Skip to content
Back to search

Data-Analysis-Agent

๐Ÿš€ไฝ ็š„็งไบบๆ•ฐๆฎๅˆ†ๆžๅŠฉๆ‰‹ใ€‚้€š่ฟ‡ๅฏน่ฏๅผไบคไบ’๏ผŒ่‡ชๅŠจ็”Ÿๆˆๅฏ่ง†ๅŒ–ๆŠฅ่กจไธŽๅ•†ไธšๆดžๅฏŸ๏ผŒ่ฎฉๆ•ฐๆฎๅ†ณ็ญ–ๅ˜ๅพ—ๅƒ่Šๅคฉไธ€ๆ ท็ฎ€ๅ•ใ€‚ ๐Ÿš€ Your personal data analysis assistant. Say goodbye to complex SQL and Excel formulas. An LLM-powered data analysis agent. Chat with your data to instantly generate visualizations and business insights. Making data-driven decisions has never been easier.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/Zafer-Liu/Data-Analysis-Agent with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/Zafer-Liu/Data-Analysis-Agent'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/zafer-liu--data-analysis-agent/badge.svg)](/listings/zafer-liu--data-analysis-agent)

HTML

<a href="/listings/zafer-liu--data-analysis-agent"><img src="/api/listings/zafer-liu--data-analysis-agent/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md ยท README ยท 804 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center"><strong>English</strong> ยท <a href="./README_CN.md">็ฎ€ไฝ“ไธญๆ–‡</a></p>
  2. <h1 align="center">Data Analysis Agent</h1>
  3. <p align="center"><strong>Ask your data. Get SQL, charts, and business insights.</strong></p>
  4. <p align="center">A conversational workspace for business analysis, from spreadsheets to SQL databases.</p>
  5. <div align="center">
  6. <a href="https://trendshift.io/repositories/29216?utm_source=trendshift-badge&utm_medium=badge&utm_campaign=badge-trendshift-29216" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/trendshift/repositories/29216/daily?language=JavaScript" alt="Zafer-Liu%2FData-Analysis-Agent | Trendshift" width="250" height="55"/></a>
  7. [![Website](https://img.shields.io/badge/%F0%9F%8C%90%20Website-sage--agent.online-2F74FF.svg)](https://sage-agent.online/)
  8. ![Python](https://img.shields.io/badge/Python-3.10%2B-blue.svg)
  9. ![Flask](https://img.shields.io/badge/Backend-Flask-black.svg)
  10. ![Plotly](https://img.shields.io/badge/Visualization-Plotly-3F4F75.svg)
  11. ![LLM](https://img.shields.io/badge/LLM-OpenAI%20Compatible-green.svg)
  12. ![Charts](https://img.shields.io/badge/Charts-41_Types-orange.svg)
  13. ![License](https://img.shields.io/badge/License-CC%20BY--NC%204.0-blue.svg)
  14. </div>
  15. <p align="center">
  16. <a href="#sponsors">Sponsors</a> ยท
  17. <a href="#demo">Demo</a> ยท
  18. <a href="#quick-start">Quick start</a> ยท
  19. <a href="#capabilities">Capabilities</a> ยท
  20. <a href="#install">Installation</a> ยท
  21. <a href="https://sage-agent.online/">Website</a> ยท
  22. <a href="https://github.com/Zafer-Liu/Data-Analysis-Agent/releases/latest">Releases</a>
  23. </p>
  24. <p align="center">
  25. <a href="https://discord.gg/EEG4Sw7tde">Discord</a> ยท
  26. <a href="https://t.me/+cdRNfS68u9BlYjJl">Telegram</a> ยท QQ: <code>991636855</code>
  27. </p>
  28. <a id="sponsors"></a>
  29. ## ๐Ÿ™ Sponsors
  30. Thank you to the sponsors supporting this project!
  31. ### โ˜๏ธ Sponsored by DolOffer
  32. <p align="center"><a href="https://doloffer.com/"><img src="./Information/assets/DolOffer.png" alt="DolOffer logo" height="80" /></a></p>
  33. Thank you to DolOffer for supporting this project! DolOffer is a platform focused on digital product recommendations and deal sharing, helping users quickly discover useful tools, services, and limited-time offers. The platform provides popular subscription services such as YouTube Premium, Claude, ChatGPT Plus, Spotify, Apple Music, and more, with prices as low as 30% of the official price or even lower. All services are genuine, stable, and backed by reliable after-sales support. Register through our exclusive link and use the coupon code **AI8888** when topping up to enjoy an additional 10% discount.
