OSPP/feat: Integrate VMind to enable automated insight annotation and enhance report generation pipeline

.gitignore

@@ -8,6 +8,8 @@ data/
 # Workspace
 workspace/
 
+config/
+
 ### Python ###
 # Byte-compiled / optimized / DLL files
 __pycache__/

.vscode/settings.json

@@ -16,5 +16,6 @@
     },
     "files.insertFinalNewline": true,
     "files.trimTrailingWhitespace": true,
-    "editor.formatOnSave": true
+    "editor.formatOnSave": true,
+    "liveServer.settings.port": 5501
 }

app/agent/data_analysis.py

@@ -4,9 +4,23 @@
 from app.config import config
 from app.prompt.visualization import NEXT_STEP_PROMPT, SYSTEM_PROMPT
 from app.tool import Terminate, ToolCollection
+from app.tool.chart_visualization.python_execute import NormalPythonExecute
+# from app.tool.chart_visualization.chart_prepare import VisualizationPrepare
+# from app.tool.chart_visualization.data_visualization import DataVisualization
+# from app.tool.chart_visualization.initial_report_generation import GenerateInitialReport
+# from app.tool.chart_visualization.final_report_generation import GenerateFinalReport
+# from app.tool.chart_visualization.search_report_template import SearchReportTemplate
+# from app.tool.chart_visualization.report_template_generation import ReportTemplateGeneration
+# from app.tool.chart_visualization.initial_information_collection import InitialInformationCollection
 from app.tool.chart_visualization.chart_prepare import VisualizationPrepare
+from app.tool.chart_visualization.select_insights import SelectInsights
+from app.tool.chart_visualization.add_insights import AddInsights
 from app.tool.chart_visualization.data_visualization import DataVisualization
-from app.tool.chart_visualization.python_execute import NormalPythonExecute
+from app.tool.chart_visualization.v2.search_html_library import SearchHtmlLibrary
+from app.tool.chart_visualization.v2.initial_report_generation import GenerateInitialReport
+from app.tool.chart_visualization.v2.report_template_generation import ReportTemplateGeneration
+from app.tool.chart_visualization.v2.final_report_generation import GenerateFinalReport
+from app.tool.chart_visualization.v2.report_beautify import ReportBeautify
 
 
 class DataAnalysis(ToolCallAgent):
@@ -18,7 +32,34 @@ class DataAnalysis(ToolCallAgent):
     """
 
     name: str = "Data_Analysis"
-    description: str = "An analytical agent that utilizes python and data visualization tools to solve diverse data analysis tasks"
+    description: str = """
+    A data science agent specializing in Python-based analytics and advanced visualization techniques
+    for solving complex data analysis challenges.
+
+    Standard Report Generation Workflow:
+    1. Template Preparation:
+       - SearchHtmlLibrary: Identify suitable visualization templates
+       - ReportTemplateGeneration & GenerateInitialReport: Create initial report structure
+
+    2. Visualization Pipeline:
+       - VisualizationPrepare: Configure data for visualization
+       - DataVisualization: Generate interactive charts and graphs
+
+    3. Insight Enhancement:
+       - SelectInsights: Extract key findings from visualizations
+       - AddInsights: Annotate charts with analytical insights
+
+    4. Report Finalization:
+       - GenerateFinalReport: Replace the placeholders with charts
+       - ReportBeautify: Apply professional styling and formatting
+
+    Operational Protocol:
+    - First determine optimal visualization types based on dataset characteristics
+    - Utilize HTML template library to establish report framework
+    - Execute visualization pipeline to create data representations
+    - Enhance each chart with key insights you selected
+    - Assemble final report by embedding enriched visualizations
+    """
 
     system_prompt: str = SYSTEM_PROMPT.format(directory=config.workspace_root)
     next_step_prompt: str = NEXT_STEP_PROMPT
@@ -30,8 +71,15 @@ class DataAnalysis(ToolCallAgent):
     available_tools: ToolCollection = Field(
         default_factory=lambda: ToolCollection(
             NormalPythonExecute(),
+            SearchHtmlLibrary(),
+            ReportTemplateGeneration(),
+            GenerateInitialReport(),
+            GenerateFinalReport(),
+            ReportBeautify(),
+            AddInsights(),
             VisualizationPrepare(),
             DataVisualization(),
+            SelectInsights(),
             Terminate(),
         )
     )

