[kit] [mission-possible]Add EDA Copilot — AI-powered Exploratory Data Analysis agent [agentkit-challenge]#138
[kit] [mission-possible]Add EDA Copilot — AI-powered Exploratory Data Analysis agent [agentkit-challenge]#138A-b-h-a-y-0-2 wants to merge 3 commits intoLamatic:mainfrom
Conversation
- Replace raw fetch() with lamatic npm SDK (executeFlow method) - Lazy-init Lamatic client to fix build-time env var error - Update package.json to include lamatic@^0.3.2 - Update .env.example with correct endpoint URL format - Update orchestrate.js to reflect SDK-based flow definitions
Each flow now has its own directory containing all 4 required files: - config.json (Lamatic flow node graph) - inputs.json (input schema definition) - meta.json (name, description, author, tags, test inputs) - README.md (setup instructions and I/O docs) Flows restructured: - flows/eda-schema-analysis/ - flows/eda-statistical-insights/ - flows/eda-ml-readiness/ Also: update tsconfig.json with ES2017 target
|
Important Review skippedAuto reviews are limited based on label configuration. 🏷️ Required labels (at least one) (1)
Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Repository UI (base), Organization UI (inherited) Review profile: ASSERTIVE Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
A-b-h-a-y-0-2
changed the title
|
I can't add a label! |
1 participant
Contribution Type
kits/agentic/eda-copilot/)What is EDA Copilot?
Upload any CSV. Get instant AI-powered Exploratory Data Analysis in seconds — schema detection, statistical profiling, correlation analysis, outlier flagging, and ML readiness scoring — all powered by a 3-stage Lamatic.ai flow pipeline.
Problem Statement: Data scientists spend 60–80% of project time on EDA before any modeling begins. EDA Copilot automates the entire process: from raw CSV to actionable ML-ready insights, in one click.
How It Works
Three sequential Lamatic.ai flows form the agent pipeline:
eda-schema-analysiseda-statistical-insightseda-ml-readinessKey architectural decision: All heavy computation (mean, std, quartiles, Pearson correlation, skewness) runs client-side in the browser using a pure TypeScript EDA engine. Only a compact JSON summary is sent to Lamatic flows — keeping token usage low and making the app fast even on 100k+ row datasets.
Features
.mdreportFile Structure
kits/agentic/eda-copilot/
├── app/
│ ├── api/analyze/route.ts # Lamatic SDK gateway (3 sequential flows)
│ ├── page.tsx # Main UI — upload, progress, results
│ ├── layout.tsx
│ └── globals.css
├── actions/
│ └── orchestrate.js # Flow definitions & SDK config
├── components/
│ ├── FileUpload.tsx # Drag-and-drop CSV uploader
│ ├── DataPreview.tsx # Column chips + sample table
│ ├── AnalysisProgress.tsx # Live 3-step pipeline tracker
│ └── AnalysisResults.tsx # Charts + AI markdown panels
├── lib/
│ └── utils.ts # Client-side EDA engine
├── flows/
│ ├── eda-schema-analysis/ # config.json, inputs.json, meta.json, README.md
│ ├── eda-statistical-insights/
│ └── eda-ml-readiness/
├── config.json
├── .env.example
└── README.md
PR Checklist
kits/agentic/eda-copilot/).env.localis gitignoredkebab-case:eda-copilotREADME.md(purpose, setup, env vars, usage, architecture)config.jsonpresent with valid metadata (name, description, tags, steps, author, env keys)flows/<flow-name>/each includeconfig.json,inputs.json,meta.json,README.md.env.examplewith placeholder values onlynpm install && npm run devworks locally ✅ (Next.js build passes with 0 errors)[kit]prefixTech Stack
lamaticnpm package (executeFlowmethod)Environment Variables
LAMATIC_API_URLhttps://org-project.lamatic.dev)LAMATIC_PROJECT_IDLAMATIC_API_KEYEDA_SCHEMA_ANALYSIS_FLOW_IDEDA_STATISTICAL_INSIGHTS_FLOW_IDEDA_ML_READINESS_FLOW_ID