Merge pull request #1 from 666haiwen/feat/data_visualization_hack_czx
Feat: Update chart generation tools in data analysis
This commit is contained in:
ZJU_czx
@@ -1,17 +1,17 @@
|
||||
from pydantic import Field
|
||||
|
||||
from app.agent.browser import BrowserAgent
|
||||
from app.agent.toolcall import ToolCallAgent
|
||||
from app.config import config
|
||||
from app.prompt.browser import NEXT_STEP_PROMPT as BROWSER_NEXT_STEP_PROMPT
|
||||
from app.prompt.visualization import NEXT_STEP_PROMPT, SYSTEM_PROMPT
|
||||
from app.tool import Terminate, ToolCollection
|
||||
from app.tool.browser_use_tool import BrowserUseTool
|
||||
from app.tool.chart_visualization.chart_visualization import ChartVisualization
|
||||
from app.tool.chart_visualization.normal_python_execute import NormalPythonExecute
|
||||
from app.tool.chart_visualization.data_analysis_python import DataAnalysisPythonExecute
|
||||
from app.tool.chart_visualization.chart_prepare import (
|
||||
VisualizationPrepare,
|
||||
)
|
||||
|
||||
|
||||
class DataAnalysis(BrowserAgent):
|
||||
class DataAnalysis(ToolCallAgent):
|
||||
"""
|
||||
A data analysis agent that uses planning to solve various data analysis tasks.
|
||||
|
||||
@@ -34,34 +34,8 @@ class DataAnalysis(BrowserAgent):
|
||||
available_tools: ToolCollection = Field(
|
||||
default_factory=lambda: ToolCollection(
|
||||
NormalPythonExecute(),
|
||||
DataAnalysisPythonExecute(),
|
||||
VisualizationPrepare(),
|
||||
ChartVisualization(),
|
||||
BrowserUseTool(),
|
||||
Terminate(),
|
||||
)
|
||||
)
|
||||
|
||||
async def think(self) -> bool:
|
||||
"""Process current state and decide next actions with appropriate context."""
|
||||
# Store original prompt
|
||||
original_prompt = self.next_step_prompt
|
||||
|
||||
# Only check recent messages (last 3) for browser activity
|
||||
recent_messages = self.memory.messages[-3:] if self.memory.messages else []
|
||||
browser_in_use = any(
|
||||
"browser_use" in msg.content.lower()
|
||||
for msg in recent_messages
|
||||
if hasattr(msg, "content") and isinstance(msg.content, str)
|
||||
)
|
||||
|
||||
if browser_in_use:
|
||||
# Override with browser-specific prompt temporarily to get browser context
|
||||
self.next_step_prompt = BROWSER_NEXT_STEP_PROMPT
|
||||
|
||||
# Call parent's think method
|
||||
result = await super().think()
|
||||
|
||||
# Restore original prompt
|
||||
self.next_step_prompt = original_prompt
|
||||
|
||||
return result
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
SYSTEM_PROMPT = (
|
||||
"You are an AI agent designed to data analysis and data visualization task. You have various tools at your disposal that you can call upon to efficiently complete complex requests."
|
||||
"The initial directory is: {directory}"
|
||||
"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."
|
||||
"The workspace directory is: {directory}"
|
||||
)
|
||||
|
||||
NEXT_STEP_PROMPT = """
|
||||
Based on user needs, proactively select the most appropriate tool or combination of tools. For complex tasks, you can break down the problem and use different tools step by step to solve it. After using each tool, clearly explain the execution results and suggest the next steps.
|
||||
Based on user needs, break down the problem and use different tools step by step to solve it. Each step select the most appropriate tool proactively(ONLY ONE). After using each tool, clearly explain the execution results and suggest the next steps.
|
||||
"""
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
from app.tool.chart_visualization.chart_visualization import ChartVisualization
|
||||
from app.tool.chart_visualization.data_analysis_python import DataAnalysisPythonExecute
|
||||
from app.tool.chart_visualization.chart_prepare import VisualizationPrepare
|
||||
from app.tool.chart_visualization.normal_python_execute import NormalPythonExecute
|
||||
|
||||
__all__ = ["ChartVisualization", "DataAnalysisPythonExecute", "NormalPythonExecute"]
|
||||
__all__ = ["ChartVisualization", "VisualizationPrepare", "NormalPythonExecute"]
|
||||
|
||||
@@ -0,0 +1,31 @@
|
||||
from app.tool.python_execute import PythonExecute
|
||||
|
||||
|
||||
class VisualizationPrepare(PythonExecute):
|
||||
"""A tool for Chart Generation Preparation"""
|
||||
|
||||
name: str = "visualization_preparation"
|
||||
description: str = (
|
||||
"Using Python code to Generates metadata of data_visualization tool. Outputs: 1) Cleaned CSV data files 2) JSON info with csv path and visualization description."
