder.container()
+        step2_placeholder = update_placeholder.container()
+        step3_placeholder = update_placeholder.container()
+
+        # 第一步：生成初始内容
+        step1_placeholder.markdown("**Step 1: 生成初始内容...**")
+        message = self.writer(message)
+        if message.content:
+            step1_placeholder.markdown(f"**生成的初始内容**:\n\n{message.content}")
+        else:
+            step1_placeholder.markdown("**生成的初始内容为空，请检查生成逻辑。**")
+
+        # 第二步：批评者提供反馈
+        step2_placeholder.markdown("**Step 2: 批评者正在提供反馈和文献推荐...**")
+        message = self.critic(message)
+        if message.content:
+            # 解析批评者反馈
+            suggestions = re.search(r"批评建议：\s*(.*?)\s*推荐的关键词：", message.content, re.S)
+            if suggestions:
+                feedback = suggestions.group(1).strip()
+            else:
+                feedback = "未提供批评建议"
+            
+
+            keywords = re.findall(r"-\s([a-zA-Z\-]+)", message.content)
+            feedback = suggestions.group(1).strip() if suggestions else "未提供批评建议"
+
+            # 打印提取的反馈和关键词
+            st.write(f"提取的批评建议：\n{feedback}")
+            st.write(f"提取的推荐关键词：\n{keywords}")
+            
+            english_keywords = [kw.strip() for kw in keywords if re.match(r'^[a-zA-Z\-]+$', kw.strip())]
+
+            # Arxiv 文献查询
+            arxiv_search = ArxivSearch()
+            arxiv_results = arxiv_search.get_arxiv_article_information(', '.join(english_keywords))
+
+            # 显示批评内容和文献推荐
+            message.content = f"**批评建议**:\n{feedback}\n\n**推荐的文献**:\n{arxiv_results}"
+            step2_placeholder.markdown(f"**批评和文献推荐**:\n\n{message.content}")
+        else:
+            step2_placeholder.markdown("**批评内容为空，请检查批评逻辑。**")
+
+
+
+        # 第三步：写作者根据反馈优化内容
+        step3_placeholder.markdown("**Step 3: 根据反馈改进内容...**")
+        improvement_prompt = AgentMessage(
+            sender="critic",
+            content=(
+                f"根据以下批评建议和推荐文献对内容进行改进：\n\n"
+                f"批评建议：\n{feedback}\n\n"
+                f"推荐文献：\n{arxiv_results}\n\n"
+                f"请优化初始内容，使其更加清晰、丰富，并符合专业水准。"
+            ),
+        )
+        message = self.writer(improvement_prompt)
+        if message.content:
+            step3_placeholder.markdown(f"**最终优化的博客内容**:\n\n{message.content}")
+        else:
+            step3_placeholder.markdown("**最终优化的博客内容为空，请检查生成逻辑。**")
+
+        return message
+
+def setup_sidebar():
+    """设置侧边栏，选择模型。"""
+    model_name = st.sidebar.text_input('模型名称：', value='internlm2.5-latest')
+    api_base = st.sidebar.text_input(
+        'API Base 地址：', value='https://internlm-chat.intern-ai.org.cn/puyu/api/v1/chat/completions'
+    )
+    
+    return model_name, api_base
+    
+def main():
+    """
+    主函数：构建Streamlit界面并处理用户交互
+    """
+    st.set_page_config(layout='wide', page_title='Lagent Web Demo', page_icon='🤖')
+    st.title("多代理博客优化助手")
+
+    model_type, api_base = setup_sidebar()
+    topic = st.text_input('输入一个话题：', 'Self-Supervised Learning')
+    generate_button = st.button('生成博客内容')
+
+    if (
+        'blogger' not in st.session_state or
+        st.session_state['model_type'] != model_type or
+        st.session_state['api_base'] != api_base
+    ):
+        st.session_state['blogger'] = AsyncBlogger(
+            model_type=model_type,
+            api_base=api_base,
+            writer_prompt="你是一位优秀的AI内容写作者，请撰写一篇有吸引力且信息丰富的博客内容。",
+            critic_prompt="""
+                作为一位严谨的批评者，请给出建设性的批评和改进建议，并基于相关主题使用已有的工具推荐一些参考文献，推荐的关键词应该是英语形式，简洁且切题。
+                请按照以下格式提供反馈：
+                1. 批评建议：
+                - （具体建议）
+                2. 推荐的关键词：
+                - （关键词1）
+                - （关键词2）
+                - （...）
+                3. 推荐的文献：
+                - （文献1）
+                - （文献2）
+                - （...）
+            """,
+            critic_prefix="请批评以下内容，并提供改进建议：\n\n"
+        )
+        st.session_state['model_type'] = model_type
+        st.session_state['api_base'] = api_base
+
+    if generate_button:
+        update_placeholder = st.empty()
+
+        async def run_async_blogger():
+            message = AgentMessage(
+                sender='user',
+                content=f"请撰写一篇关于{topic}的博客文章，要求表达专业，生动有趣，并且易于理解。"
+            )
+            result = await st.session_state['blogger'].forward(message, update_placeholder)
+            return result
+
+        loop = asyncio.new_event_loop()