  34. ๐Ÿ‘‰ **[Learn more](https://github.com/Doloffer-g/guide)**
  35. ---
  36. ### โ˜๏ธ Sponsored by Mozhenzhen
  37. <p align="center"><a href="https://mozhenzhen.com/go/data-analysis-agent"><img src="./Information/assets/Mozhenzhen.png" alt="Mozhenzhen logo" height="80" /></a></p>
  38. Mozhenzhen โ€” a consumer anti-pitfall guide for developers and AI enthusiasts. Whether you are looking for real-time API price comparison, latency benchmarking and authenticity verification (no watered-down or fake models), comparing after-sales warranties, risk prevention and hidden traps among account / subscription top-up providers, or even discovering free community relays and backup nodes, Mozhenzhen uses transparent data to help you avoid pitfalls and spend every cent wisely.
  39. ๐Ÿ‘‰ **[Visit Mozhenzhen](https://mozhenzhen.com/go/data-analysis-agent)**
  40. ---
  41. ### โ˜๏ธ Sponsored by Infistar
  42. <p align="center"><a href="https://www.infistar.cc/register?aff=U2DQQJPT&ref_source=link"><img src="./Information/assets/InfistarEN.png" alt="Infistar banner" height="160" /></a></p>
  43. Thank you to Infistar.cc for sponsoring Data-Analysis-Agent! It provides stable and efficient multi-model API services that fit perfectly into data cleaning, code generation, chart plotting and automated analysis report workflows.
  44. โš™๏ธ Compatible integration: select the OpenAI-compatible interface in the project, configure the Base URL and API Key, and you are ready to go.
  45. ๐Ÿงฉ Multi-model support: brings together top models such as Claude, GPT, Gemini and DeepSeek, making it easy to switch between them and compare analysis and code generation results.
  46. ๐Ÿท๏ธ Pricing & service: selected models from as low as 1% of official pricing, with public and transparent multipliers, RMB settlement, invoicing and model verification.
  47. ๐ŸŽ Exclusive perk: sign up via our [exclusive promo link](https://www.infistar.cc/register?aff=U2DQQJPT&ref_source=link) and get $5 in free credits!
  48. ๐Ÿ‘‰ **[Register on Infistar ยท Claim $5 credits](https://www.infistar.cc/register?aff=U2DQQJPT&ref_source=link)**
  49. ---
  50. <a id="demo"></a>
  51. ## See it in action
  52. <p align="center">
  53. <img src="./Information/assets/analysis-demo.gif" alt="Animated analysis workflow: connect sales data, ask a question, generate SQL, and reveal a chart and insights" width="100%" />
  54. </p>
  55. *Illustrated workflow with fictional sales data; not a live screen recording.*
  56. [View the still preview](./Information/assets/analysis-demo.png)
  57. ---
  58. <a id="features"></a>
  59. ## Why Data Analysis Agent?
