docs: Fix Gemini API key variable name

README.md

@@ -7,26 +7,67 @@ sdk: docker
 pinned: false
 ---
 
-# MerchFlow AI - Open Source E-Commerce Agent
+# MerchFlow AI
 
 ![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)
 ![Python](https://img.shields.io/badge/Made%20with-Python-blue.svg)
+![FastAPI](https://img.shields.io/badge/FastAPI-005571?style=flat&logo=fastapi)
+![Docker](https://img.shields.io/badge/Docker-2496ED?style=flat&logo=docker&logoColor=white)
 
-## About
-MerchFlow AI is a **Multi-Agent System built in Pure Python (No LangChain)** that automates product listing generation using Enterprise-Grade Computer Vision. It leverages advanced visual analysis to streamline e-commerce workflows.
+MerchFlow AI is a high-performance, multi-agent orchestration system designed to automate the generation of premium e-commerce product listings. By synergizing Computer Vision, Retrieval Augmented Generation (RAG), and Large Language Models (LLMs), it transforms raw product images into SEO-optimized market-ready content.
 
-## Architecture
-The system operates through a coordinated pipeline:
-1.  **Input Image** → Raw processing
-2.  **Visual Analyst (Gemini 1.5)** → Extracts visual features and metadata
-3.  **Manager Agent** → Orchestrates data flow and decision making
-4.  **n8n Webhook (Self-Hosted)** → Triggers downstream automation and integration
+## 🏗️ Architecture Flow
 
-## Open Source Notice
-This project is open source under the MIT License. Feel free to fork and contribute.
+The system employs a sophisticated event-driven architecture orchestrated by **FastAPI**:
 
-## Setup
-To run this project, you need to configure the following Environment Variables:
+1.  **👁️ Visual Agent (Gemini 1.5)**
+    *   **Function**: Zero-shot image analysis.
+    *   **Process**: Extracts high-fidelity visual attributes including dominant color palettes, stylistic classifications, and granular item types.
+    *   **Engine**: Google Gemini 1.5 Flash (Vision).
 
-*   `GOOGLE_API_KEY`: Your Google Gemini API Key.
-*   `N8N_WEBHOOK_URL`: The URL for your self-hosted n8n webhook connector.
+2.  **🧠 Memory Agent (Pinecone)**
+    *   **Function**: Semantic Search & RAG.
+    *   **Process**: Vectorizes visual tags to query a high-dimensional index, retrieving historically high-performing SEO keywords and market trends relevant to the product.
+    *   **Engine**: Pinecone Vector Database.
+
+3.  **✍️ Writer Agent (Llama 3)**
+    *   **Function**: Creative Synthesis.
+    *   **Process**: Fuses visual data with retrieved market intelligence to generate persuasive, conversion-focused title, description, and feature bullets.
+    *   **Engine**: Meta Llama 3 (via Groq Cloud).
+
+4.  **⚙️ Orchestrator (FastAPI)**
+    *   **Function**: Async Pipeline Management.
+    *   **Process**: Handles non-blocking agent execution, error propagation, and API lifecycle management.
+
+5.  **🔗 Post-Processing (n8n)**
+    *   **Function**: Automation Webhook.
+    *   **Process**: Triggers downstream workflows (database storage, Shopify API integration) via secure webhooks upon successful generation.
+
+## 🚀 Complete Setup
+
+To run this system locally, ensure you have the following environment variables configured in your `.env` file:
+
+```env
+GEMINI_API_KEY=your_gemini_key
+GROQ_API_KEY=your_groq_key
+PINECONE_API_KEY=your_pinecone_key
+N8N_WEBHOOK_URL=your_n8n_webhook_url
+```
+
+## ⚡ Quick Start
+
+### 1. Installation
+Install the required dependencies using pip:
+
+```bash
+pip install -r requirements.txt
+```
+
+### 2. Execution
+Launch the FastAPI server:
+
+```bash
+python main.py
+```
+
+The API will be available at `http://localhost:7860`.