{"id":51018592,"url":"https://github.com/kaverikb/smartledger","last_synced_at":"2026-06-21T14:01:15.963Z","repository":{"id":355599525,"uuid":"1228769701","full_name":"kaverikb/SmartLedger","owner":"kaverikb","description":"A full-stack financial dashboard that visualizes spending patterns with interactive charts and allows querying insights via natural language. It uses a React frontend, a FastAPI backend, and is designed for cloud deployment using Docker.","archived":false,"fork":false,"pushed_at":"2026-05-04T11:13:27.000Z","size":220,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-04T13:18:31.115Z","etag":null,"topics":["dashboard-application","fastapi","python","reactjs"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kaverikb.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-04T11:06:35.000Z","updated_at":"2026-05-04T11:13:32.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/kaverikb/SmartLedger","commit_stats":null,"previous_names":["kaverikb/smartledger"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/kaverikb/SmartLedger","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaverikb%2FSmartLedger","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaverikb%2FSmartLedger/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaverikb%2FSmartLedger/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaverikb%2FSmartLedger/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kaverikb","download_url":"https://codeload.github.com/kaverikb/SmartLedger/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaverikb%2FSmartLedger/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34610832,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-21T02:00:05.568Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["dashboard-application","fastapi","python","reactjs"],"created_at":"2026-06-21T14:01:14.941Z","updated_at":"2026-06-21T14:01:15.931Z","avatar_url":"https://github.com/kaverikb.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Smart Ledger\n\nSmart Ledger is an end-to-end financial analytics dashboard that combines data processing, anomaly detection, and natural language querying to help users understand their spending behavior.\n\nThe system integrates a FastAPI backend, a React-based frontend, and a hybrid query engine that leverages large language models for intent parsing while maintaining deterministic computation for accuracy.\n\n---\n\n## Overview\n\nSmart Ledger allows users to:\n\n* Analyze total and category-wise spending\n* Explore monthly spending trends\n* Detect anomalous transactions\n* Interactively query financial data using natural language\n\nThe system is designed to balance flexibility and correctness by separating language understanding from computation.\n\n---\n\n## Features\n\n### Financial Summary\n\n* Total spending overview\n* Top spending category identification\n\n### Data Visualization\n\n* Monthly spending distribution (bar chart)\n* Category-wise spending distribution (pie chart)\n* Monthly category breakdown (interactive donut chart)\n\n### Transaction Analysis\n\n* Tabular view of transactions\n* Highlighted anomalies for unusual spending patterns\n\n### Natural Language Query System\n\nUsers can ask questions such as:\n\n* How much did I spend in March?\n* Where did I spend the most?\n* What is my average spending?\n* Show anomalies\n\nThe system interprets queries and returns precise answers based on structured data.\n\n---\n\n## System Architecture\n\nFrontend (React)\n→ API Calls\n→ FastAPI Backend\n→ Query Engine (LLM + Rule Logic)\n→ Pandas Data Processing\n→ Response to Frontend\n\n---\n\n## Tech Stack\n\n### Backend\n\n* Python\n* FastAPI\n* Pandas\n* Requests\n* OpenRouter API (LLM integration)\n\n### Frontend\n\n* React.js\n* Recharts\n\n### Utilities\n\n* dotenv for environment variables\n* REST APIs for communication\n\n---\n\n## How It Works\n\n### Query Processing Pipeline\n\n1. User enters a natural language query\n2. LLM parses the query into structured fields:\n\n   * intent\n   * category\n   * month\n3. Backend filters and aggregates data using Pandas\n4. A formatted response is returned to the UI\n\nExample:\n\nQuery:\nHow much did I spend in March\n\nParsed:\n{\n\"intent\": \"total_spending\",\n\"category\": null,\n\"month\": \"03\"\n}\n\nResponse:\nYou spent ₹XXXXX in March\n\n---\n\n## Key Design Decision\n\nThe system follows a hybrid approach:\n\n* LLM is used only for understanding user intent\n* All numerical computation is performed using structured data processing\n\nThis prevents hallucinations and ensures consistent, reliable outputs.\n\n---\n\n## Project Structure\n\n```\nSmartLedger/\n│\n├── backend/\n│   ├── app/\n│   │   ├── routes/\n│   │   │   ├── summary.py\n│   │   │   ├── transactions.py\n│   │   │   └── chat.py\n│   │   ├── services/\n│   │   │   ├── data_loader.py\n│   │   │   └── query_engine.py\n│   │   └── main.py\n│   ├── requirements.txt\n│\n├── frontend/\n│   ├── src/\n│   │   ├── App.js\n│   │   ├── App.css\n│   │   └── ...\n│   ├── public/\n│   └── package.json\n│\n├── docker-compose.yml\n├── .env.example\n├── .gitignore\n└── README.md\n```\n\n## Setup Instructions\n\n### Backend\n\ncd backend\npython -m venv venv\nvenv\\Scripts\\activate\npip install -r requirements.txt\n\nCreate a .env file:\n\nOPENROUTER_API_KEY=your_api_key_here\n\nRun backend:\n\nuvicorn app.main:app --reload\n\n---\n\n### Frontend\n\ncd frontend\nnpm install\nnpm start\n\n---\n\n## API Endpoints\n\n### GET /summary\n\nReturns:\n\n* total_spent\n* top_category\n* category_breakdown\n* monthly_trend\n\n---\n\n### GET /transactions\n\nReturns full transaction dataset with:\n\n* categories\n* timestamps\n* anomaly flags\n\n---\n\n### GET /ask?query=\n\nReturns:\n\n* natural language response based on user query\n\n---\n\n## Limitations\n\n* Limited handling of highly complex or ambiguous queries\n* No conversational memory across multiple queries\n* Dependence on external LLM API\n* Static dataset (no real-time financial integration)\n\n---\n\n## Future Improvements\n\n* Conversational memory and context retention\n* Advanced query understanding using embeddings\n* Forecasting and predictive analytics\n* Deployment using Docker and cloud services\n* Multi-user support and authentication\n\n---\n\n## Summary\n\nSmart Ledger demonstrates a practical implementation of combining large language models with structured data systems. It ensures both flexibility in interaction and accuracy in computation, making it suitable for real-world financial analytics use cases.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkaverikb%2Fsmartledger","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkaverikb%2Fsmartledger","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkaverikb%2Fsmartledger/lists"}