update st demo .

.github/ISSUE_TEMPLATE/bug-report.md

@@ -0,0 +1,28 @@
+---
+name: Bug Report
+about: Create a report to help us improve
+title: ''
+labels: bug
+assignees: ''
+
+---
+
+### Describe the bug
+Please provide a clear and concise description of what the bug is. If applicable, add screenshots to help explain your problem, especially for visualization related problems.
+
+### To Reproduce
+Please provide a [Minimal, Complete, and Verifiable example](https://stackoverflow.com/help/mcve) here. We hope we can simply copy/paste/run it. It is also nice to share a hosted runnable script (e.g. Google Colab), especially for hardware-related problems.
+
+### Describe your attempts
+- [ ] I checked the documentation and found no answer
+- [ ] I checked to make sure that this is not a duplicate issue
+
+You should also provide code snippets you tried as a workaround, StackOverflow solution that you have walked through, or your best guess of the cause that you can't locate (e.g. cosmic radiation).
+
+### Context
+ - **OS** [e.g. Windows 10, macOS 10.14]: 
+ - **Hardware** [e.g. CPU only, GTX 1080 Ti]: 
+
+
+### Additional Information
+Other things you want the developers to know.

.github/ISSUE_TEMPLATE/feature-request.md

@@ -0,0 +1,23 @@
+---
+name: Feature Request
+about: Suggest an idea for this project
+title: ''
+labels: enhancement
+assignees: ''
+
+---
+
+- [ ] I checked to make sure that this is not a duplicate issue
+- [ ] I'm submitting the request to the correct repository (for model requests
+
+### Is your feature request related to a problem? Please describe.
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+### Describe the solution you'd like
+A clear and concise description of what you want to happen.
+
+### Describe alternatives you've considered
+A clear and concise description of any alternative solutions or features you've considered.
+
+### Additional Information
+Other things you want the developers to know.

.github/ISSUE_TEMPLATE/usage-question.md

@@ -0,0 +1,18 @@
+---
+name: Usage Question
+about: Ask a question about usage
+title: ''
+labels: question
+assignees: ''
+
+---
+
+### Describe the Question
+Please provide a clear and concise description of what the question is.
+
+### Describe your attempts
+- [ ] I walked through the tutorials
+- [ ] I checked the documentation
+- [ ] I checked to make sure that this is not a duplicate question
+
+You may also provide a [Minimal, Complete, and Verifiable example](https://stackoverflow.com/help/mcve) you tried as a workaround, or StackOverflow solution that you have walked through. (e.g. cosmic radiation).

.github/stale.yml

@@ -0,0 +1,17 @@
+# Number of days of inactivity before an issue becomes stale
+daysUntilStale: 60
+# Number of days of inactivity before a stale issue is closed
+daysUntilClose: 7
+# Issues with these labels will never be considered stale
+exemptLabels:
+  - pinned
+  - security
+# Label to use when marking an issue as stale
+staleLabel: wontfix
+# Comment to post when marking an issue as stale. Set to `false` to disable
+markComment: >
+  This issue has been automatically marked as stale because it has not had
+  recent activity. It will be closed if no further activity occurs. Thank you
+  for your contributions.(由于长期不活动，机器人自动关闭此问题，如果需要欢迎提问)
+# Comment to post when closing a stale issue. Set to `false` to disable
+closeComment: false

.github/workflows/ubuntu.yml

@@ -0,0 +1,53 @@
+on:
+  workflow_dispatch: # Manually running a workflow
+name: Linux build
+jobs:
+  test-ubuntu:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+#        python-version: [ 3.7, 3.8, 3.9 ]
+        python-version: [ 3.9 ]
+    steps:
+      - uses: actions/checkout@v2
+      - name: Cache pip
+        uses: actions/cache@v2
+        if: startsWith(runner.os, 'Linux')
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+      - name: Cache huggingface models
+        uses: actions/cache@v2
+        with:
+          path: ~/.cache/huggingface
+          key: ${{ runner.os }}-huggingface-
+      - name: Cache text2vec models
+        uses: actions/cache@v2
+        with:
+          path: ~/.text2vec
+          key: ${{ runner.os }}-text2vec-
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install torch
+        run: |
+          python -m pip install --upgrade pip
+          pip install Cython
+          pip install torch
+      - name: Install from pypi
+        run: |
+          pip install -U agentica
+          python -c "import agentica; print(agentica.__version__)"
+          pip uninstall -y agentica
+      - name: Install dependencies
+        run: |
+          pip install -r requirements.txt
+          pip install .
+          pip install pytest
+      - name: PKG-TEST
+        run: |
+          python -m pytest

