add http api server

2026-05-09 17:13:53 +08:00
parent f31409bdba
commit 2563ab8f70
5 changed files with 482 additions and 7 deletions
--- a/.env.example
+++ b/.env.example
@@ -10,3 +10,19 @@ GEMINI_API_KEY="MY_GEMINI_API_KEY"
 # AI Studio automatically injects this at runtime with the Cloud Run service URL.
 # Used for self-referential links, OAuth callbacks, and API endpoints.
 APP_URL="MY_APP_URL"
+
+# API_PORT: HTTP API server port. Frontend still runs on 3000 by default.
+API_PORT="3002"
+
+# API_AUTH_TOKEN: Optional token for API calls. Leave empty to disable auth.
+# When set, send Authorization: Bearer <token> or x-api-key: <token>.
+API_AUTH_TOKEN=""
+
+# Gemini model defaults used by the API service.
+GEMINI_IMAGE_MODEL="gemini-3.1-flash-image-preview"
+GEMINI_TEXT_MODEL="gemini-2.5-flash"
+
+# Upload limits.
+API_MAX_FILE_MB="25"
+API_MAX_FILES="20"
+API_JSON_LIMIT="50mb"
--- a/README.md
+++ b/README.md
@@ -18,3 +18,43 @@ View your app in AI Studio: https://ai.studio/apps/96002e3b-5eec-4566-85e8-71871
 2. Set the `GEMINI_API_KEY` in [.env.local](.env.local) to your Gemini API key
 3. Run the app:
   `npm run dev`
+
+## Run the API server
+
+The UI runs on port `3000`. The HTTP API runs separately on port `3002`.
+
+1. Set `GEMINI_API_KEY` in `.env.local` or your shell.
+2. Start the API:
+   `npm run api`
+3. Check the API:
+   `http://localhost:3002/api/health`
+
+### API examples
+
+Generate or edit with JSON/base64:
+
+```bash
+curl -X POST http://localhost:3002/api/generate \
+  -H "Content-Type: application/json" \
+  -d "{\"prompt\":\"Create a clean product poster for a white coffee mug\",\"imageSize\":\"1K\",\"aspectRatio\":\"1:1\"}"
+```
+
+Upload an image or document with a prompt:
+
+```bash
+curl -X POST http://localhost:3002/api/generate/upload \
+  -F "prompt=Change the background to a bright studio scene" \
+  -F "imageSize=1K" \
+  -F "aspectRatio=1:1" \
+  -F "files=@input.png"
+```
+
+Analyze a document:
+
+```bash
+curl -X POST http://localhost:3002/api/analyze-document \
+  -F "prompt=Summarize this document in Chinese" \
+  -F "files=@report.pdf"
+```
+
+Optional API auth: set `API_AUTH_TOKEN`, then send either `Authorization: Bearer <token>` or `x-api-key: <token>`.
--- a/package-lock.json
+++ b/package-lock.json
@@ -16,12 +16,14 @@
        "express": "^4.21.2",
        "lucide-react": "^0.546.0",
        "motion": "^12.23.24",
+        "multer": "^2.1.1",
        "react": "^19.0.0",
        "react-dom": "^19.0.0",
        "vite": "^6.2.0"
      },
      "devDependencies": {
        "@types/express": "^4.17.21",
+        "@types/multer": "^2.1.0",
        "@types/node": "^22.14.0",
        "autoprefixer": "^10.4.21",
        "tailwindcss": "^4.1.14",
@@ -1537,6 +1539,16 @@
      "dev": true,
      "license": "MIT"
    },
+    "node_modules/@types/multer": {
+      "version": "2.1.0",
+      "resolved": "https://registry.npmjs.org/@types/multer/-/multer-2.1.0.tgz",
+      "integrity": "sha512-zYZb0+nJhOHtPpGDb3vqPjwpdeGlGC157VpkqNQL+UU2qwoacoQ7MpsAmUptI/0Oa127X32JzWDqQVEXp2RcIA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@types/express": "*"
+      }
+    },
    "node_modules/@types/node": {
      "version": "22.19.17",
      "resolved": "https://registry.npmjs.org/@types/node/-/node-22.19.17.tgz",
@@ -1641,6 +1653,12 @@
        "node": ">= 14"
      }
    },
+    "node_modules/append-field": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/append-field/-/append-field-1.0.0.tgz",
+      "integrity": "sha512-klpgFSWLW1ZEs8svjfb7g4qWY0YS5imI82dTg+QahUvJ8YqAY0P10Uk8tTyh9ZGuYEZEMaeJYCF5BFuX552hsw==",