  60. | Capability | What you can do |
  61. | --- | --- |
  62. | **Ask in plain language** | Turn a business question into SQL, a chart, and an explanation. |
  63. | **Bring your data** | Upload Excel / CSV files or connect a SQL database. |
  64. | **Follow the analysis** | Watch schema discovery, queries, and results stream over SSE. |
  65. | **Visualize and export** | Choose from 41 chart types and export Excel, Word, or PowerPoint deliverables. |
  66. | **Choose your model** | Connect OpenAI-compatible APIs or discover compatible local services. |
  67. | **Extend the workflow** | Add business knowledge, analysis Skills, MCP tools, or Feishu Bitable integration. |
  68. | **Delegate to a team** | Let the main Agent construct and call bounded subagents, with A2A 1.0 send, get, and cancel endpoints. |
  69. ---
  70. <a id="quick-start"></a>
  71. ## Quick start
  72. Requires **Python 3.10+**. Run in a dedicated virtual environment:
  73. ```bash
  74. git clone https://github.com/Zafer-Liu/Data-Analysis-Agent.git
  75. cd Data-Analysis-Agent
  76. python -m venv .venv
  77. ```
  78. Activate the environment:
  79. ```powershell
  80. # Windows PowerShell
  81. .\.venv\Scripts\Activate.ps1
  82. ```
  83. ```bash
  84. # macOS / Linux
  85. source .venv/bin/activate
  86. ```
  87. ```bash
  88. python -m pip install -r requirements.txt
  89. python app.py
  90. ```
  91. Open [localhost:5001](http://localhost:5001), configure your model API key, upload Excel / CSV or connect a database, and ask:
  92. ```text
  93. Show monthly sales and plot the trend.
  94. ```
  95. Running the source directly requires no cloud login. See [installation options](#install) and [model configuration](#llm-config) for more details.
  96. Optional machine-learning, deep-learning, packaging, and test dependencies live in [`requirements/`](./requirements/README.md). See the [product specification](./Information/PRODUCT.md) and [frontend build guide](./frontend/README.md) for development details.
  97. ---
  98. <details>
  99. <summary>Table of contents</summary>
  100. - [Sponsors](#sponsors)
  101. - [Capabilities](#capabilities)
  102. - [Installation](#install)
  103. - [Slash commands](#commands)
  104. - [Examples](#examples)
  105. - [LLM configuration](#llm-config)
  106. - [Agent Manager](#agent-manager)
  107. - [Changelog](#changelog)
  108. - [FAQ](#faq)
  109. - [Contributing](#contributing)
  110. - [License](#license)
  111. - [Project goal](#goal)
  112. </details>
  113. ---
  114. <a id="capabilities"></a>
  115. ## ๐Ÿง  Core Capabilities
  116. ### 1๏ธโƒฃ Natural Language Data Analysis
  117. No SQL required โ€” just type in plain language:
  118. ```text
  119. Monthly order volume trend for this year
  120. ```
  121. The system will automatically:
  122. - Generate SQL
  123. - Query the data
  124. - Recommend a chart
  125. - Summarize the analysis
  126. ![Data Query](./Information/assets/Data_query.png)
  127. ### 2๏ธโƒฃ Multi-Source Data Support
  128. Supports uploading and connecting to multiple data sources:
  129. - **Files**: Excel / CSV
  130. - **Databases**: SQLite, MySQL, PostgreSQL, SQL Server
  131. - **Planned**: DuckDB, Spark
  132. ![Data Preview](./Information/assets/Data_preview.png)
  133. ### 3๏ธโƒฃ Intelligent Chart System
  134. Based on your query results, the system automatically recommends the most appropriate chart from 6 major categories:
  135. | Category | Chart Types |
  136. |---|---|
  137. | **COMPARING** | Marimekko_ABS, Marimekko_PCT, Bar_Chart, Grouped_Bar_Chart, Stacked_Bar_Chart, Diverging_Bar_Chart, Dot_Plot, Waffle, Bullet_Chart, Sankey_Chart, Heatmap, Waterfall |
  138. | **TIME** | Line_Chart, Circular_Line_Chart, Slope_Chart, Sparkline, Bump_Chart, Cycle_Chart, Area_Chart, Stacked_Area_Chart, Horizon_Chart, Connected_Scatter |
  139. | **DISTRIBUTION** | Histogram_Pareto_chart, Pyramid_Chart, Error_Bar_Chart, Box-and-Whisker_Plot, Violin_Chart, Ridgeline_Plot, Beeswarm_Plot, stem_leaf |
  140. | **GEOSPATIAL** | Flow_Map, Dot_Density_Map, Choropleth_Map |
  141. | **RELATIONSHIP** | Scatter_Plot, Bubble_Plot, Radar_Charts, Chord_Diagram, Arc_Chart, Network_Diagram, Parallel_Coordinates_Plot |
  142. | **PART-TO-WHOLE** | Treemap, Sunburst_Diagram, Nightingale_Chart, Pie_Chart |
  143. ![Auto Generated](./Information/assets/Auto_generated_image.png)
  144. ### 4๏ธโƒฃ SSE Streaming Analysis Experience
  145. The analysis process is visible in real time:
  146. ```text
  147. [1/4] Reading data structure...