|
||||
)
|
||||
parameters: dict = {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": """Python code template EXCLUSIVELY for visualization prepare. Must Contains:
|
||||
1. Data loading logic (handle dataframe/dict/file/url/json/web crawler)
|
||||
2. Csv Data and chart description generate
|
||||
2.1 Csv data (The data you want to visulazation, cleaning / transform from origin data, saved in .csv)
|
||||
2.2 Chart description of csv data (The chart title or description should be concise and clear. Examples: 'Product sales distribution', 'Monthly revenue trend'.)
|
||||
3. Save information in json file.( format: {"csvFilePath": string, "chartTitle": string}[])
|
||||
4. Json file saving with path print: print(json_path)
|
||||
# Note
|
||||
1. You can generate one or multiple csv data with different visualization needs.
|
||||
2. Make each chart data esay, clean and different.
|
||||
3. save/read in utf-8
|
||||
""",
|
||||
},
|
||||
},
|
||||
"required": ["code"],
|
||||
}
|
||||
@@ -1,8 +1,6 @@
|
||||
import subprocess
|
||||
import json
|
||||
import base64
|
||||
import asyncio
|
||||
import pandas as pd
|
||||
import aiofiles
|
||||
import os
|
||||
from typing import Any, Hashable
|
||||
from pydantic import Field, model_validator
|
||||
@@ -10,23 +8,20 @@ from pydantic import Field, model_validator
|
||||
from app.llm import LLM
|
||||
from app.tool.base import BaseTool
|
||||
from app.logger import logger
|
||||
from app.config import config
|
||||
|
||||
|
||||
class ChartVisualization(BaseTool):
|
||||
name: str = "generate_data_visualization"
|
||||
description: str = """Visualize a statistical chart using csv data and chart description. The tool accepts local csv data file path and description of the chart, and output a chart in png or html.
|
||||
Note: Each tool call generates only one single chart.
|
||||
"""
|
||||
name: str = "data_visualization"
|
||||
description: str = (
|
||||
"""Visualize statistical chart with JSON info from visualization_preparation tool. Outputs: 1) Charts (png/html) 2) Charts Insights (.md)(Optional)."""
|
||||
)
|
||||
parameters: dict = {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"csv_path": {
|
||||
"json_path": {
|
||||
"type": "string",
|
||||
"description": """file path of csv data with ".csv" in the end""",
|
||||
},
|
||||
"chart_description": {
|
||||
"type": "string",
|
||||
"description": "The chart title or description should be concise and clear. Examples: 'Product sales distribution', 'Monthly revenue trend'.",
|
||||
"description": """file path of json info with ".json" in the end""",
|
||||
},
|
||||
"output_type": {
|
||||
"description": "Rendering format (html=interactive)",
|
||||
@@ -35,7 +30,7 @@ Note: Each tool call generates only one single chart.
|
||||
"enum": ["png", "html"],
|
||||
},
|
||||
},
|
||||
"required": ["code", "chart_description"],
|
||||
"required": ["code"],
|
||||
}
|
||||
llm: LLM = Field(default_factory=LLM, description="Language model instance")
|
||||
|
||||
@@ -46,40 +41,86 @@ Note: Each tool call generates only one single chart.
|
||||
self.llm = LLM(config_name=self.name.lower())
|
||||
return self
|
||||
|
||||
async def execute(
|
||||
self, csv_path: str, chart_description: str, output_type: str
|
||||
) -> str:
|
||||
logger.info(
|
||||
f"📈 Chart Generation with data and description: {chart_description} with {csv_path} "
|
||||
)
|
||||
def get_csv_path(self, json_info: list[dict[str, str]]) -> list[str]:
|
||||
res = []
|
||||
for item in json_info:
|
||||
if os.path.exists(item["csvFilePath"]):
|
||||
res.append(item["csvFilePath"])
|
||||
elif os.path.exists(
|
||||
os.path.join(f"{config.workspace_root}", item["csvFilePath"])
|
||||
):
|
||||
res.append(
|
||||
os.path.join(f"{config.workspace_root}", item["csvFilePath"])
|
||||
)
|
||||
else:
|
||||
raise Exception(f"No such file or directory: {item["csvFilePath"]}")
|
||||
return res
|
||||
|
||||
def success_output_template(self, result: list[dict[str, str]]) -> str:
|
||||
content = ""
|
||||
if len(result) == 0:
|
||||
return "Is EMPTY!"