+      "license": "MIT"
+    },
    "node_modules/array-flatten": {
      "version": "1.1.1",
      "resolved": "https://registry.npmjs.org/array-flatten/-/array-flatten-1.1.1.tgz",
@@ -1861,6 +1879,23 @@
      "integrity": "sha512-zRpUiDwd/xk6ADqPMATG8vc9VPrkck7T07OIx0gnjmJAnHnTVXNQG3vfvWNuiZIkwu9KrKdA1iJKfsfTVxE6NA==",
      "license": "BSD-3-Clause"
    },
+    "node_modules/buffer-from": {
+      "version": "1.1.2",
+      "resolved": "https://registry.npmjs.org/buffer-from/-/buffer-from-1.1.2.tgz",
+      "integrity": "sha512-E+XQCRwSbaaiChtv6k6Dwgc+bx+Bs6vuKJHHl5kox/BaKbhiXzqQOwK4cO22yElGp2OCmjwVhT3HmxgyPGnJfQ==",
+      "license": "MIT"
+    },
+    "node_modules/busboy": {
+      "version": "1.6.0",
+      "resolved": "https://registry.npmjs.org/busboy/-/busboy-1.6.0.tgz",
+      "integrity": "sha512-8SFQbg/0hQ9xy3UNTB0YEnsNBbWfhf7RtnzpL7TkBiTBRfrQ9Fxcnz7VJsleJpyp6rVLvXiuORqjlHi5q+PYuA==",
+      "dependencies": {
+        "streamsearch": "^1.1.0"
+      },
+      "engines": {
+        "node": ">=10.16.0"
+      }
+    },
    "node_modules/bytes": {
      "version": "3.1.2",
      "resolved": "https://registry.npmjs.org/bytes/-/bytes-3.1.2.tgz",
@@ -1925,6 +1960,21 @@
      "integrity": "sha512-jJ0bqzaylmJtVnNgzTeSOs8DPavpbYgEr/b0YL8/2GO3xJEhInFmhKMUnEJQjZumK7KXGFhUy89PrsJWlakBVg==",
      "license": "ISC"
    },
+    "node_modules/concat-stream": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/concat-stream/-/concat-stream-2.0.0.tgz",
+      "integrity": "sha512-MWufYdFw53ccGjCA+Ol7XJYpAlW6/prSMzuPOTRnJGcGzuhLn4Scrz7qf6o8bROZ514ltazcIFJZevcfbo0x7A==",
+      "engines": [
+        "node >= 6.0"
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "buffer-from": "^1.0.0",
+        "inherits": "^2.0.3",
+        "readable-stream": "^3.0.2",
+        "typedarray": "^0.0.6"
+      }
+    },
    "node_modules/content-disposition": {
      "version": "0.5.4",
      "resolved": "https://registry.npmjs.org/content-disposition/-/content-disposition-0.5.4.tgz",
@@ -3215,6 +3265,25 @@
      "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==",
      "license": "MIT"
    },
+    "node_modules/multer": {
+      "version": "2.1.1",
+      "resolved": "https://registry.npmjs.org/multer/-/multer-2.1.1.tgz",
+      "integrity": "sha512-mo+QTzKlx8R7E5ylSXxWzGoXoZbOsRMpyitcht8By2KHvMbf3tjwosZ/Mu/XYU6UuJ3VZnODIrak5ZrPiPyB6A==",
+      "license": "MIT",
+      "dependencies": {
+        "append-field": "^1.0.0",
+        "busboy": "^1.6.0",
+        "concat-stream": "^2.0.0",
+        "type-is": "^1.6.18"
+      },
+      "engines": {
+        "node": ">= 10.16.0"
+      },
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/express"
+      }
+    },
    "node_modules/nanoid": {
      "version": "3.3.11",
      "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.11.tgz",
@@ -3901,6 +3970,14 @@
        "node": ">= 0.8"
      }
    },
+    "node_modules/streamsearch": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/streamsearch/-/streamsearch-1.1.0.tgz",
+      "integrity": "sha512-Mcc5wHehp9aXz1ax6bZUyY5afg9u2rv5cqQI3mRrYkGC8rW2hM02jWuwjtL++LS5qinSyhj2QfLyNsuc+VsExg==",
+      "engines": {
+        "node": ">=10.0.0"
+      }
+    },
    "node_modules/string_decoder": {
      "version": "1.3.0",
      "resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.3.0.tgz",
@@ -4042,6 +4119,12 @@
        "node": ">= 0.6"
      }
    },
+    "node_modules/typedarray": {
+      "version": "0.0.6",
+      "resolved": "https://registry.npmjs.org/typedarray/-/typedarray-0.0.6.tgz",
