Add notebook executor as service function and add codeact agent.

README.md

@@ -167,6 +167,8 @@ the following libraries.
   - <img src="https://img.alicdn.com/imgextra/i3/O1CN01SFL0Gu26nrQBFKXFR_!!6000000007707-2-tps-500-500.png" alt="new" width="30" height="30"/>[Conversation with Customized Tools](https://github.com/modelscope/agentscope/blob/main/examples/conversation_with_customized_services/)
   - <img src="https://img.alicdn.com/imgextra/i3/O1CN01SFL0Gu26nrQBFKXFR_!!6000000007707-2-tps-500-500.png" alt="new" width="30" height="30"/>[Mixture of Agents Algorithm](https://github.com/modelscope/agentscope/blob/main/examples/conversation_mixture_of_agents/)
   - <img src="https://img.alicdn.com/imgextra/i3/O1CN01SFL0Gu26nrQBFKXFR_!!6000000007707-2-tps-500-500.png" alt="new" width="30" height="30"/>[Conversation in Stream Mode](https://github.com/modelscope/agentscope/blob/main/examples/conversation_in_stream_mode/)
+  - <img src="https://img.alicdn.com/imgextra/i3/O1CN01SFL0Gu26nrQBFKXFR_!!6000000007707-2-tps-500-500.png" alt="new" width="30" height="30"/>[Conversation with CodeAct Agent](https://github.com/modelscope/agentscope/blob/main/examples/conversation_with_codeact_agent/)
+
 
 - Game
   - [Gomoku](https://github.com/modelscope/agentscope/blob/main/examples/game_gomoku)

README_ZH.md

@@ -153,10 +153,14 @@ AgentScope支持使用以下库快速部署本地模型服务。
   - [通过对话查询SQL信息](./examples/conversation_nl2sql/)
   - [与RAG智能体对话](./examples/conversation_with_RAG_agents)
   - <img src="https://img.alicdn.com/imgextra/i3/O1CN01SFL0Gu26nrQBFKXFR_!!6000000007707-2-tps-500-500.png" alt="new" width="30" height="30"/>[与gpt-4o模型对话](./examples/conversation_with_gpt-4o)
+  - <img src="https://img.alicdn.com/imgextra/i3/O1CN01SFL0Gu26nrQBFKXFR_!!6000000007707-2-tps-500-500.png" alt="new" width="30" height="30"/>[与自定义服务对话](./examples/conversation_with_customized_services/)
+
   - <img src="https://img.alicdn.com/imgextra/i3/O1CN01SFL0Gu26nrQBFKXFR_!!6000000007707-2-tps-500-500.png" alt="new" width="30" height="30"/>[与SoftWare Engineering智能体对话](./examples/conversation_with_swe-agent/)
   - <img src="https://img.alicdn.com/imgextra/i3/O1CN01SFL0Gu26nrQBFKXFR_!!6000000007707-2-tps-500-500.png" alt="new" width="30" height="30"/>[自定义工具函数](./examples/conversation_with_customized_services/)
   - <img src="https://img.alicdn.com/imgextra/i3/O1CN01SFL0Gu26nrQBFKXFR_!!6000000007707-2-tps-500-500.png" alt="new" width="30" height="30"/>[Mixture of Agents算法](https://github.com/modelscope/agentscope/blob/main/examples/conversation_mixture_of_agents/)
   - <img src="https://img.alicdn.com/imgextra/i3/O1CN01SFL0Gu26nrQBFKXFR_!!6000000007707-2-tps-500-500.png" alt="new" width="30" height="30"/>[流式对话](https://github.com/modelscope/agentscope/blob/main/examples/conversation_in_stream_mode/)
+  - <img src="https://img.alicdn.com/imgextra/i3/O1CN01SFL0Gu26nrQBFKXFR_!!6000000007707-2-tps-500-500.png" alt="new" width="30" height="30"/>[与CodeAct智能体对话](https://github.com/modelscope/agentscope/blob/main/examples/conversation_with_codeact_agent/)
+
 