|
||||
for item in result:
|
||||
content += f"""## {item["title"]}\nChart saved in: {item["chart_path"]}"""
|
||||
if "insight_path" in item and item["insight_path"]:
|
||||
content += f"""\nChart insights saved in {item["insight_path"]}\n"""
|
||||
else:
|
||||
content += "\n"
|
||||
return f"Chart Generated Successful! Detail is below:\n{content}"
|
||||
|
||||
async def execute(self, json_path: str, output_type: str) -> str:
|
||||
logger.info(f"📈 Chart Generation with json path: {json_path} ")
|
||||
try:
|
||||
df = pd.read_csv(csv_path)
|
||||
df = df.astype(object)
|
||||
df = df.where(pd.notnull(df), None)
|
||||
data_dict_list = df.to_json(orient="records", force_ascii=False)
|
||||
result = await self.invoke_vmind(
|
||||
data_dict_list, chart_description, output_type
|
||||
)
|
||||
if "error" in result:
|
||||
with open(json_path, "r", encoding="utf-8") as file:
|
||||
json_info = json.load(file)
|
||||
data_list = []
|
||||
csv_file_path = self.get_csv_path(json_info)
|
||||
for index, item in enumerate(json_info):
|
||||
df = pd.read_csv(csv_file_path[index], encoding="utf-8")
|
||||
df = df.astype(object)
|
||||
df = df.where(pd.notnull(df), None)
|
||||
data_dict_list = df.to_json(orient="records", force_ascii=False)
|
||||
|
||||
data_list.append(
|
||||
{
|
||||
"file_name": os.path.basename(csv_file_path[index]).replace(
|
||||
".csv", ""
|
||||
),
|
||||
"dict_data": data_dict_list,
|
||||
"chartTitle": item["chartTitle"],
|
||||
}
|
||||
)
|
||||
tasks = [
|
||||
self.invoke_vmind(
|
||||
item["dict_data"],
|
||||
item["chartTitle"],
|
||||
item["file_name"],
|
||||
output_type,
|
||||
)
|
||||
for item in data_list
|
||||
]
|
||||
|
||||
results = await asyncio.gather(*tasks)
|
||||
error_list = []
|
||||
success_list = []
|
||||
for index, result in enumerate(results):
|
||||
csv_path = csv_file_path[index]
|
||||
if "error" in result and "chart_path" not in result:
|
||||
error_list.append(f"Error in {csv_path}: {result["error"]}")
|
||||
else:
|
||||
success_list.append(
|
||||
{
|
||||
**result,
|
||||
"title": json_info[index]["chartTitle"],
|
||||
}
|
||||
)
|
||||
if len(error_list) > 0:
|
||||
return {
|
||||
"observation": f"Error: {result["error"]}",
|
||||
"observation": f"# Error chart generated{'\n'.join(error_list)}\n{self.success_output_template(success_list)}",
|
||||
"success": False,
|
||||
}
|
||||
chart_file_path = csv_path.replace(".csv", f".{output_type}")
|
||||
while os.path.exists(chart_file_path):
|
||||
chart_file_path = chart_file_path.replace(
|
||||
f".{output_type}", f"_new.{output_type}"
|
||||
)
|
||||
if output_type == "png":
|
||||
byte_data = base64.b64decode(result["res"])
|
||||
async with aiofiles.open(chart_file_path, "wb") as file:
|
||||
await file.write(byte_data)
|
||||
else:
|
||||
async with aiofiles.open(
|
||||
chart_file_path, "w", encoding="utf-8"
|
||||
) as file:
|
||||
await file.write(result["res"])
|
||||
return {"observation": f"chart successfully saved to {chart_file_path}"}
|
||||
return {"observation": f"{self.success_output_template(success_list)}"}
|
||||
except Exception as e:
|
||||
return {
|
||||
"observation": f"Error: {e}",
|
||||
@@ -90,6 +131,7 @@ Note: Each tool call generates only one single chart.