+      "integrity": "sha512-/aCDEGatGvZ2BIk+HmLf4ifCJFwvKFNb9/JeZPMulfgFracn9QFcAf5GO8B/mweUjSoblS5In0cWhqpfs/5PQA==",
+      "license": "MIT"
+    },
    "node_modules/typescript": {
      "version": "5.8.3",
      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.8.3.tgz",
--- a/package.json
+++ b/package.json
@@ -5,6 +5,7 @@
  "type": "module",
  "scripts": {
    "dev": "vite --port=3000 --host=0.0.0.0",
+    "api": "tsx server/index.ts",
    "build": "vite build",
    "preview": "vite preview",
    "clean": "rm -rf dist",
@@ -14,22 +15,24 @@
    "@google/genai": "^1.29.0",
    "@tailwindcss/vite": "^4.1.14",
    "@vitejs/plugin-react": "^5.0.4",
+    "better-sqlite3": "^12.4.1",
+    "dotenv": "^17.2.3",
+    "express": "^4.21.2",
    "lucide-react": "^0.546.0",
+    "motion": "^12.23.24",
+    "multer": "^2.1.1",
    "react": "^19.0.0",
    "react-dom": "^19.0.0",
-    "vite": "^6.2.0",
-    "express": "^4.21.2",
-    "dotenv": "^17.2.3",
-    "better-sqlite3": "^12.4.1",
-    "motion": "^12.23.24"
+    "vite": "^6.2.0"
  },
  "devDependencies": {
+    "@types/express": "^4.17.21",
+    "@types/multer": "^2.1.0",
    "@types/node": "^22.14.0",
    "autoprefixer": "^10.4.21",
    "tailwindcss": "^4.1.14",
    "tsx": "^4.21.0",
    "typescript": "~5.8.2",
-    "vite": "^6.2.0",
-    "@types/express": "^4.17.21"
+    "vite": "^6.2.0"
  }
 }
--- a/server/index.ts
+++ b/server/index.ts
@@ -0,0 +1,333 @@
+import 'dotenv/config';
+import express from 'express';
+import multer from 'multer';
+import { GoogleGenAI } from '@google/genai';
+
+type InlineInput = {
+  name?: string;
+  mimeType?: string;
+  data?: string;
+  base64?: string;
+  dataUrl?: string;
+  url?: string;
+};
+
+type GenerateRequest = {
+  prompt?: string;
+  instruction?: string;
+  model?: string;
+  imageSize?: '1K' | '2K' | '4K';
+  aspectRatio?: '1:1' | '4:3' | '3:4' | '16:9' | '9:16';
+  images?: InlineInput[];
+  documents?: InlineInput[];
+  files?: InlineInput[];
+};
+
+type GeminiPart = {
+  text?: string;
+  inlineData?: {
+    data: string;
+    mimeType: string;
+  };
+};
+
+const app = express();
+const upload = multer({
+  storage: multer.memoryStorage(),
+  limits: {
+    fileSize: Number(process.env.API_MAX_FILE_MB || 25) * 1024 * 1024,
+    files: Number(process.env.API_MAX_FILES || 20),
+  },
+});
+
+const apiKey = process.env.GEMINI_API_KEY || process.env.API_KEY;
+const apiPort = Number(process.env.API_PORT || 3002);
+const defaultImageModel = process.env.GEMINI_IMAGE_MODEL || 'gemini-3.1-flash-image-preview';
+const defaultTextModel = process.env.GEMINI_TEXT_MODEL || 'gemini-2.5-flash';
+const apiAuthToken = process.env.API_AUTH_TOKEN || '';
+
+if (!apiKey) {
+  console.warn('GEMINI_API_KEY/API_KEY is not set. API calls will fail until it is configured.');
+}
+
+const ai = new GoogleGenAI({ apiKey });
+
+app.use((req, res, next) => {
+  res.setHeader('Access-Control-Allow-Origin', process.env.API_CORS_ORIGIN || '*');
+  res.setHeader('Access-Control-Allow-Methods', 'GET,POST,OPTIONS');
+  res.setHeader('Access-Control-Allow-Headers', 'Content-Type,Authorization,x-api-key');
+  if (req.method === 'OPTIONS') {
+    res.status(204).end();
+    return;
+  }
+  next();
+});
+
+app.use(express.json({ limit: process.env.API_JSON_LIMIT || '50mb' }));
+
+function requireAuth(req: express.Request, res: express.Response, next: express.NextFunction) {
+  if (!apiAuthToken) {
+    next();
+    return;
+  }
+
+  const authHeader = req.header('authorization') || '';
+  const bearerToken = authHeader.startsWith('Bearer ') ? authHeader.slice(7) : '';