 - 游戏
   - [五子棋](./examples/game_gomoku)

examples/conversation_with_codeact_agent/codeact_agent.py

@@ -0,0 +1,166 @@
+# -*- coding: utf-8 -*-
+# pylint: disable=C0301
+"""An agent class that implements the CodeAct agent.
+This agent can execute code interactively as actions.
+More details can be found at the paper of codeact agent
+https://arxiv.org/abs/2402.01030
+and the original repo of codeact https://github.com/xingyaoww/code-act
+"""
+from agentscope.agents import AgentBase
+from agentscope.message import Msg
+from agentscope.service import (
+    ServiceResponse,
+    ServiceExecStatus,
+    NoteBookExecutor,
+)
+from agentscope.parsers import RegexTaggedContentParser
+
+SYSTEM_MESSAGE = """system
+You are a helpful assistant that gives helpful, detailed, and polite answers to the user's questions.
+You should interact with the interactive Python (Jupyter Notebook) environment and receive the corresponding output when needed. The code written by assistant should be enclosed using <execute> tag, for example: <execute> print('Hello World!') </execute>.
+You should attempt fewer things at a time instead of putting too much code in one <execute> block. You can install packages through PIP by <execute> !pip install [package needed] </execute> and should always import packages and define variables before starting to use them.
+You should stop <execute> and provide an answer when they have already obtained the answer from the execution result. Whenever possible, execute the code for the user using <execute> instead of providing it.
+Your response should be concise, but do express their thoughts. Always write the code in <execute> block to execute them.
+You should not ask for the user's input unless necessary. Solve the task on your own and leave no unanswered questions behind.
+You should do every thing by your self.
+"""  # noqa
+
+EXAMPLE_MESSAGE = """
+Additionally, you are provided with the following code available:
+{example_code}
+The above code is already available in your interactive Python (Jupyter Notebook) environment, allowing you to directly use these variables and functions without needing to redeclare them.
+"""  # noqa
+
+
+class CodeActAgent(AgentBase):
+    """
+    The implementation of CodeAct-agent.
+    The agent can execute code interactively as actions.
+    More details can be found at the paper of codeact agent
+    https://arxiv.org/abs/2402.01030
+    and the original repo of codeact https://github.com/xingyaoww/code-act
+    """
+
+    def __init__(
+        self,
+        name: str,
+        model_config_name: str,
+        example_code: str = "",
+    ) -> None:
+        """
+        Initialize the CodeActAgent.
+        Args:
+            name(`str`):
+                The name of the agent.
+            model_config_name(`str`):
+                The name of the model configuration.
+            example_code(Optional`str`):
+                The example code to be executed bewfore the interaction.
+                You can import reference libs, define variables
+                and functions to be called. For example:
+
+                    ```python
+                    from agentscope.service import bing_search
+                    import os
+
+                    api_key = "{YOUR_BING_API_KEY}"
+
+                    def search(question: str):
+                        return bing_search(question, api_key=api_key, num_results=3).content
+                    ```
+
+        """  # noqa
+        super().__init__(
+            name=name,
+            model_config_name=model_config_name,
+        )
+        self.n_max_executions = 5
+        self.example_code = example_code
+        self.code_executor = NoteBookExecutor()
+
+        sys_msg = Msg(name="system", role="system", content=SYSTEM_MESSAGE)
+        example_msg = Msg(
+            name="user",
+            role="user",
+            content=EXAMPLE_MESSAGE.format(example_code=self.example_code),
+        )
+
+        self.memory.add(sys_msg)
+
+        if self.example_code != "":
+            code_execution_result = self.code_executor.run_code_on_notebook(
+                self.example_code,
+            )
+            code_exec_msg = self.handle_code_result(
+                code_execution_result,
+                "Example Code excuted: ",
+            )
+            self.memory.add(example_msg)
+            self.memory.add(code_exec_msg)
+            self.speak(code_exec_msg)
+
+        self.parser = RegexTaggedContentParser(try_parse_json=False)
+
+    def handle_code_result(
+        self,
+        code_execution_result: ServiceResponse,
+        content_pre_sring: str = "",
+    ) -> Msg:
+        """return the message from code result"""
+        code_exec_content = content_pre_sring
+        if code_execution_result.status == ServiceExecStatus.SUCCESS:
+            code_exec_content += "Excution Successful:\n"
+        else:
+            code_exec_content += "Excution Failed:\n"
+        code_exec_content += "Execution Output:\n" + str(
+            code_execution_result.content,
+        )
+        return Msg(name="user", role="user", content=code_exec_content)
+
+    def reply(self, x: Msg = None) -> Msg:
+        """The reply function that implements the codeact agent."""
+
+        self.memory.add(x)
+
+        excution_count = 0
+        while (
+            self.memory.get_memory(1)[-1].role == "user"
+            and excution_count < self.n_max_executions
+        ):
+            prompt = self.model.format(self.memory.get_memory())
+            model_res = self.model(prompt)
+            msg_res = Msg(
+                name=self.name,
+                content=model_res.text,
+                role="assistant",
+            )
+            self.memory.add(msg_res)
+            self.speak(msg_res)
+            res = self.parser.parse(model_res)
+            code = res.parsed.get("execute")
+            if code is not None:
+                code = code.strip()
+                code_execution_result = (
+                    self.code_executor.run_code_on_notebook(code)
+                )
+                excution_count += 1
+                code_exec_msg = self.handle_code_result(code_execution_result)
+                self.memory.add(code_exec_msg)
+                self.speak(code_exec_msg)
+
+        if excution_count == self.n_max_executions:
+            assert self.memory.get_memory(1)[-1].role == "user"
+            code_max_exec_msg = Msg(
+                name="assitant",
+                role="assistant",
+                content=(
+                    "I have reached the maximum number "
+                    f"of executions ({self.n_max_executions=}). "
+                    "Can you assist me or ask me another question?"
+                ),
+            )
+            self.memory.add(code_max_exec_msg)
+            self.speak(code_max_exec_msg)
+            return code_max_exec_msg
+
+        return msg_res

