# yaml-language-server: $schema=https://schema.zeabur.app/template.json
apiVersion: zeabur.com/v1
kind: Template
metadata:
    name: RAG Service
spec:
    description: |
        Deploy your own RAG (Retrieval-Augmented Generation) service with admin dashboard.
        Hybrid search (semantic + BM25), API key management, query analytics, and knowledge learning API.
        Powered by InsForge (pgvector) and Zeabur AI Hub.
    variables:
        - key: PUBLIC_DOMAIN
          type: DOMAIN
          name: Domain
          description: Domain to bind the RAG service to
        - key: INSFORGE_URL
          type: STRING
          name: InsForge Project URL
          description: e.g. https://xxx.us-east.insforge.app
        - key: INSFORGE_API_KEY
          type: STRING
          name: InsForge API Key
          description: starts with ik_...
        - key: INSFORGE_KEY
          type: STRING
          name: InsForge Anon Key
          description: starts with eyJ...
        - key: ZEABUR_AI_HUB_API_KEY
          type: AI_HUB_KEY
          name: Zeabur AI Hub API Key
          description: Your Zeabur AI Hub API key for LLM inference
    tags:
        - AI
        - RAG
        - Search
    readme: |
        # RAG Service

        A complete RAG service with admin dashboard for managing your knowledge base.

        ## Getting Started

        ### Step 1: Create a Zeabur Project

        Go to [Zeabur Dashboard](https://zeabur.com/projects) and create a new project.

        ### Step 2: Enable InsForge

        In your project, go to **Integration → InsForge → Enable InsForge**. Additional charges may apply based on usage ([pricing details](https://zeabur.com/docs/en-US/integrations/insforge/overview)).

        ### Step 3: Get InsForge Credentials

        After enabling, open InsForge and go to **Project Settings → API** to find:

        - **Project URL** (`INSFORGE_URL`): e.g. `https://xxx.us-east.insforge.app`
        - **API Key** (`INSFORGE_API_KEY`): starts with `ik_...`
        - **Anon Key** (`INSFORGE_KEY`): starts with `eyJ...`

        ### Step 4: Deploy RAG Service

        In your project, click **Add Service → Marketplace**, search for **RAG Service**, and fill in:

        - The three InsForge credentials from Step 3
        - **Zeabur AI Hub API Key**: can be generated during deployment, or created in advance at [Zeabur AI Hub](https://zeabur.com/ai-hub)

        Schema migrations run automatically on first startup — no manual setup needed.

        ## Features

        - **Hybrid search**: semantic (pgvector) + BM25 keyword with RRF fusion
        - **Streaming RAG answers** via configurable LLM model
        - **Admin dashboard**: chunk browser, query signals, reports, audit log
        - **API key management** with scopes and expiry
        - **Knowledge learning API**: add new chunks via `/api/learn`
        - **Feedback collection** on query results

        ## API Endpoints

        | Endpoint | Method | Description |
        |----------|--------|-------------|
        | `/api/query` | POST | RAG search + answer |
        | `/api/learn` | POST | Add knowledge chunks |
        | `/api/report` | POST | Report data issues |
        | `/api/feedback` | POST | Submit feedback |
        | `/api/admin/*` | GET/POST | Admin API (API key management, signals, reports, chunks) |
        | `/dashboard` | GET | Admin dashboard (Basic Auth) |

        ## Environment Variables

        | Variable | Required | Description |
        |----------|----------|-------------|
        | `INSFORGE_URL` | Yes | InsForge backend URL |
        | `INSFORGE_KEY` | Yes | InsForge anon key |
        | `INSFORGE_API_KEY` | Yes | InsForge API key (ik_...) for schema migration |
        | `ZEABUR_AI_HUB_API_KEY` | Yes | Zeabur AI Hub key for LLM inference |
        | `RAG_API_KEY` | Auto | API key for service access (auto-generated) |
        | `RAG_BASIC_AUTH` | Auto | Dashboard auth (auto-generated, format admin:password) |
        | `RAG_MODEL` | No | LLM model (default: gemini-2.5-flash-lite) |
        | `CORS_ORIGIN` | No | CORS origin (default: service URL) |

        Schema migrations run automatically on first startup.

        ## License

        [MIT](https://github.com/zeabur/rag-service) — Built by [Zeabur](https://zeabur.com)
    services:
        - name: rag-service
          template: PREBUILT_V2
          spec:
            source:
                image: zeabur/rag-service:latest
            ports:
                - id: web
                  port: 3000
                  type: HTTP
            instructions:
                - title: Username
                  content: admin
                - title: Password / RAG_API_KEY
                  content: ${PASSWORD}
            env:
                CORS_ORIGIN:
                    default: ${ZEABUR_WEB_URL}
                INSFORGE_API_KEY:
                    default: ${INSFORGE_API_KEY}
                INSFORGE_KEY:
                    default: ${INSFORGE_KEY}
                INSFORGE_URL:
                    default: ${INSFORGE_URL}
                RAG_API_KEY:
                    default: ${PASSWORD}
                RAG_BASIC_AUTH:
                    default: admin:${PASSWORD}
                RAG_MODEL:
                    default: gemini-2.5-flash-lite
                ZEABUR_AI_HUB_API_KEY:
                    default: ${ZEABUR_AI_HUB_API_KEY}
                ZEABUR_AI_HUB_URL:
                    default: https://hnd1.aihub.zeabur.ai/v1
          domainKey: PUBLIC_DOMAIN