+  const headerToken = req.header('x-api-key') || '';
+
+  if (bearerToken === apiAuthToken || headerToken === apiAuthToken) {
+    next();
+    return;
+  }
+
+  res.status(401).json({
+    ok: false,
+    error: 'Unauthorized. Send Authorization: Bearer <API_AUTH_TOKEN> or x-api-key.',
+  });
+}
+
+function stripDataPrefix(value: string) {
+  const match = value.match(/^data:([^;]+);base64,(.+)$/);
+  if (!match) {
+    return null;
+  }
+  return {
+    mimeType: match[1],
+    data: match[2],
+  };
+}
+
+async function fetchAsBase64(url: string) {
+  const response = await fetch(url);
+  if (!response.ok) {
+    throw new Error(`Failed to fetch ${url}: ${response.status} ${response.statusText}`);
+  }
+
+  const contentLength = Number(response.headers.get('content-length') || 0);
+  const maxBytes = Number(process.env.API_MAX_URL_MB || 25) * 1024 * 1024;
+  if (contentLength > maxBytes) {
+    throw new Error(`Remote file is too large. Max size is ${process.env.API_MAX_URL_MB || 25}MB.`);
+  }
+
+  const buffer = Buffer.from(await response.arrayBuffer());
+  if (buffer.length > maxBytes) {
+    throw new Error(`Remote file is too large. Max size is ${process.env.API_MAX_URL_MB || 25}MB.`);
+  }
+
+  return {
+    data: buffer.toString('base64'),
+    mimeType: response.headers.get('content-type')?.split(';')[0] || 'application/octet-stream',
+  };
+}
+
+async function inlineInputToPart(input: InlineInput): Promise<GeminiPart> {
+  if (input.dataUrl) {
+    const parsed = stripDataPrefix(input.dataUrl);
+    if (!parsed) {
+      throw new Error(`Invalid dataUrl${input.name ? ` for ${input.name}` : ''}.`);
+    }
+    return {
+      inlineData: {
+        data: parsed.data,
+        mimeType: input.mimeType || parsed.mimeType,
+      },
+    };
+  }
+
+  if (input.url) {
+    const fetched = await fetchAsBase64(input.url);
+    return {
+      inlineData: {
+        data: fetched.data,
+        mimeType: input.mimeType || fetched.mimeType,
+      },
+    };
+  }
+
+  const rawData = input.base64 || input.data;
+  if (!rawData) {
+    throw new Error(`File input${input.name ? ` ${input.name}` : ''} is missing data, base64, dataUrl, or url.`);
+  }
+
+  const parsed = stripDataPrefix(rawData);
+  return {
+    inlineData: {
+      data: parsed?.data || rawData,
+      mimeType: input.mimeType || parsed?.mimeType || 'application/octet-stream',
+    },
+  };
+}
+
+function uploadedFileToPart(file: Express.Multer.File): GeminiPart {
+  return {
+    inlineData: {
+      data: file.buffer.toString('base64'),
+      mimeType: file.mimetype || 'application/octet-stream',
+    },
+  };
+}
+
+async function buildParts(body: GenerateRequest, files: Express.Multer.File[] = []) {
+  const prompt = (body.prompt || body.instruction || '').trim();
+  if (!prompt) {
+    throw new Error('prompt or instruction is required.');
+  }
+
+  const inlineInputs = [
+    ...(body.images || []),
+    ...(body.documents || []),
+    ...(body.files || []),
+  ];
+
+  const parts: GeminiPart[] = [];
+  for (const input of inlineInputs) {
+    parts.push(await inlineInputToPart(input));
+  }
+
+  for (const file of files) {
+    parts.push(uploadedFileToPart(file));
+  }
+
+  parts.push({ text: prompt });
+  return parts;
+}
+
+function normalizeMultipartBody(req: express.Request): GenerateRequest {
+  return {
+    prompt: String(req.body.prompt || req.body.instruction || ''),
+    model: req.body.model,
+    imageSize: req.body.imageSize,
+    aspectRatio: req.body.aspectRatio,
+  };
+}
+
+function collectResponseParts(response: any) {