examples/conversation_with_codeact_agent/codeact_agent_example_modeling.ipynb

@@ -0,0 +1,201 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Conversation with CodeAct Agent\n",
+    "\n",
+    "CodeAct agent is an agent that not only chats but also writes and executes Python code for you.\n",
+    "More details can be found in the project's related [github repo](https://github.com/xingyaoww/code-act). In the example here, we implement the CodeAct agent, and provide a simple example of how to use the CodeAct agent.\n",
+    "\n",
+    "## Prerequisites\n",
+    "\n",
+    "- Follow [READMD.md](https://github.com/modelscope/agentscope) to install AgentScope. We require the lastest version, so you should build from source by running `pip install -e .` instead of intalling from pypi. \n",
+    "- Prepare a model configuration. AgentScope supports both local deployed model services (CPU or GPU) and third-party services. More details and example model configurations please refer to our [tutorial](https://modelscope.github.io/agentscope/en/tutorial/203-model.html).\n",
+    "\n",
+    "## Note\n",
+    "- The example is tested with the following models. For other models, you may need to adjust the prompt.\n",
+    "    - qwen-max"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "YOUR_MODEL_CONFIGURATION_NAME = \"{YOUR_MODEL_CONFIGURATION_NAME}\"\n",
+    "\n",
+    "YOUR_MODEL_CONFIGURATION = {\n",
+    "    \"model_type\": \"xxx\", \n",
+    "    \"config_name\": YOUR_MODEL_CONFIGURATION_NAME\n",
+    "    \n",
+    "    # ...\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Step 1: Initalize the CodeAct-agent\n",
+    "\n",
+    "Here we load the CodeAct agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from codeact_agent import CodeActAgent\n",
+    "\n",
+    "import agentscope\n",
+    "\n",
+    "agentscope.init(model_configs=YOUR_MODEL_CONFIGURATION)\n",
+    "\n",
+    "import nest_asyncio\n",
+    "nest_asyncio.apply()\n",
+    "agent = CodeActAgent(\n",
+    "    name=\"assistant\",\n",
+    "    model_config_name=YOUR_MODEL_CONFIGURATION_NAME,\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "###Step 2: Ask the CodeAct-agent to execute tasks\n",
+    "\n",
+    "Here, we ask the CodeAct-agent to implement a statistical simulation and modeling procedure."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2024-05-16 19:48:01.620 | INFO     | agentscope.models.model:__init__:201 - Initialize model by configuration [dashscope_chat-qwen-max]\n",
+      "2024-05-16 19:48:01.624 | INFO     | agentscope.utils.monitor:register:417 - Register metric [qwen-max.call_counter] to SqliteMonitor with unit [times] and quota [None]\n",
+      "2024-05-16 19:48:01.627 | INFO     | agentscope.utils.monitor:register:417 - Register metric [qwen-max.prompt_tokens] to SqliteMonitor with unit [token] and quota [None]\n",
+      "2024-05-16 19:48:01.630 | INFO     | agentscope.utils.monitor:register:417 - Register metric [qwen-max.completion_tokens] to SqliteMonitor with unit [token] and quota [None]\n",
+      "2024-05-16 19:48:01.632 | INFO     | agentscope.utils.monitor:register:417 - Register metric [qwen-max.total_tokens] to SqliteMonitor with unit [token] and quota [None]\n",
+      "user: Given y = 0.9x + 6.1, randomly sample data points as pairs of (x, y). Then fit a linear regression on the sampled data and plot the points, fitted line, and ground-truth line.\n",
+      "assistant: To accomplish this task, I will follow these steps:\n",
+      "\n",
+      "1. Generate random `x` values within a reasonable range.\n",
+      "2. Use the equation `y = 0.9x + 6.1` to compute the corresponding `y` values for each `x`.\n",
+      "3. Add some noise to the `y` values to simulate real-world data variability.\n",
+      "4. Split the data into training and testing sets (though for simplicity and since you didn't specify, we'll just use all the data for fitting).\n",
+      "5. Fit a linear regression model on the generated data.\n",
+      "6. Plot the original data points, the fitted line from the regression, and the ground-truth line.\n",
+      "\n",
+      "Let's start by generating the data points and fitting the regression model.\n",
