{"id":30729377,"url":"https://github.com/dsaikiran01/e-commerce-chat-assistant","last_synced_at":"2025-09-03T15:08:01.915Z","repository":{"id":311268125,"uuid":"1043198633","full_name":"dsaikiran01/E-commerce-Chat-Assistant","owner":"dsaikiran01","description":"AI Shopping Assistant built with LangGraph.js, MongoDB, and React. An intelligent agent that searches, reasons, and adapts like a real sales associate—powered by vector search, multi-turn memory, and dynamic tool use.","archived":false,"fork":false,"pushed_at":"2025-08-23T11:42:08.000Z","size":304,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-23T17:26:45.394Z","etag":null,"topics":["agentic-ai","gemini","langgraph","langgraph-js","mern","vector-search"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","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/dsaikiran01.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}},"created_at":"2025-08-23T10:48:13.000Z","updated_at":"2025-08-23T11:42:11.000Z","dependencies_parsed_at":"2025-08-23T17:33:53.284Z","dependency_job_id":"723b3468-9132-40e0-97d7-88f8f5b3b1cc","html_url":"https://github.com/dsaikiran01/E-commerce-Chat-Assistant","commit_stats":null,"previous_names":["dsaikiran01/e-commerce-chat-assistant"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/dsaikiran01/E-commerce-Chat-Assistant","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dsaikiran01%2FE-commerce-Chat-Assistant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dsaikiran01%2FE-commerce-Chat-Assistant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dsaikiran01%2FE-commerce-Chat-Assistant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dsaikiran01%2FE-commerce-Chat-Assistant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dsaikiran01","download_url":"https://codeload.github.com/dsaikiran01/E-commerce-Chat-Assistant/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dsaikiran01%2FE-commerce-Chat-Assistant/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273460881,"owners_count":25109821,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-03T02:00:09.631Z","response_time":76,"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":["agentic-ai","gemini","langgraph","langgraph-js","mern","vector-search"],"created_at":"2025-09-03T15:07:56.230Z","updated_at":"2025-09-03T15:08:01.896Z","avatar_url":"https://github.com/dsaikiran01.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🤖 AI Shopping Assistant with LangGraph.js \u0026 MongoDB\n\n\u003cdiv align=\"center\"\u003e\n\n![AI Agent](https://img.shields.io/badge/AI-Agent-blue?style=for-the-badge\u0026logo=openai)\n![LangGraph.js](https://img.shields.io/badge/LangGraph-JS-green?style=for-the-badge)\n![MongoDB](https://img.shields.io/badge/MongoDB-Atlas-green?style=for-the-badge\u0026logo=mongodb)\n![React](https://img.shields.io/badge/React-Frontend-blue?style=for-the-badge\u0026logo=react)\n\n**An AI-powered shopping assistant that interacts, reasons, and adapts like a real sales associate.**\n\n\u003c/div\u003e\n\n---\n\n## 🎯 Overview\n\nThis project is an advanced **AI Agent** for e-commerce, designed using an **agentic architecture**. Unlike traditional chatbots, this agent:\n\n- 🧠 **Thinks**: Determines the best course of action for a user's request\n- 🔍 **Acts**: Searches product catalogs using semantic vector embeddings\n- 🔄 **Adapts**: Falls back to keyword-based search if needed\n- 💬 **Remembers**: Maintains context over long conversations\n\n---\n\n## 📽️ Demo\n\nhttps://github.com/user-attachments/assets/1043b1d9-15c2-48fd-a4b5-d89daf41c0f3\n\n---\n\n## 🤔 Why Agentic AI?