|
||||
self,
|
||||
dict_data: list[dict[Hashable, Any]],
|
||||
chart_description: str,
|
||||
file_name: str,
|
||||
output_type: str,
|
||||
):
|
||||
llm_config = {
|
||||
@@ -102,16 +144,27 @@ Note: Each tool call generates only one single chart.
|
||||
"user_prompt": chart_description,
|
||||
"dataset": dict_data,
|
||||
"output_type": output_type,
|
||||
"file_name": file_name,
|
||||
"directory": str(config.workspace_root),
|
||||
}
|
||||
process = subprocess.run(
|
||||
["npx", "ts-node", "src/chartVisualize.ts"],
|
||||
input=json.dumps(vmind_params),
|
||||
capture_output=True,
|
||||
text=True,
|
||||
encoding="utf-8",
|
||||
# build async sub process
|
||||
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__),
|
||||
)
|
||||
if process.returncode == 0:
|
||||
return json.loads(process.stdout)
|
||||
else:
|
||||
return {"error": f"Node.js Error: {process.stderr}"}
|
||||
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)}"}
|
||||
|
||||
@@ -1,42 +0,0 @@
|
||||
from app.tool.chart_visualization.normal_python_execute import NormalPythonExecute
|
||||
|
||||
|
||||
class DataAnalysisPythonExecute(NormalPythonExecute):
|
||||
"""A tool for executing Python code in data analysis task with timeout and safety restrictions."""
|
||||
|
||||
name: str = "data_analysis_python_execute"
|
||||
description: str = (
|
||||
"Executes Python code string in data analysis task, save data table in csv file. Note: Only print outputs are visible, function return values are not captured. Use print statements to see results."
|
||||
)
|
||||
parameters: dict = {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": """Python code template EXCLUSIVELY for data analysis. Must Contains:
|
||||
1. Data loading logic (handle dataframe/dict/file/url/json/web crawler)
|
||||
2. Data analysis (cleaning/transformation)
|
||||
3. CSV saving with path print: print(csv_path)
|
||||
""",
|
||||
},
|
||||
"analysis_content": {
|
||||
"type": "string",
|
||||
"description": "Your analysis of current task, ensure your analysis is concise, clear, and easy to understand.",
|
||||
},
|
||||
},
|
||||
"required": ["code"],
|
||||
}
|
||||
|
||||
async def execute(self, code: str, analysis_content: str, timeout=5):
|
||||
"""
|
||||
Executes the provided Python code with a timeout.
|
||||
|
||||
Args:
|
||||
code (str): The Python code to execute.
|
||||
analysis_content (str): The analysis content of current task.
|
||||
timeout (int): Execution timeout in seconds.
|
||||
|
||||
Returns:
|
||||
Dict: Contains 'output' with execution output or error message and 'success' status.
|
||||
"""
|
||||
return await super().execute(code, timeout)
|
||||
@@ -1,10 +1,4 @@
|
||||
import sys
|
||||
from io import StringIO
|
||||
|
||||
from app.tool.python_execute import PythonExecute
|
||||
from app.tool.chart_visualization.utils import (
|
||||
extract_executable_code,
|
||||
)
|
||||
|
||||
|
||||
class NormalPythonExecute(PythonExecute):
|
||||
@@ -12,34 +6,26 @@ class NormalPythonExecute(PythonExecute):
|
||||
|
||||
name: str = "common_python_execute"
|
||||
description: str = (
|
||||
"""Executes Python code strings. Note:
|
||||
1. Only outputs from print() are visible; function return values are not captured. Use print() statements to display results
|
||||
2. Applicable to scenarios **excluding data analysis and chart generation**"""
|
||||
"""Executes Python code strings to tasks such as data process and data report"""
|
||||
)
|
||||
parameters: dict = {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": "The Python code to execute.",