  148. [2/4] Generating SQL...
  149. [3/4] Executing query...
  150. [4/4] Generating chart and insights...
  151. ```
  152. More transparent and interactive than traditional BI tools.
  153. ### 5๏ธโƒฃ Multi-Model Compatibility
  154. Supports the following model providers:
  155. - DeepSeek
  156. - OpenAI
  157. - AtlasCloud
  158. - Any OpenAI SDK-compatible API
  159. Supports custom `base_url`, `model`, and `api_key`. Default configurations:
  160. | Provider | Default Model |
  161. |---|---|
  162. | DeepSeek | `deepseek-v4-flash` |
  163. | OpenAI | `gpt-4o-mini` |
  164. | AtlasCloud | `deepseek-v4-pro` |
  165. ### 6๏ธโƒฃ Data Analysis
  166. Currently supported analysis features:
  167. - Outlier handling (trimming and winsorizing)
  168. - Decile grouping analysis
  169. - K-Means clustering
  170. - Decision tree modeling
  171. - And more...
  172. ### 7๏ธโƒฃ Report Generation
  173. Supports exporting:
  174. - Formatted Excel spreadsheets
  175. - Reports in `.docx` format
  176. - Built-in styled PowerPoint presentations
  177. ### 8๏ธโƒฃ MCP Extensions
  178. Supports connecting to local or remote MCP servers to expand the Agent's capabilities.
  179. ![MCP](./Information/assets/MCP1.png)
  180. - Tutorial: [MCP_tutorial](./Information/MCP_tutorial.md)
  181. ### 9๏ธโƒฃ Knowledge Base Input
  182. Supports uploading business knowledge to help the Agent better understand your data.
  183. ![repository](./Information/assets/repository2.png)
  184. - Tutorial: [repository_tutorial](./Information/repository_tutorial.md)
  185. ---
  186. <a id="install"></a>
  187. ## โš™๏ธ Installation
  188. ### ๐Ÿ–ฅ๏ธ Option 1: Windows Installer (Easiest โ€” Recommended)
  189. Download the latest version from [GitHub Releases](https://github.com/Zafer-Liu/Data-Analysis-Agent/releases/latest):
  190. | Platform | File |
  191. |---|---|
  192. | Windows | Latest Windows `.exe` installer |
  193. > **Prerequisites: Python 3.10+ and 64-bit Windows 10 / 11.**
  194. Run the installer and follow the setup wizard. After installation, launch **Business Analytics Agent** from the desktop or Start Menu.
  195. Desktop packages built from the current source open in local mode without a platform account. Configure your own model API key in Settings. Existing published installers are unchanged until a new release is built; v1.5.0 still depends on the retired cloud login service.