\n\n| 🤖 Traditional Chatbot | 🧠 Agentic AI System          |\n| ---------------------- | ----------------------------- |\n| Static replies         | Autonomous decision-making    |\n| No real tools          | Real-world API + search tools |\n| Single-turn dialogs    | Contextual, multi-turn memory |\n| No learning            | Adaptive and flexible         |\n\n---\n\n## 📚 Topics\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\"\u003e\n\n### 🧠 **Conceptual Knowledge**\n- Agentic AI architectures\n- LangGraph.js orchestration flows\n- Vector-based search using MongoDB Atlas\n- Multi-turn conversation design\n\n\u003c/td\u003e\n\u003ctd width=\"50%\"\u003e\n\n### 🛠️ **Technical Skills**\n- Node.js backend with REST APIs\n- AI integrations (OpenAI, Gemini)\n- React frontend with live AI chat\n- Seeding and embedding product data\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n---\n\n## 🚀 Prerequisites\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd\u003e\n\n### 📦 Software Requirements\n- [Node.js](https://nodejs.org/) (v18+)\n- Git \u0026 Terminal\n\n\u003c/td\u003e\n\u003ctd\u003e\n\n### 🔐 API Access\n- [Google AI API Key](https://aistudio.google.com/app/apikey)\n- [MongoDB Atlas URI](https://www.mongodb.com/cloud/atlas)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n---\n\n## ⚡ Quick Start\n\n### 1️⃣ Clone \u0026 Install Dependencies\n\n```bash\ngit clone https://github.com/dsaikiran01/E-commerce-Chat-Assistant.git\ncd E-commerce-Chat-Assistant/server\nnpm install\n````\n\n### 2️⃣ Setup Environment Variables\n\nCreate a `.env` file in the `/server` directory:\n\n```env\nPORT=8000\nGOOGLE_API_KEY=your_google_api_key\nMONGODB_ATLAS_URI=your_mongodb_uri\n```\n\n### 3️⃣ Seed the Database\n\n```bash\nnpm run seed\n```\n\n\u003cdetails\u003e\n\u003csummary\u003e🔍 What This Does\u003c/summary\u003e\n\n* Generates synthetic product data\n* Embeds item descriptions for vector search\n* Stores everything in MongoDB\n\n\u003c/details\u003e\n\n### 4️⃣ Start the Backend\n\n```bash\nnpm run dev\n```\n\nThe backend will be running on `http://localhost:8000`.\n\n---\n\n## 🧪 Try the Agent\n\n### Start a Conversation\n\n```bash\ncurl -X POST http://localhost:8000/chat \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"message\": \"I need a modern coffee table\"}'\n```\n\n### Continue the Conversation\n\n```bash\ncurl -X POST http://localhost:8000/chat/\u003cthreadId\u003e \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"message\": \"What's the price range?\"}'\n```\n\n---\n\n## 🖥️ Frontend Setup\n\n### 5️⃣ Launch React Client\n\n```bash\ncd ../client\nnpm install\nnpm run start\n```\n\nVisit `http://localhost:3000` to start chatting with your AI shopping assistant.\n\n---\n\n## 🧩 Architecture Diagram\n\n\u003cdiv align=\"center\"\u003e\n\n```mermaid\ngraph TD\n    A[User] --\u003e B[LangGraph Agent]\n    B --\u003e C{Decision Engine}\n    C --\u003e|Search| D[Vector Search Tool]\n    C --\u003e|Direct| E[Language Model Response]\n    D --\u003e F[MongoDB Atlas]\n    F --\u003e G[Search Results]\n    G --\u003e E\n    E --\u003e H[Final Response]\n```\n\n\u003c/div\u003e\n\n---\n\n## 🌟 Features\n\n| 🧠 Smart Decisions  | 🔍 Search Intelligence      | 💬 Conversational Memory |\n| ------------------- | --------------------------- | ------------------------ |\n| Dynamic tool usage  | Vector + fallback search    | Multi-turn support       |\n| Context-aware logic | Real-time inventory lookups | Persistent threads       |\n| Adaptive strategies | Semantic understanding      | Human-like tone          |\n\n---\n\n## 📡 API Reference\n\n| Method | Endpoint          | Description              |\n| ------ | ----------------- | ------------------------ |\n| `GET`  | `/`               | Health check             |\n| `POST` | `/chat`           | Start a new conversation |\n| `POST` | `/chat/:threadId` | Continue a conversation  |\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdsaikiran01%2Fe-commerce-chat-assistant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdsaikiran01%2Fe-commerce-chat-assistant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdsaikiran01%2Fe-commerce-chat-assistant/lists"}