|
||||
"description": """The Python code to execute. Note:
|
||||
1. Only outputs from print() are visible; function return values are not captured. Use print() statements to display results
|
||||
2. Do data process (cleaning / transform) saved in *.csv
|
||||
3. Generate a data analysis report in html""",
|
||||
},
|
||||
"code_type": {
|
||||
"description": "code type",
|
||||
"type": "string",
|
||||
"enum": ["process", "report", "others"],
|
||||
},
|
||||
},
|
||||
"required": ["code"],
|
||||
}
|
||||
|
||||
def _run_code(self, code: str, result_dict: dict, safe_globals: dict) -> None:
|
||||
original_stdout = sys.stdout
|
||||
be_extracted_code = extract_executable_code(code) # ignore_security_alert RCE
|
||||
try:
|
||||
output_buffer = StringIO()
|
||||
sys.stdout = output_buffer
|
||||
exec( # ignore_security_alert RCE
|
||||
be_extracted_code, safe_globals, safe_globals
|
||||
) # ignore_security_alert RCE
|
||||
result_dict["observation"] = output_buffer.getvalue()
|
||||
result_dict["success"] = True
|
||||
except Exception as e:
|
||||
result_dict["observation"] = str(e)
|
||||
result_dict["success"] = False
|
||||
finally:
|
||||
sys.stdout = original_stdout
|
||||
async def execute(self, code: str, code_type: str, timeout=5):
|
||||
return await super().execute(code, timeout)
|
||||
|
||||
+28
-5
@@ -11,9 +11,11 @@
|
||||
"dependencies": {
|
||||
"@visactor/vchart": "^1.13.7",
|
||||
"@visactor/vmind": "^2.0.4",
|
||||
"canvas": "^2.11.2"
|
||||
"canvas": "^2.11.2",
|
||||
"get-stdin": "^9.0.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/get-stdin": "^7.0.0",
|
||||
"@types/node": "^22.10.1",
|
||||
"ts-node": "^10.9.2",
|
||||
"typescript": "^5.7.2"
|
||||
@@ -6213,6 +6215,16 @@
|
||||
"url": "https://opencollective.com/turf"
|
||||
}
|
||||
},
|
||||
"node_modules/@types/get-stdin": {
|
||||
"version": "7.0.0",
|
||||
"resolved": "https://bnpm.byted.org/@types/get-stdin/-/get-stdin-7.0.0.tgz",
|
||||
"integrity": "sha512-kiDwIsKQvsLRvtBOnasij+6eChbCzcUT7OyVvrC5BEOE4QSKbpnwejEp0xND/9sIdOTfiu+BBl3zsB16MJ3Fww==",
|
||||
"deprecated": "This is a stub types definition. get-stdin provides its own type definitions, so you do not need this installed.",
|
||||
"dev": true,
|
||||
"dependencies": {
|
||||
"get-stdin": "*"
|
||||
}
|
||||
},
|
||||
"node_modules/@types/node": {
|
||||
"version": "22.13.10",
|
||||
"resolved": "https://registry.npmjs.org/@types/node/-/node-22.13.10.tgz",
|
||||
@@ -7131,6 +7143,14 @@
|
||||
"geojson-flatten": "geojson-flatten"
|
||||
}
|
||||
},
|
||||
"node_modules/geojson-flatten/node_modules/get-stdin": {
|
||||
"version": "6.0.0",
|
||||
"resolved": "https://bnpm.byted.org/get-stdin/-/get-stdin-6.0.0.tgz",
|
||||
"integrity": "sha512-jp4tHawyV7+fkkSKyvjuLZswblUtz+SQKzSWnBbii16BuZksJlU1wuBYXY75r+duh/llF1ur6oNwi+2ZzjKZ7g==",
|
||||
"engines": {
|
||||
"node": ">=4"
|
||||
}
|
||||
},
|
||||
"node_modules/geojson-linestring-dissolve": {
|
||||
"version": "0.0.1",
|
||||
"resolved": "https://bnpm.byted.org/geojson-linestring-dissolve/-/geojson-linestring-dissolve-0.0.1.tgz",
|
||||
@@ -7180,11 +7200,14 @@
|
||||
}
|
||||
},
|
||||
"node_modules/get-stdin": {
|
||||
"version": "6.0.0",
|
||||
"resolved": "https://bnpm.byted.org/get-stdin/-/get-stdin-6.0.0.tgz",
|
||||
"integrity": "sha512-jp4tHawyV7+fkkSKyvjuLZswblUtz+SQKzSWnBbii16BuZksJlU1wuBYXY75r+duh/llF1ur6oNwi+2ZzjKZ7g==",
|
||||
"version": "9.0.0",
|
||||
"resolved": "https://bnpm.byted.org/get-stdin/-/get-stdin-9.0.0.tgz",
|