+        asyncio.set_event_loop(loop)
+        loop.run_until_complete(run_async_blogger())
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,176 @@
+aiohappyeyeballs==2.4.4
+aiohttp==3.11.11
+aiosignal==1.3.2
+altair==5.5.0
+annotated-types==0.7.0
+anyio==4.7.0
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+arrow==1.3.0
+arxiv==2.1.3
+asttokens==3.0.0
+async-lru==2.0.4
+async-timeout==5.0.1
+asyncache==0.3.1
+asyncer==0.0.8
+attrs==24.3.0
+babel==2.16.0
+backports.strenum==1.3.1
+beautifulsoup4==4.12.3
+bleach==6.2.0
+blinker==1.9.0
+Brotli @ file:///croot/brotli-split_1714483155106/work
+cachetools==5.5.0
+certifi @ file:///croot/certifi_1734473278428/work/certifi
+cffi==1.17.1
+charset-normalizer @ file:///croot/charset-normalizer_1721748349566/work
+class-registry==2.1.2
+click==8.1.8
+colorama==0.4.6
+comm==0.2.2
+datasets==3.1.0
+debugpy==1.8.11
+decorator==5.1.1
+defusedxml==0.7.1
+dill==0.3.8
+distro==1.9.0
+duckduckgo_search==5.3.1b1
+exceptiongroup==1.2.2
+executing==2.1.0
+fastjsonschema==2.21.1
+feedparser==6.0.11
+filelock @ file:///croot/filelock_1700591183607/work
+fqdn==1.5.1
+frozenlist==1.5.0
+fsspec==2024.9.0
+func_timeout==4.3.5
+gitdb==4.0.11
+GitPython==3.1.43
+gmpy2 @ file:///tmp/build/80754af9/gmpy2_1645455533097/work
+griffe==0.48.0
+h11==0.14.0
+h2==4.1.0
+hpack==4.0.0
+httpcore==1.0.7
+httpx==0.28.1
+huggingface-hub==0.27.0
+hyperframe==6.0.1
+idna @ file:///croot/idna_1714398848350/work
+ipykernel==6.29.5
+ipython==8.31.0
+ipywidgets==8.1.5
+isoduration==20.11.0
+jedi==0.19.2
+Jinja2 @ file:///croot/jinja2_1730902924303/work
+jiter==0.8.2
+json5==0.10.0
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+jupyter==1.0.0
+jupyter-console==6.6.3
+jupyter-events==0.11.0
+jupyter-lsp==2.2.5
+jupyter_client==8.6.2
+jupyter_core==5.7.2
+jupyter_server==2.15.0
+jupyter_server_terminals==0.5.3
+jupyterlab==4.3.4
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.27.3
+jupyterlab_widgets==3.0.13
+-e git+https://github.com/InternLM/lagent.git@e304e5d323cdbb631257fac9187d16b99476bc2f#egg=lagent
+markdown-it-py==3.0.0
+MarkupSafe @ file:///croot/markupsafe_1704205993651/work
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mistune==3.0.2
+mkl-service==2.4.0
+mkl_fft @ file:///io/mkl313/mkl_fft_1730824109137/work
+mkl_random @ file:///io/mkl313/mkl_random_1730823916628/work
+mpmath @ file:///croot/mpmath_1690848262763/work
+multidict==6.1.0
+multiprocess==0.70.16
+narwhals==1.19.1
+nbclient==0.10.2
+nbconvert==7.16.4
+nbformat==5.10.4
+nest-asyncio==1.6.0
+networkx @ file:///croot/networkx_1717597493534/work
+notebook==7.3.2
+notebook_shim==0.2.4
+numpy @ file:///croot/numpy_and_numpy_base_1725470312869/work/dist/numpy-2.0.1-cp310-cp310-linux_x86_64.whl#sha256=120568f3fd675f59e4cb6de79a5c193b4067d90878d8bab2040fda8e3a2df6fa
+overrides==7.7.0
+packaging==24.2
+pandas==2.2.3
+pandocfilters==1.5.1
+parso==0.8.4
+pexpect==4.9.0
+pillow==10.4.0
+platformdirs==4.3.6
+prometheus_client==0.21.1
+prompt_toolkit==3.0.48
+propcache==0.2.1
+protobuf==5.29.2
+psutil==6.1.1
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyarrow==18.1.0
+pycparser==2.22
+pydantic==2.6.4
+pydantic_core==2.16.3
+pydeck==0.9.1
+Pygments==2.18.0
+PySocks @ file:///home/builder/ci_310/pysocks_1640793678128/work
+python-dateutil==2.9.0.post0
+python-json-logger==3.2.1
+pytz==2024.2
+PyYAML @ file:///croot/pyyaml_1728657952215/work
+pyzmq==26.2.0
+qtconsole==5.6.1
+QtPy==2.4.2
+referencing==0.35.1
+regex==2024.11.6
+requests @ file:///croot/requests_1730999120400/work
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rich==13.9.4
+rpds-py==0.22.3
+Send2Trash==1.8.3
+sgmllib3k==1.0.0
+six==1.17.0
+smmap==5.0.1
+sniffio==1.3.1
+socksio==1.0.0
+soupsieve==2.6
+stack-data==0.6.3
+streamlit==1.39.0
+sympy @ file:///croot/sympy_1734622612703/work
+tenacity==9.0.0
+termcolor==2.4.0
+terminado==0.18.1
+tiktoken==0.8.0
+timeout-decorator==0.5.0
+tinycss2==1.4.0
+toml==0.10.2
+tomli==2.2.1
+torch==2.1.2
+torchaudio==2.1.2
+torchvision==0.16.2
+tornado==6.4.2
+tqdm==4.67.1
+traitlets==5.14.3
+triton==2.1.0
+types-python-dateutil==2.9.0.20241206
+typing_extensions @ file:///croot/typing_extensions_1734714854207/work
+tzdata==2024.2
+uri-template==1.3.0
+urllib3 @ file:///croot/urllib3_1727769808118/work
+watchdog==5.0.3
+wcwidth==0.2.13
+webcolors==24.11.1
+webencodings==0.5.1
+websocket-client==1.8.0
+widgetsnbextension==4.0.13
+xxhash==3.5.0
+yarl==1.18.3