app/prompt/visualization.py

@@ -1,7 +1,33 @@
 SYSTEM_PROMPT = """You are an AI agent designed to data analysis / visualization task. You have various tools at your disposal that you can call upon to efficiently complete complex requests.
 # Note:
 1. The workspace directory is: {directory}; Read / write file in workspace
-2. Generate analysis conclusion report in the end"""
+2. Generate analysis conclusion report in the end
+
+Standard Report Generation Workflow:
+1. Template Preparation:
+    - SearchHtmlLibrary: Identify suitable visualization templates
+    - ReportTemplateGeneration & GenerateInitialReport: Create initial report structure
+
+2. Visualization Pipeline:
+    - VisualizationPrepare: Configure data for visualization
+    - DataVisualization: Generate interactive charts and graphs
+
+3. Insight Enhancement:
+    - SelectInsights: Extract key findings from visualizations
+    - AddInsights: Annotate charts with analytical insights
+
+4. Report Finalization:
+    - GenerateFinalReport: Replace the placeholders with charts
+    - ReportBeautify: Apply professional styling and formatting
+
+Operational Protocol:
+- First determine optimal visualization types based on dataset characteristics
+- Utilize HTML template library to establish report framework
+- Execute visualization pipeline to create data representations
+- Enhance each chart with key insights you selected
+- Assemble final report by embedding enriched visualizations
+
+"""
 
 NEXT_STEP_PROMPT = """Based on user needs, break down the problem and use different tools step by step to solve it.
 # Note

app/tool/chart_visualization/__init__.py

@@ -1,6 +1,3 @@
 from app.tool.chart_visualization.chart_prepare import VisualizationPrepare
 from app.tool.chart_visualization.data_visualization import DataVisualization
 from app.tool.chart_visualization.python_execute import NormalPythonExecute
-
-
-__all__ = ["DataVisualization", "VisualizationPrepare", "NormalPythonExecute"]