||||
"integrity": "sha512-dVKBjfWisLAicarI2Sf+JuBE/DghV4UzNAVe9yhEJuzeREd3JhOTE9cUaJTeSa77fsbQUK3pcOpJfM59+VKZaA==",
|
||||
"engines": {
|
||||
"node": ">=4"
|
||||
"node": ">=12"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/sindresorhus"
|
||||
}
|
||||
},
|
||||
"node_modules/gifuct-js": {
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
"version": "1.0.0",
|
||||
"main": "src/index.ts",
|
||||
"devDependencies": {
|
||||
"@types/get-stdin": "^7.0.0",
|
||||
"@types/node": "^22.10.1",
|
||||
"ts-node": "^10.9.2",
|
||||
"typescript": "^5.7.2"
|
||||
@@ -10,7 +11,8 @@
|
||||
"dependencies": {
|
||||
"@visactor/vchart": "^1.13.7",
|
||||
"@visactor/vmind": "^2.0.4",
|
||||
"canvas": "^2.11.2"
|
||||
"canvas": "^2.11.2",
|
||||
"get-stdin": "^9.0.0"
|
||||
},
|
||||
"scripts": {
|
||||
"test": "echo \"Error: no test specified\" && exit 1"
|
||||
|
||||
@@ -1,10 +1,27 @@
|
||||
import Canvas from "canvas";
|
||||
import path from "path";
|
||||
import { readFileSync } from "fs";
|
||||
import VMind from "@visactor/vmind";
|
||||
import fs from "fs";
|
||||
import VMind, { ChartType } from "@visactor/vmind";
|
||||
import VChart from "@visactor/vchart";
|
||||
import { isString } from "@visactor/vutils";
|
||||
|
||||
enum AlgorithmType {
|
||||
OverallTrending = "overallTrend",
|
||||
AbnormalTrend = "abnormalTrend",
|
||||
PearsonCorrelation = "pearsonCorrelation",
|
||||
SpearmanCorrelation = "spearmanCorrelation",
|
||||
ExtremeValue = "extremeValue",
|
||||
MajorityValue = "majorityValue",
|
||||
StatisticsAbnormal = "statisticsAbnormal",
|
||||
StatisticsBase = "statisticsBase",
|
||||
DbscanOutlier = "dbscanOutlier",
|
||||
LOFOutlier = "lofOutlier",
|
||||
TurningPoint = "turningPoint",
|
||||
PageHinkley = "pageHinkley",
|
||||
DifferenceOutlier = "differenceOutlier",
|
||||
Volatility = "volatility",
|
||||
}
|
||||
|
||||
const getBase64 = async (spec: any, width?: number, height?: number) => {
|
||||
spec.animation = false;
|
||||
width && (spec.width = width);
|
||||
@@ -36,7 +53,7 @@ const serializeSpec = (spec: any) => {
|
||||
});
|
||||
};
|
||||
|
||||
async function getHtmlVChart(spec: any, width: number, height: number) {
|
||||
async function getHtmlVChart(spec: any, width?: number, height?: number) {
|
||||
return `<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
@@ -77,8 +94,55 @@ async function getHtmlVChart(spec: any, width: number, height: number) {
|
||||
`;
|
||||
}
|
||||
|
||||
function getSavedPathName(
|
||||
directory: string,
|
||||
fileName: string,
|
||||
outputType: "html" | "png" | "json" | "md"
|
||||
) {
|
||||
let newFileName = fileName;
|
||||
while (
|
||||
fs.existsSync(
|
||||
path.join(directory, "visualization", `${newFileName}.${outputType}`)
|
||||
)
|
||||
) {
|
||||
newFileName += "_new";
|
||||
}
|
||||
return path.join(directory, "visualization", `${newFileName}.${outputType}`);
|
||||
}
|
||||
|
||||
const readStdin = (): Promise<string> => {
|
||||
return new Promise((resolve) => {
|
||||
let input = "";
|
||||
process.stdin.setEncoding("utf-8"); // 确保编码与 Python 端一致
|
||||
process.stdin.on("data", (chunk) => (input += chunk));
|
||||
process.stdin.on("end", () => resolve(input));
|
||||
});
|
||||
};
|
||||
|
||||
const setInsightTemplate = (
|
||||
path: string,
|
||||
title: string,
|
||||
insights: string[]
|
||||
) => {
|
||||
let res = "";
|
||||
if (insights.length) {
|
||||
res += `## ${title} Insights`;
|
||||
insights.forEach((insight, index) => {
|
||||
res += `\n${index + 1}. ${insight}`;
|
||||
