denario

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Denario

Overview

概述

Denario is a multiagent AI system designed to automate scientific research workflows from initial data analysis through publication-ready manuscripts. Built on AG2 and LangGraph frameworks, it orchestrates multiple specialized agents to handle hypothesis generation, methodology development, computational analysis, and paper writing.

Denario是一款多Agent AI系统，旨在自动化从初始数据分析到生成可发表手稿的整个科研工作流。它基于AG2和LangGraph框架构建，可编排多个专业Agent来处理假设生成、方法制定、计算分析和论文撰写等任务。

When to Use This Skill

适用场景

Use this skill when:

Analyzing datasets to generate novel research hypotheses
Developing structured research methodologies
Executing computational experiments and generating visualizations
Conducting literature searches for research context
Writing journal-formatted LaTeX papers from research results
Automating the complete research pipeline from data to publication

当你有以下需求时，可使用该工具：

分析数据集以生成新颖的研究假设
制定结构化的研究方法
执行计算实验并生成可视化结果
为研究背景进行文献检索
根据研究结果撰写符合期刊格式的LaTeX论文
自动化从数据到论文发表的完整研究流程

Installation

安装步骤

Install denario using uv (recommended):

bash

uv init
uv add "denario[app]"

Or using pip:

bash

uv pip install "denario[app]"

For Docker deployment or building from source, see

references/installation.md

推荐使用uv安装denario：

bash

uv init
uv add "denario[app]"

或使用pip安装：

bash

uv pip install "denario[app]"

关于Docker部署或从源码构建的方法，请查看

references/installation.md

。

LLM API Configuration

LLM API配置

Denario requires API keys from supported LLM providers. Supported providers include:

Google Vertex AI
OpenAI
Other LLM services compatible with AG2/LangGraph

Store API keys securely using environment variables or

.env

files. For detailed configuration instructions including Vertex AI setup, see

references/llm_configuration.md

Denario需要来自支持的LLM提供商的API密钥。支持的提供商包括：

Google Vertex AI
OpenAI
其他与AG2/LangGraph兼容的LLM服务

请使用环境变量或

.env

文件安全存储API密钥。包括Vertex AI设置在内的详细配置说明，请查看

references/llm_configuration.md

。

Core Research Workflow

核心研究工作流

Denario follows a structured four-stage research pipeline:

Denario遵循结构化的四阶段研究流程：

1. Data Description

1. 数据描述

Define the research context by specifying available data and tools:

python

from denario import Denario

den = Denario(project_dir="./my_research")
den.set_data_description("""
Available datasets: time-series data on X and Y
Tools: pandas, sklearn, matplotlib
Research domain: [specify domain]
""")

通过指定可用数据和工具来定义研究背景：

python

from denario import Denario

den = Denario(project_dir="./my_research")
den.set_data_description("""
Available datasets: time-series data on X and Y
Tools: pandas, sklearn, matplotlib
Research domain: [specify domain]
""")

2. Idea Generation

2. 思路生成

Generate research hypotheses from the data description:

python

den.get_idea()

This produces a research question or hypothesis based on the described data. Alternatively, provide a custom idea:

python

den.set_idea("Custom research hypothesis")

根据数据描述生成研究假设：

python

den.get_idea()

该操作会基于提供的数据描述生成研究问题或假设。你也可以自定义研究思路：

python

den.set_idea("Custom research hypothesis")

3. Methodology Development

3. 方法制定

Develop the research methodology:

python

den.get_method()

This creates a structured approach for investigating the hypothesis. Can also accept markdown files with custom methodologies:

python

den.set_method("path/to/methodology.md")

制定研究方法：

python

den.get_method()

该操作会创建用于验证假设的结构化方法。你也可以传入包含自定义方法的markdown文件：

python

den.set_method("path/to/methodology.md")

4. Results Generation

4. 结果生成

Execute computational experiments and generate analysis:

python

den.get_results()

This runs the methodology, performs computations, creates visualizations, and produces findings. Can also provide pre-computed results:

python

den.set_results("path/to/results.md")

执行计算实验并生成分析结果：

python

den.get_results()

该操作会执行研究方法、进行计算、创建可视化图表并生成研究发现。你也可以提供预先计算好的结果：

python

den.set_results("path/to/results.md")

5. Paper Generation

5. 论文生成

Create a publication-ready LaTeX paper:

python

from denario import Journal

den.get_paper(journal=Journal.APS)

The generated paper includes proper formatting for the specified journal, integrated figures, and complete LaTeX source.