app/tool/chart_visualization/add_insights.py

@@ -0,0 +1,228 @@
+import sys
+import asyncio
+import json
+import os
+print(os.path.dirname(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))))
+sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))))
+
+from typing import Any, Hashable
+
+import pandas as pd
+from pydantic import Field, model_validator
+
+from app.config import config
+from app.llm import LLM
+from app.logger import logger
+from app.tool.base import BaseTool
+
+
+class AddInsights(BaseTool):
+    name: str = "add_insights"
+    description: str = (
+        "Enhances charts by adding insights markers and annotations "
+        "using JSON data generated by the insights_selection tool. "
+        "This creates the final annotated visualization output."
+    )
+
+    parameters: dict = {
+        "type": "object",
+        "properties": {
+            "json_path": {
+                "type": "string",
+                "description": """Path to the JSON file generated by insights_selection tool.
+Contains chart insights data in format:
+{
+  "chartPath": string,
+  "insights_id": number[]
+}""",
+            },
+            "output_type": {
+                "type": "string",
+                "description": "Visualization output format selection",
+                "default": "html",
+                "enum": [
+                    "png",    # Static image format
+                    "html"    # Interactive web format (recommended)
+                ],
+            },
+        },
+        "required": ["json_path"],
+    }
+    llm: LLM = Field(default_factory=LLM, description="Language model instance")
+
+    @model_validator(mode="after")
+    def initialize_llm(self):
+        """Initialize llm with default settings if not provided."""
+        if self.llm is None or not isinstance(self.llm, LLM):
+            self.llm = LLM(config_name=self.name.lower())
+        return self
+
+    def load_chart_with_css(self, chart_path):
+        # 读取 HTML 文件
+        with open(chart_path, 'r', encoding='utf-8') as f:
+            html_content = f.read()
+        html_content = html_content.replace('`', "'")
+
+        # 在 <head> 里插入 CSS
+        css = """
+        <style>
+            body, html {
+                margin: 0;
+                padding: 0;
+                height: 100%;
+                overflow: hidden;
+            }
+            #chart-container {
+                width: 100%;
+                height: 100%;
+            }
+        </style>
+        """
+
+        # 如果原文件没有 <head>，直接插入到最前面
+        if "<head>" in html_content:
+            html_content = html_content.replace("<head>", "<head>" + css)
+        else:
+            html_content = css + html_content
+
+        with open(chart_path, 'w', encoding='utf-8') as f:
+            f.write(html_content)
+
+    def get_file_path(
+        self,
+        json_info: list[dict[str, str]],
+        path_str: str,
+        directory: str = None,
+    ) -> list[str]:
+        res = []
+        for item in json_info:
+            if os.path.exists(item[path_str]):
+                res.append(item[path_str])
+            elif os.path.exists(
+                os.path.join(f"{directory or config.workspace_root}", item[path_str])
+            ):
+                res.append(
+                    os.path.join(
+                        f"{directory or config.workspace_root}", item[path_str]
+                    )
+                )
+            else:
+                raise Exception(f"No such file or directory: {item[path_str]}")
+        return res
+
+    async def add_insights(
+        self, json_info: list[dict[str, str]], output_type: str
+    ) -> str:
+        data_list = []
+        chart_file_path = self.get_file_path(
+            json_info, "chartPath", os.path.join(config.workspace_root, "visualization")
+        )
+        for index, item in enumerate(json_info):
+            if "insights_id" in item:
+                data_list.append(
+                    {
+                        "file_name": os.path.basename(chart_file_path[index]).replace(
+                            f".{output_type}", ""
+                        ),
+                        "insights_id": item["insights_id"],
+                    }
+                )
+        tasks = [
+            self.invoke_vmind(
+                insights_id=item["insights_id"],
+                file_name=item["file_name"],
+                output_type=output_type,
+                task_type="insight",
+            )
+            for item in data_list
+        ]
+        results = await asyncio.gather(*tasks)
+        error_list = []
+        success_list = []
+        for index, result in enumerate(results):
+            chart_path = chart_file_path[index]
+            if "error" in result and "chart_path" not in result:
+                error_list.append(f"Error in {chart_path}: {result['error']}")
+            else:
+                success_list.append(chart_path)
+                self.load_chart_with_css(chart_path)
+
+        success_template = (
+            f"# Charts Update with Insights\n{','.join(success_list)}"
+            if len(success_list) > 0
+            else ""
+        )
+        if len(error_list) > 0:
+            return {
+                "observation": f"# Error in chart insights:{'\n'.join(error_list)}\n{success_template}",
+                "success": False,
+            }
+        else:
+            return {"observation": f"{success_template}"}
+
+    async def execute(
+        self,
+        json_path: str,
+        output_type: str | None = "html",
+        tool_type: str | None = "visualization",
+        language: str | None = "en",
+    ) -> str:
+        try:
+            logger.info(f"📈 data_visualization with {json_path} in: {tool_type} ")
+            with open(json_path, "r", encoding="utf-8") as file:
+                json_info = json.load(file)
+                return await self.add_insights(json_info, output_type)
+        except Exception as e:
+            return {
+                "observation": f"Error: {e}",
+                "success": False,
+            }
+
+    async def invoke_vmind(
+        self,
+        file_name: str,
+        output_type: str,
+        task_type: str,
+        insights_id: list[str] = None,
+        dict_data: list[dict[Hashable, Any]] = None,
+        chart_description: str = None,
+        language: str = "en",
+    ):
+        llm_config = {
+            "base_url": self.llm.base_url,
+            "model": self.llm.model,
+            "api_key": self.llm.api_key,
+        }
+        vmind_params = {
+            "llm_config": llm_config,
+            "user_prompt": chart_description,
+            "dataset": dict_data,
+            "file_name": file_name,
+            "output_type": output_type,
+            "insights_id": insights_id,
+            "task_type": task_type,
+            "directory": str(config.workspace_root),
+            "language": language,
+        }
+
+        process = await asyncio.create_subprocess_exec(
+            "npx",
+            "ts-node",
+            "src/chartVisualize.ts",
+            stdin=asyncio.subprocess.PIPE,
+            stdout=asyncio.subprocess.PIPE,
+            stderr=asyncio.subprocess.PIPE,
+            cwd=os.path.dirname(__file__),
+        )
+        input_json = json.dumps(vmind_params, ensure_ascii=False).encode("utf-8")
+        try:
+            stdout, stderr = await process.communicate(input_json)
+            stdout_str = stdout.decode("utf-8")
+            stderr_str = stderr.decode("utf-8")
+            if process.returncode == 0:
+                return json.loads(stdout_str)
+            else:
+                return {"error": f"Node.js Error: {stderr_str}"}
+        except Exception as e:
+            return {"error": f"Subprocess Error: {str(e)}"}
+