+      "\n",
+      "[execute]\n",
+      "import numpy as np\n",
+      "import matplotlib.pyplot as plt\n",
+      "from sklearn.linear_model import LinearRegression\n",
+      "\n",
+      "# Set a seed for reproducibility\n",
+      "np.random.seed(42)\n",
+      "\n",
+      "# Generate random x values between 0 and 100\n",
+      "x_values = np.random.rand(100) * 100\n",
+      "\n",
+      "# Compute the corresponding y values without noise\n",
+      "y_values_ground_truth = 0.9 * x_values + 6.1\n",
+      "\n",
+      "# Add some noise to y values\n",
+      "noise = np.random.normal(0, 10, size=x_values.shape)\n",
+      "y_values_noisy = y_values_ground_truth + noise\n",
+      "\n",
+      "# Combine into a single dataset\n",
+      "data = np.column_stack((x_values, y_values_noisy))\n",
+      "\n",
+      "# Fit a linear regression model\n",
+      "model = LinearRegression()\n",
+      "model.fit(data[:, 0].reshape(-1, 1), data[:, 1])\n",
+      "\n",
+      "# Prepare to plot\n",
+      "plt.figure(figsize=(10, 6))\n",
+      "[/execute]\n",
+      "user: Execution Output:\n",
+      "['<Figure size 1000x600 with 0 Axes>', 'Unsupported display type']\n",
+      "assistant: It seems there was an issue with displaying the plot directly here. No worries, I will still generate the plot and save it to a file instead, which you can view separately. Let me adjust the code to save the plot as an image file.\n",
+      "\n",
+      "[execute]\n",
+      "# Plotting the data points, fitted line, and ground-truth line\n",
+      "plt.scatter(data[:, 0], data[:, 1], label='Sampled Data', color='blue')\n",
+      "plt.plot(data[:, 0], model.predict(data[:, 0].reshape(-1, 1)), label='Fitted Line', color='red', linestyle='--')\n",
+      "plt.plot(data[:, 0], y_values_ground_truth, label='Ground-Truth Line', color='green')\n",
+      "\n",
+      "plt.title('Linear Regression on Sampled Data')\n",
+      "plt.xlabel('X')\n",
+      "plt.ylabel('Y')\n",
+      "plt.legend()\n",
+      "plt.grid(True)\n",
+      "\n",
+      "# Save the plot to a file\n",
+      "plt.savefig('linear_regression_plot.png')\n",
+      "plt.close()\n",
+      "[/execute]\n",
+      "\n",
+      "The plot has been saved as 'linear_regression_plot.png'. You can view this file to see the sampled data points, the fitted line from the linear regression, and the ground-truth line based on the equation `y = 0.9x + 6.1`. If you need further analysis or have any other requests, feel free to ask!\n",
+      "user: Execution Output:\n",
+      "[]\n",
+      "assistant: It appears the output confirmation was suppressed in this environment, but typically, when running the code locally or in a supported environment, you would see a message indicating the plot was successfully saved to 'linear_regression_plot.png'.\n",
+      "\n",
+      "Since we cannot directly view the saved file here, trust that the file has been created with the following components:\n",
+      "\n",
+      "- **Sampled Data Points**: Represented as blue dots, scattered according to the generated `x` values and the noisy `y` values.\n",
+      "- **Fitted Line**: Shown as a red dashed line, representing the linear regression model's prediction based on the sampled data.\n",
+      "- **Ground-Truth Line**: Displayed as a green line, illustrating the true relationship defined by `y = 0.9x + 6.1`.\n",
+      "\n",
+      "If you need further assistance or another operation, such as analyzing the quality of the fit or re-running the process with different parameters, please let me know!\n"
+     ]
+    }
+   ],
+   "source": [
+    "from loguru import logger\n",
+    "from agentscope.message import Msg\n",
+    "\n",
+    "mss = Msg(\n",
+    "    name=\"user\", \n",
+    "    content=\"Given y = 0.9x + 6.1, randomly sample data points as pairs of (x, y). Then fit a linear regression on the sampled data and plot the points, fitted line, and ground-truth line.\", \n",
+    "    role=\"user\"\n",
+    ")\n",
+    "logger.chat(mss)\n",
+    "answer_mss1 = agent(mss)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "datajuicer",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}