生成可直接用于发表的LaTeX论文：

python

from denario import Journal

den.get_paper(journal=Journal.APS)

生成的论文会符合指定期刊的格式规范，包含整合的图表和完整的LaTeX源码。

Available Journals

支持的期刊格式

Denario supports multiple journal formatting styles:

```
Journal.APS
```
- American Physical Society format
Additional journals may be available; check
```
references/research_pipeline.md
```
for the complete list

Denario支持多种期刊格式：

```
Journal.APS
```
- 美国物理学会格式
可能支持更多期刊；完整列表请查看
```
references/research_pipeline.md
```

Launching the GUI

启动GUI界面

Run the graphical user interface:

bash

denario run

This launches a web-based interface for interactive research workflow management.

运行图形用户界面：

bash

denario run

这会启动一个基于网页的交互界面，用于管理研究工作流。

Common Workflows

常见工作流示例

End-to-End Research Pipeline

端到端研究流程

python

from denario import Denario, Journal

python

from denario import Denario, Journal

Initialize project

初始化项目

den = Denario(project_dir="./research_project")

Define research context

定义研究背景

den.set_data_description(""" Dataset: Time-series measurements of [phenomenon] Available tools: pandas, sklearn, scipy Research goal: Investigate [research question] """)

Generate research idea

生成研究思路

den.get_idea()

Develop methodology

制定研究方法

den.get_method()

Execute analysis

执行分析

den.get_results()

Create publication

生成发表论文

den.get_paper(journal=Journal.APS)

undefined

den.get_paper(journal=Journal.APS)

undefined

Hybrid Workflow (Custom + Automated)

混合工作流（自定义+自动化）

python

undefined

python

undefined

Provide custom research idea

提供自定义研究思路

den.set_idea("Investigate the correlation between X and Y using time-series analysis")

Auto-generate methodology

自动生成研究方法

den.get_method()

Auto-generate results

自动生成结果

den.get_results()

Generate paper

生成论文

den.get_paper(journal=Journal.APS)

undefined

den.get_paper(journal=Journal.APS)

undefined

Literature Search Integration

文献检索集成

For literature search functionality and additional workflow examples, see

references/examples.md

关于文献检索功能和更多工作流示例，请查看

references/examples.md

。

Advanced Features

高级功能

Multiagent orchestration: AG2 and LangGraph coordinate specialized agents for different research tasks
Reproducible research: All stages produce structured outputs that can be version-controlled
Journal integration: Automatic formatting for target publication venues
Flexible input: Manual or automated at each pipeline stage
Docker deployment: Containerized environment with LaTeX and all dependencies

多Agent编排：AG2和LangGraph协调不同的专业Agent处理各类研究任务
可复现研究：所有阶段都会生成可版本控制的结构化输出
期刊集成：自动适配目标期刊的格式规范
灵活输入：每个流程阶段都支持手动输入或自动化生成
Docker部署：包含LaTeX和所有依赖项的容器化环境

Detailed References

详细参考文档

For comprehensive documentation:

Installation options:
```
references/installation.md
```
LLM configuration:
```
references/llm_configuration.md
```
Complete API reference:
```
references/research_pipeline.md
```
Example workflows:
```
references/examples.md
```

完整文档请查看：

安装选项：
```
references/installation.md
```
LLM配置：
```
references/llm_configuration.md
```
完整API参考：
```
references/research_pipeline.md
```
示例工作流：
```
references/examples.md
```

Troubleshooting

故障排除

Common issues and solutions:

API key errors: Ensure environment variables are set correctly (see
```
references/llm_configuration.md
```
)
LaTeX compilation: Install TeX distribution or use Docker image with pre-installed LaTeX
Package conflicts: Use virtual environments or Docker for isolation
Python version: Requires Python 3.12 or higher

常见问题及解决方案：

API密钥错误：确保环境变量设置正确（请查看
```
references/llm_configuration.md
```
）
LaTeX编译问题：安装TeX发行版或使用预安装LaTeX的Docker镜像
包冲突：使用虚拟环境或Docker进行环境隔离
Python版本要求：需要Python 3.12或更高版本