  196. ---
  197. ### Option 2: Download the ZIP (Recommended for Beginners, Cross-Platform)
  198. > **Prerequisite: Python 3.10+**
  199. > Don't have it? [Download here](https://www.python.org/downloads/) (Windows: check **"Add Python to PATH"** during install)
  200. **Step 1: Download and extract**
  201. ![Download installation package](Information/assets/package.png)
  202. **Step 2: Double-click to launch**
  203. | OS | Action |
  204. |---|---|
  205. | **Windows** | Double-click `start.bat` |
  206. | **macOS** | โ‘  Open Terminal (Command + Space โ†’ type Terminal โ†’ Enter) โ‘ก Run the following (replace the path with your actual extraction location): `chmod +x ~/Downloads/Data-Analysis-Agent/start.command` then `xattr -d com.apple.quarantine ~/Downloads/Data-Analysis-Agent/start.command` โ‘ข Double-click `start.command` |
  207. > **First launch** will automatically create a virtual environment and install dependencies โ€” this takes about 3โ€“5 minutes. **Subsequent launches are instant.**
  208. **Step 3: Browser auto-opens** at `http://localhost:5001`
  209. ![Download installation package2](./Information/assets/package2.png)
  210. **Step 4: Configure your API Key**
  211. ![Configure the API3](./Information/assets/Deepseek3.png)
  212. **Step 5: Future updates**
  213. ![Update](./Information/assets/Update.png)
  214. ---
  215. ### Option 3: One-Click Online Install
  216. **Windows (run in PowerShell):**
  217. ```powershell
  218. iwr -useb https://raw.githubusercontent.com/Zafer-Liu/Data-Analysis-Agent/main/install.ps1 | iex
  219. ```
  220. After installation, double-click `data-analysis-agent.bat` on your desktop, or run:
  221. ```powershell
  222. cd $env:USERPROFILE\.data-analysis-agent\Data-Analysis-Agent
  223. .\.venv\Scripts\activate
  224. python app.py
  225. ```
  226. **macOS / Linux (run in Terminal):**
  227. ```bash
  228. curl -fsSL https://raw.githubusercontent.com/Zafer-Liu/Data-Analysis-Agent/main/install.sh | sh
  229. ```
  230. After installation, run:
  231. ```bash
  232. data-analysis-agent
  233. ```
  234. If you see `command not found`, add the following to `~/.zshrc` or `~/.bashrc`, then restart Terminal:
  235. ```bash
  236. export PATH="$HOME/.local/bin:$PATH"
  237. ```
  238. ---
  239. ### Option 4: Clone from GitHub
  240. ```bash
  241. git clone https://github.com/Zafer-Liu/Data-Analysis-Agent.git
  242. cd Data-Analysis-Agent
  243. pip install -r requirements.txt
  244. python app.py
  245. ```
  246. Open `http://localhost:5001` in your browser and configure your API Key.
  247. ---
  248. <a id="commands"></a>
  249. ## ๐Ÿ›  Slash Commands
  250. | Command | Status | Description |
  251. |---|---|---|
  252. | `/chart` | โœ… | Force chart generation as the priority output |
  253. | `/sql` | โœ… | Execute SQL directly |
  254. | `/analyze` | โœ… | Deep statistical analysis |
  255. | `/tree` | โœ… | Decision tree analysis |
  256. | `/kmeans` | โœ… | K-Means clustering analysis |
  257. | `/data` | โœ… | Data exploration and preview |
  258. | `/inset` | โœ… | Missing value imputation |
  259. | `/winsorize` | โœ… | Winsorizing (replace extreme values) |
  260. | `/trimming` | โœ… | Trimming (remove extreme values) |
  261. | `/export` | โœ… | Export data file |
  262. | `/report` | โœ… | Export Word/PDF report |
  263. | `/ppt` | โœ… | Export PowerPoint presentation |
  264. | `/status` | โœ… | View task status |
  265. ---
  266. <a id="examples"></a>
  267. ## ๐Ÿ“ˆ Usage Examples
  268. ### Example 1: Trend Analysis
  269. User input:
  270. ```text
  271. Sales trend for the last 12 months
  272. ```
  273. System output:
  274. - SQL query
  275. - Trend line chart
  276. - Sales growth analysis
  277. ---
  278. ### Example 2: Regional Analysis
  279. User input:
  280. ```text
  281. Which region has the highest profit?
  282. ```
  283. System output:
  284. - Regional profit rankings
  285. - Bar chart
  286. - Regional business insights
  287. ---
  288. ### Example 3: Chart-First Mode
  289. User input:
  290. ```text
  291. /chart User growth overview
  292. ```
  293. The system will prioritize generating a visualization.
  294. ---
  295. <a id="llm-config"></a>
  296. ## ๐Ÿค– LLM Configuration
  297. In the sidebar โš™, fill in:
  298. ```text
  299. API Key
  300. Base URL
  301. Model
  302. ```
  303. to switch between models.
