Livrare LOT 1 - Didi

ai_platform/modules/gateway/README.md

@@ -0,0 +1,87 @@
+# Gateway
+
+Nginx reverse proxy that serves as the **single entry point** for all didiAI services. All requests (except `/health`) require Bearer token authentication.
+
+## Prerequisites
+
+- All global prerequisites (see main [README.md](../../README.md))
+- Docker network `deploy_default` (shared with other modules)
+- At least one backend service running (llm-inference, audio, web, catalog-api)
+
+## Routes
+
+| Route | Upstream | Description |
+|-------|----------|-------------|
+| `/health` | (nginx direct) | Health check, no auth required |
+| `/llm/` | `didiAI-llm-api:14011` | LLM Inference API (SSE streaming enabled) |
+| `/audio/` | `didiAI-audio-api:54300` | Audio Transcription API (10M body buffer) |
+| `/web/` | `didiAI-web-api:51100` | Web Fact-checking API |
+| `/catalog/` | `didiAI-catalog-api:11000` | Catalog API (service discovery) |
+| `/embeddings/` | `didiAI-embeddings-api:14100` | Embeddings API (OpenAI-compatible) |
+| `/rerank/` | `didiAI-rerank-api:14200` | Rerank API (Cohere/Jina-compatible) |
+
+## Authentication
+
+All routes except `/health` require a Bearer token:
+
+```
+Authorization: Bearer <GATEWAY_API_TOKEN>
+```
+
+Unauthorized requests receive:
+```json
+{"error": "unauthorized", "message": "Invalid or missing Bearer token"}
+```
+
+## Configuration
+
+| Variable | Required | Description |
+|----------|----------|-------------|
+| `GATEWAY_API_TOKEN` | Yes | Bearer token for authentication |
+
+## Quick Start
+
+```bash
+cd deploy/
+
+# Configure
+cp .env.example .env
+# Edit .env and set GATEWAY_API_TOKEN
+
+# Start
+docker compose up -d
+
+# Test
+curl http://localhost:11000/health
+curl -H "Authorization: Bearer <token>" http://localhost:11000/llm/health
+```
+
+## Port
+
+| Port | Service | Description |
+|------|---------|-------------|
+| 11000 | Gateway | Only externally exposed port for the platform |
+
+## Proxy Settings
+
+- **Connect timeout:** 60s
+- **Send timeout:** 300s
+- **Read timeout:** 600s
+- **Max upload size:** 500MB
+- **Request ID:** Auto-generated `X-Request-ID` header on all requests
+
+## Architecture
+
+```
+Client
+  |
+  v
+Gateway (nginx :11000) ---> Bearer token check
+  |
+  +-- /llm/        --> didiAI-llm-api:14011        (SSE streaming)
+  +-- /audio/      --> didiAI-audio-api:54300       (large uploads)
+  +-- /web/        --> didiAI-web-api:51100
+  +-- /catalog/    --> didiAI-catalog-api:11000
+  +-- /embeddings/ --> didiAI-embeddings-api:14100
+  +-- /rerank/     --> didiAI-rerank-api:14200
+```