});
|
||||
}
|
||||
if (res) {
|
||||
fs.writeFileSync(path, res, "utf-8");
|
||||
return path;
|
||||
}
|
||||
return "";
|
||||
};
|
||||
|
||||
async function generateChart() {
|
||||
const inputData = JSON.parse(readFileSync(process.stdin.fd, "utf-8"));
|
||||
const input = await readStdin();
|
||||
const inputData = JSON.parse(input);
|
||||
const res: { chart_path?: string; error?: string; insight_path?: string } =
|
||||
{};
|
||||
try {
|
||||
const {
|
||||
llm_config,
|
||||
@@ -87,6 +151,8 @@ async function generateChart() {
|
||||
output_type: outputType = "png",
|
||||
width,
|
||||
height,
|
||||
file_name: fileName,
|
||||
directory,
|
||||
} = inputData;
|
||||
const { base_url: baseUrl, model, api_key: apiKey } = llm_config;
|
||||
const vmind = new VMind({
|
||||
@@ -97,8 +163,9 @@ async function generateChart() {
|
||||
Authorization: `Bearer ${apiKey}`,
|
||||
},
|
||||
});
|
||||
// Get chart spec and save in local file
|
||||
const jsonDataset = isString(dataset) ? JSON.parse(dataset) : dataset;
|
||||
const { spec, error } = await vmind.generateChart(
|
||||
const { spec, error, chartType } = await vmind.generateChart(
|
||||
userPrompt,
|
||||
undefined,
|
||||
jsonDataset,
|
||||
@@ -115,17 +182,72 @@ async function generateChart() {
|
||||
);
|
||||
return;
|
||||
}
|
||||
if (outputType === "png") {
|
||||
console.log(
|
||||
JSON.stringify({ res: await getBase64(spec, width, height) })
|
||||
);
|
||||
} else {
|
||||
console.log(
|
||||
JSON.stringify({ res: await getHtmlVChart(spec, width, height) })
|
||||
);
|
||||
|
||||
spec.title = {
|
||||
text: userPrompt,
|
||||
};
|
||||
if (!fs.existsSync(path.join(directory, "visualization"))) {
|
||||
fs.mkdirSync(path.join(directory, "visualization"));
|
||||
}
|
||||
} catch (error) {
|
||||
console.log(JSON.stringify({ error }));
|
||||
const specPath = getSavedPathName(directory, fileName, "json");
|
||||
fs.writeFileSync(specPath, JSON.stringify(spec, null, 2));
|
||||
const savedPath = getSavedPathName(directory, fileName, outputType);
|
||||
if (outputType === "png") {
|
||||
const base64 = await getBase64(spec, width, height);
|
||||
fs.writeFileSync(savedPath, base64);
|
||||
} else {
|
||||
const html = await getHtmlVChart(spec, width, height);
|
||||
fs.writeFileSync(savedPath, html, "utf-8");
|
||||
}
|
||||
res.chart_path = savedPath;
|
||||
|
||||
// get chart insights and save in local
|
||||
const insights = [];
|
||||
if (
|
||||
chartType &&
|
||||
[
|
||||
ChartType.BarChart,
|
||||
ChartType.LineChart,
|
||||
ChartType.AreaChart,
|
||||
ChartType.ScatterPlot,
|
||||
ChartType.DualAxisChart,
|
||||
].includes(chartType)
|
||||
) {
|
||||
const { insights: vmindInsights } = await vmind.getInsights(spec, {
|
||||
maxNum: 6,
|
||||
algorithms: [
|
||||
AlgorithmType.OverallTrending,
|
||||
AlgorithmType.AbnormalTrend,
|
||||
AlgorithmType.PearsonCorrelation,
|
||||
AlgorithmType.SpearmanCorrelation,
|
||||
AlgorithmType.StatisticsAbnormal,
|
||||
AlgorithmType.LOFOutlier,
|
||||
AlgorithmType.DbscanOutlier,
|
||||
AlgorithmType.MajorityValue,
|
||||
AlgorithmType.PageHinkley,
|
||||
AlgorithmType.TurningPoint,
|
||||
AlgorithmType.StatisticsBase,
|
||||
AlgorithmType.Volatility,
|
||||
],
|
||||
usePolish: false,
|
||||
});
|
||||
insights.push(...vmindInsights);
|
||||
}
|
||||
const insightsText = insights
|
||||
.map((insight) => insight.textContent?.plainText)
|
||||
.filter((insight) => !!insight) as string[];
|
||||
spec.insights = insights;
|
||||
fs.writeFileSync(specPath, JSON.stringify(spec, null, 2));