  304. ---
  305. <a id="agent-manager"></a>
  306. ## ๐Ÿงฉ Recommended Management: Agent Manager
  307. Business Analytics Agent can run independently or with **Agent Manager** for a more convenient desktop management experience.
  308. <details>
  309. <summary><strong>Learn how Agent Manager manages this project</strong></summary>
  310. <br>
  311. **Agent Manager** is a unified control center for local AI Agent projects. After adding Business Analytics Agent, you can:
  312. * Start or stop the Agent with one click
  313. * View logs and port status in real time
  314. * Open the web analysis interface inside the desktop app
  315. * Ask the Manager Agent to start or open this project in natural language
  316. * Create a temporary public sharing link for demos
  317. ```text
  318. Example:
  319. Start Business Analytics Agent and open its interface.
  320. ```
  321. This is especially useful when you frequently demonstrate, debug, or run multiple Agent projects.
  322. ๐Ÿ‘‰ Project: [Agent Manager](https://github.com/Zafer-Liu/Agent_Manager)
  323. </details>
  324. ---
  325. <a id="changelog"></a>
  326. ## ๐Ÿ“ Changelog
  327. > **Current source version `v1.4.0`** ยท October 16, 2026 ยท Check [Releases](https://github.com/Zafer-Liu/Data-Analysis-Agent/releases/latest) for published installers.
  328. The public source now includes the existing private-edition features: the read-only administration console, desktop cloud authentication and model gateways, referral and quota ledgers, browser/table ingestion, browser-local persistence, PyTorch GRU/LSTM, chart themes and PNG export, in-memory SQL transformations and numeric provenance checks, canvas save recovery, Skill tags, and SSE reliability improvements.
  329. Direct `python app.py` launches and default desktop packages require no cloud login and use your own model configuration. Hosted services retain account authentication; desktop cloud authentication is enabled only by an explicitly configured `BAA_CLOUD_AUTH_URL`.
  330. ### Local models and services (source update)
  331. Manage HTTP and Docker connections in **Settings โ†’ Local services**. Custom HTTP connections support health checks and manual JSON requests; OpenAI-compatible services can discover models and add them to the LLM list. TimesFM is a forecasting adapter with `run_analysis`, backtesting, result tables, and chart export. See the [local services guide](./deploy/local-services/README.md) for configuration and capability boundaries. No models, model dependencies, or container images are downloaded automatically.
  332. For existing model directories, explicit downloads, Docker templates, and a three-product example, see the [TimesFM guide](./deploy/timesfm/README.md). The main application environment stays lightweight; TimesFM weights are limited to non-commercial, non-production research.
  333. ### v1.3.0 history
  334. v1.3.0 enters the Feishu AI Skills Hackathon, adds a Feishu bot and built-in Bitable analysis, and delivers targeted feature improvements:
  335. 1. **Feishu bot and Bitable loop**: Mention the bot in a group to read a Feishu Bitable, load records into DuckDB / SQL analysis, and reply in the same group. Creating result tables or changing records always requires an explicit request.
  336. 2. **More dependable long-term memory**: Fixes extraction failures caused by thinking-model output, JSON formatting, and scope detection; adds result notices, 24-hour consolidation, safer session restore, and a global memory switch.
  337. 3. **Trustworthy knowledge-retrieval status**: Repairs local Embedding model download/compatibility and makes cloud retrieval status an explicit real check. The former Hash mode is now labelled **Basic** in the UI.
  338. 4. **Clearer settings and reading experience**: Unifies settings headers, cards, and spacing; fixes LLM provider-row inset, hover, spacing, and long-content clipping; wide chat layouts now use available space more effectively.