README.md

@@ -1,2 +1,72 @@
 # weibo-roast
-基于 agentica 构建了一个微博毒舌AI，疯狂 diss 微博博主
+基于 agentica 构建了一个微博毒舌AI，疯狂 diss 微博博主。
+
+微博吐槽（weibo-roast）是一个微博毒舌AI，集成了微博数据抓取、处理、分析和生成幽默毒舌评论的功能，通过weibo-crawler爬取指定用户的近20条原创微博，然后调用 GPT 模型生成对微博博主的"吐槽"。
+
+## 快速开始
+
+![demo](https://github.com/user-attachments/assets/bbcf26bd-2072-429c-9b50-876adfa6d9e8)
+
+
+```shell
+pip install -r requirements.txt
+cp .env.example .env
+python app.py
+```
+
+## 高级用法
+
+- 修改 `prompts.py` 中的提示以自定义 AI 生成的内容
+- 修改 `app.py` 中的 `model` , 推荐效果 sonnet > Qwen1.5 72B > deepseek-coder
+
+## Contact
+
+- Issue(建议)
+  ：[![GitHub issues](https://img.shields.io/github/issues/shibing624/agentica.svg)](https://github.com/shibing624/agentica/issues)
+- 邮件我：xuming: [email protected]
+- 微信我： 加我*微信号：xuming624, 备注：姓名-公司-NLP* 进NLP交流群。
+
+<img src="https://github.com/shibing624/weibo-roast/blob/main/docs/wechat.jpeg" width="200" />
+
+<img src="https://github.com/shibing624/weibo-roast/blob/main/docs/wechat_group.jpg" width="200" />
+
+
+## Citation
+
+如果你在研究中使用了`agentica`，请按如下格式引用：
+
+APA:
+
+```
+Xu, M. weibo-roast: Weibo Roast AI (Version 0.0.1) [Computer software]. https://github.com/shibing624/weibo-roast
+```
+
+BibTeX:
+
+```
+@misc{Xu_weibo-roast,
+  title={weibo-roast: Weibo Roast AI},
+  author={Xu Ming},
+  year={2024},
+  howpublished={\url{https://github.com/shibing624/weibo-roast}},
+}
+```
+
+## License
+
+授权协议为 [The Apache License 2.0](/LICENSE)，可免费用做商业用途。请在产品说明中附加`weibo-roast`的链接和授权协议。
+## Contribute
+
+项目代码还很粗糙，如果大家对代码有所改进，欢迎提交回本项目，在提交之前，注意以下两点：
+
+- 在`tests`添加相应的单元测试
+- 使用`python -m pytest`来运行所有单元测试，确保所有单测都是通过的
+
+之后即可提交PR。
+
+## 致谢
+
+- [weibo-crawler](https://github.com/dataabc/weibo-crawler) 
+- [WeiboSuperSpider](https://github.com/Python3Spiders/WeiboSuperSpider) 
+- [agentica](https://github.com/shibing624/agantica)
+- [WeiboRoast](https://github.com/Huanshere/WeiboRoast/tree/main)

ask_llm.py

@@ -0,0 +1,72 @@
+# -*- coding: utf-8 -*-
+"""
+@author:XuMing([email protected])
+@description:
+"""
+
+from agentica import Message
+from agentica import Assistant, DeepseekLLM
+from agentica.tools.file import FileTool
+from loguru import logger
+
+assistant = Assistant(
+    llm=DeepseekLLM(),
+    tools=[FileTool()],
+    add_datetime_to_instructions=True,
+    show_tool_calls=True,
+    read_chat_history=True,
+    debug_mode=False,
+)
+logger.debug(f"assistant loaded, assistant={assistant}")
+
+
+def llm_response(messages, response_json=False):
+    if response_json:
+        llm = DeepseekLLM(response_format={"type": "json_object"})
+    else:
+        llm = DeepseekLLM()
+    if isinstance(messages, str):
+        messages = [Message(role="user", content=messages)]
+    elif isinstance(messages, list):
+        llm_messages = []
+        # If messages are provided, simply use them
+        if messages is not None and len(messages) > 0:
+            for _m in messages:
+                if isinstance(_m, Message):
+                    llm_messages.append(_m)
+                elif isinstance(_m, dict):
+                    llm_messages.append(Message.model_validate(_m))
+        messages = llm_messages
+    return llm.response_stream(messages)
+
+
+def assistant_response(prompt):
+    r = assistant.run(prompt)
+    print(r, "".join(r))
+    return r
+
+
+if __name__ == '__main__':
+    prompt = "一句话介绍alpaca?"
+    r = llm_response(prompt)
+    print(r)
+    for i in r:
+        print(i)
+
+    prompt = """
+按照以下格式，输入待评分的文本，返回敏感度评分结果。
+
+- 响应格式
+用JSON格式返回评分结果。
+
+- 示例
+```json
+{{"sensitive": 1}}
+```
+### 问题
+alpaca是哺乳动物吗?"
+"""
+    print(llm_response(prompt, response_json=True))
+    prompt = "一句话介绍北京"
+    r = assistant_response(prompt)
+    print(r, "".join(r))

example.env

@@ -0,0 +1,7 @@
+LOG_LEVEL=DEBUG
+
+DEEPSEEK_API_KEY=
+MOONSHOT_API_KEY=
+
+OPENAI_API_KEY=
+OPENAI_BASE_URL=