|
||||
const insightRes = setInsightTemplate(
|
||||
getSavedPathName(directory, fileName, "md"),
|
||||
userPrompt,
|
||||
insightsText
|
||||
);
|
||||
res.insight_path = insightRes;
|
||||
} catch (error: any) {
|
||||
res.error = error.toString();
|
||||
} finally {
|
||||
console.log(JSON.stringify(res));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,50 @@
|
||||
import asyncio
|
||||
import time
|
||||
|
||||
from app.agent.manus import Manus
|
||||
from app.agent.data_analysis import DataAnalysis
|
||||
from app.flow.base import FlowType
|
||||
from app.flow.flow_factory import FlowFactory
|
||||
from app.logger import logger
|
||||
|
||||
|
||||
async def run_flow():
|
||||
agents = {
|
||||
# "manus": Manus(),
|
||||
"visactor": DataAnalysis(),
|
||||
}
|
||||
|
||||
try:
|
||||
prompt = """Here's last month's sales data from my Amazon store. Could you analyze it thoroughly with visualizations and recommend specific, data-driven strategies to boost next month's sales by 10%?
|
||||
File Path: workspace/amazon_sales_jan2025.csv
|
||||
"""
|
||||
|
||||
flow = FlowFactory.create_flow(
|
||||
flow_type=FlowType.PLANNING,
|
||||
agents=agents,
|
||||
)
|
||||
logger.warning("Processing your request...")
|
||||
|
||||
try:
|
||||
start_time = time.time()
|
||||
result = await asyncio.wait_for(
|
||||
flow.execute(prompt),
|
||||
timeout=3600, # 60 minute timeout for the entire execution
|
||||
)
|
||||
elapsed_time = time.time() - start_time
|
||||
logger.info(f"Request processed in {elapsed_time:.2f} seconds")
|
||||
logger.info(result)
|
||||
except asyncio.TimeoutError:
|
||||
logger.error("Request processing timed out after 1 hour")
|
||||
logger.info(
|
||||
"Operation terminated due to timeout. Please try a simpler request."
|
||||
)
|
||||
|
||||
except KeyboardInterrupt:
|
||||
logger.info("Operation cancelled by user.")
|
||||
except Exception as e:
|
||||
logger.error(f"Error: {str(e)}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(run_flow())
|
||||
@@ -0,0 +1,32 @@
|
||||
import asyncio
|
||||
from app.tool.chart_visualization import ChartVisualization
|
||||
|
||||
|
||||
async def mock_request(delay, value):
|
||||
print("!!!!")
|
||||
await asyncio.sleep(delay) # 模拟异步IO操作（如网络请求）
|
||||
return value
|
||||
|
||||
|
||||
async def main():
|
||||
# 创建多个异步任务
|
||||
tasks = [
|
||||
mock_request(1, "结果1"),
|
||||
mock_request(2, "结果2"),
|
||||
mock_request(3, "结果3"),
|
||||
]
|
||||
|
||||
# 并发执行所有任务，等待全部完成
|
||||
results = await asyncio.gather(*tasks)
|
||||
print(results) # 输出: ['结果1', '结果2', '结果3']
|
||||
|
||||
|
||||
async def test_chart():
|
||||
chartTool = ChartVisualization()
|
||||
print(await chartTool.execute("./data/visualization_info.json", "html"))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(test_chart())
|
||||
# 运行主协程
|
||||
# asyncio.run(main())
|
||||
@@ -10,7 +10,9 @@ class PythonExecute(BaseTool):
|
||||
"""A tool for executing Python code with timeout and safety restrictions."""
|
||||
|
||||
name: str = "python_execute"
|
||||
description: str = "Executes Python code string. Note: Only print outputs are visible, function return values are not captured. Use print statements to see results."
|
||||
description: str = (
|
||||
"Executes Python code string. Note: Only print outputs are visible, function return values are not captured. Use print statements to see results."
|
||||
)
|
||||
parameters: dict = {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
Reference in New Issue
Block a user