  339. 5. **Compatibility and delivery reliability**: Clarifies SQL Server connection/error boundaries and workflow observability. GPU compute is labelled **Planned** until end-to-end validation is complete; existing implementation and configuration remain preserved.
  340. ### ๐Ÿ“– Detailed Changelog
  341. - [Version Update Log (ไธญๆ–‡)](./Information/Version_Update_Log.md)
  342. - [Version Update Log (English)](./Information/Version_Update_Log_EN.md)
  343. ---
  344. <a id="faq"></a>
  345. ## โ“ FAQ
  346. <details>
  347. <summary><b>๐Ÿ“ฆ Installation & Startup</b></summary>
  348. <details>
  349. <summary><b>Network timeout while installing dependencies?</b></summary>
  350. The script will automatically switch to the Tsinghua mirror and retry.
  351. If it still fails, run manually:
  352. ```bash
  353. pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
  354. ```
  355. </details>
  356. <details>
  357. <summary><b>pip install error / dependency installation failed?</b></summary>
  358. The script automatically retries using a domestic mirror (Tsinghua).
  359. If it still fails, specify the mirror manually:
  360. ```bash
  361. pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
  362. ```
  363. Also ensure at least **2 GB** of free disk space is available.
  364. </details>
  365. <details>
  366. <summary><b>Wrong Python version (requires 3.10+)?</b></summary>
  367. Check your current version:
  368. ```bash
  369. python --version
  370. ```
  371. If below 3.10, download the latest version at:
  372. https://www.python.org/downloads/
  373. </details>
  374. <details>
  375. <summary><b>Double-clicking start.bat does nothing or flashes briefly?</b></summary>
  376. Python is not correctly added to the system PATH.
  377. Reinstall Python and check **"Add Python to PATH"**, then restart your computer and try again.
  378. </details>
  379. <details>
  380. <summary><b>macOS blocks start.command from running?</b></summary>
  381. Run this in Terminal to remove the restriction:
  382. ```bash
  383. xattr -d com.apple.quarantine /your/path/to/start.command
  384. ```
  385. If you see:
  386. > "Cannot be opened because the developer cannot be verified"
  387. You can:
  388. 1. Right-click `start.command`
  389. 2. Select "Open"
  390. 3. Click "Open" again
  391. </details>
  392. </details>
  393. ---
  394. <details>
  395. <summary><b>๐Ÿ”‘ API Configuration</b></summary>
  396. <details>
  397. <summary><b>Prompted that LLM is not configured?</b></summary>
  398. Enter your API Key in the sidebar โš™ and save.
  399. </details>
  400. <details>
  401. <summary><b>How do I get an API Key?</b></summary>
  402. Using DeepSeek as an example:
  403. ![Configure the API1](./Information/assets/Deepseek1.png)
  404. ![Configure the API2](./Information/assets/Deepseek2.png)
  405. ![Configure the API3](./Information/assets/Deepseek3.png)
  406. </details>
  407. </details>
  408. ---
  409. <details>
  410. <summary><b>๐Ÿ—„๏ธ Database Connection</b></summary>
  411. <details>
  412. <summary><b>How do I connect to a SQL database?</b></summary>
  413. Use the following connection format:
  414. ```text
  415. mysql+pymysql://username:password@host:port/database_name
  416. ```
  417. Example:
  418. โŒ Wrong:
  419. ```text
  420. mysql://user:pass@host:3306/dbname
  421. ```
  422. โœ… Correct:
  423. ```text
  424. mysql+pymysql://user:pass@host:3306/dbname
  425. ```
  426. </details>
  427. </details>
  428. ---
  429. <details>
  430. <summary><b>๐Ÿ“Š Charts & Files</b></summary>
  431. <details>
  432. <summary><b>Chart links broken after restart?</b></summary>
  433. Generated charts are saved locally at:
  434. ```text
  435. outputs/charts
  436. ```
  437. You can open the corresponding HTML files directly in your browser.
  438. </details>
  439. </details>
  440. ---
  441. <a id="contributing"></a>
  442. ## ๐Ÿค Contribution Guide
  443. We welcome every kind of contribution, whether you are fixing a bug, improving documentation, or adding a feature.
  444. ### Contribution Workflow
  445. 1. **Fork this repository**
  446. 2. **Create a feature branch**
  447. ```bash
  448. git checkout -b feature/your-feature-name
  449. ```
  450. 3. **Commit your changes**
  451. ```bash
  452. git add .
  453. git commit -m "feat: add your feature"
  454. ```
  455. We recommend following the [Conventional Commits](https://www.conventionalcommits.org/) specification.
  456. 4. **Push your branch**
  457. ```bash
  458. git push origin feature/your-feature-name
  459. ```
  460. 5. **Open a Pull Request**
  461. - Describe your changes
  462. - Include screenshots or a recording for new UI features
  463. - Link related issues, if any
  464. ### Code Standards
  465. - Follow [PEP 8](https://pep8.org/) for Python code
  466. - Run `flake8` before submitting changes
  467. - Add relevant tests for new features
  468. - Keep commit messages clear and concise
  469. ### Reporting Bugs
  470. Report bugs through [GitHub Issues](https://github.com/Zafer-Liu/Data-Analysis-Agent/issues) and include:
  471. - ๐Ÿ“‹ Steps to reproduce
  472. - ๐ŸŽฏ Expected behavior
  473. - โš ๏ธ Actual behavior
  474. - ๐Ÿ“ธ Screenshots, when applicable
  475. - ๐Ÿ’ป Environment details, including OS and Python version
  476. ---
  477. ### ๐Ÿš€ Looking for Contributors
  478. A great open-source project is never a solo act.
  479. We're building a **data tool that can genuinely handle complex business scenarios** โ€” one that races through massive datasets, navigates multi-table logic with ease, and surfaces insights on visual dashboards.
  480. We've hit a few deeply challenging, high-value problems. If you love solving hard technical problems, we need you:
  481. ---
  482. ### Key challenges we'd love your help with:
  483. - **Multi-sheet inter-table logic optimization** โ€” How do you intelligently map dependencies and calculations across dozens of sheets?
  484. - **Visualization dashboard interactivity & performance** โ€” Making data stories flow more smoothly, intuitively, and powerfully.
  485. - **Model capability enhancement for specialized business scenarios** โ€” The edge cases that general-purpose tools can't handle.
  486. - **Remote server invocation** โ€” Building a framework for remote GPU calls.
  487. ---
  488. ### Why is it worth joining?
  489. - You'll tackle **real, deep, non-toy technical challenges**
  490. - Your code will directly impact the productivity of **front-line business users**
  491. - Contribute freely, collaborate flexibly โ€” submit a PR or reach out directly, entirely up to you
  492. - Outstanding contributors may be invited to become project Committers
  493. ---
  494. ### How to join?
  495. - Open a **Pull Request** directly โ€” we review within 24 hours
  496. - Or contact us at: `rusboldtshanti34@gmail.com` (please note "Contributor + area of expertise")
  497. - Join the official community: QQ Group `991636855` or [Telegram Group](https://t.me/+cdRNfS68u9BlYjJl) or [Discord](https://discord.gg/EEG4Sw7tde)
  498. ---
  499. <a id="license"></a>
  500. ## ๐Ÿ“„ License
  501. This software is licensed under **CC BY-NC 4.0** and a Chinese software copyright registration has been applied for (Acceptance No. 2026R11S0817877, Software: Natural-Language Interactive Business Data Analysis Software V1.0).
  502. See the [LICENSE](./LICENSE) file for the full terms.
  503. > Unauthorized commercial use is prohibited; contact the author for a separate commercial license.
  504. ---
  505. <a id="goal"></a>
  506. ## โญ Project Goal
  507. Leave the process to Business Analytics Agent, and save your time for thinking.
  508. ---
  509. <div align="center">
  510. โญ๏ธ If this project helps you, please give it a star!
  511. Made with โค๏ธ by [Zafer-Liu](https://github.com/Zafer-Liu)
  512. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If itโ€™s helped, pass it on.