+  const images: Array<{ mimeType: string; data: string; dataUrl: string }> = [];
+  const texts: string[] = [];
+
+  for (const candidate of response.candidates || []) {
+    for (const part of candidate.content?.parts || []) {
+      if (part.inlineData?.data) {
+        const mimeType = part.inlineData.mimeType || 'image/png';
+        images.push({
+          mimeType,
+          data: part.inlineData.data,
+          dataUrl: `data:${mimeType};base64,${part.inlineData.data}`,
+        });
+      }
+      if (part.text) {
+        texts.push(part.text);
+      }
+    }
+  }
+
+  return { images, texts };
+}
+
+async function runGemini(body: GenerateRequest, files: Express.Multer.File[] = [], textOnly = false) {
+  const parts = await buildParts(body, files);
+  const model = body.model || (textOnly ? defaultTextModel : defaultImageModel);
+  const config: Record<string, unknown> = {};
+
+  if (!textOnly) {
+    config.imageConfig = {
+      imageSize: body.imageSize || '1K',
+      aspectRatio: body.aspectRatio || '1:1',
+    };
+  }
+
+  const response = await ai.models.generateContent({
+    model,
+    contents: { parts } as any,
+    config,
+  } as any);
+
+  const { images, texts } = collectResponseParts(response);
+
+  return {
+    ok: true,
+    model,
+    input: {
+      fileCount: files.length + (body.images?.length || 0) + (body.documents?.length || 0) + (body.files?.length || 0),
+      partCount: parts.length,
+      imageSize: textOnly ? undefined : body.imageSize || '1K',
+      aspectRatio: textOnly ? undefined : body.aspectRatio || '1:1',
+    },
+    images,
+    texts,
+    usageMetadata: response.usageMetadata,
+  };
+}
+
+function handleError(res: express.Response, error: unknown) {
+  const message = error instanceof Error ? error.message : String(error);
+  res.status(400).json({
+    ok: false,
+    error: message,
+  });
+}
+
+app.get('/api', (_req, res) => {
+  res.json({
+    ok: true,
+    name: 'Gemini Draw API',
+    endpoints: [
+      'GET /api/health',
+      'POST /api/generate',
+      'POST /api/generate/upload',
+      'POST /api/edit-image',
+      'POST /api/analyze-document',
+    ],
+  });
+});
+
+app.get('/api/health', (_req, res) => {
+  res.json({
+    ok: true,
+    apiPort,
+    hasGeminiApiKey: Boolean(apiKey),
+    authEnabled: Boolean(apiAuthToken),
+    defaultImageModel,
+    defaultTextModel,
+  });
+});
+
+app.post('/api/generate', requireAuth, async (req, res) => {
+  try {
+    res.json(await runGemini(req.body));
+  } catch (error) {
+    handleError(res, error);
+  }
+});
+
+app.post('/api/generate/upload', requireAuth, upload.any(), async (req, res) => {
+  try {
+    res.json(await runGemini(normalizeMultipartBody(req), (req.files as Express.Multer.File[]) || []));
+  } catch (error) {
+    handleError(res, error);
+  }
+});
+
+app.post('/api/edit-image', requireAuth, upload.any(), async (req, res) => {
+  try {
+    const files = (req.files as Express.Multer.File[]) || [];
+    const body = req.is('multipart/form-data') ? normalizeMultipartBody(req) : req.body;
+    res.json(await runGemini(body, files));
+  } catch (error) {
+    handleError(res, error);
+  }
+});
+
+app.post('/api/analyze-document', requireAuth, upload.any(), async (req, res) => {
+  try {
+    const files = (req.files as Express.Multer.File[]) || [];
+    const body = req.is('multipart/form-data') ? normalizeMultipartBody(req) : req.body;
+    res.json(await runGemini(body, files, true));
+  } catch (error) {
+    handleError(res, error);
+  }
+});
+
+app.listen(apiPort, '0.0.0.0', () => {
+  console.log(`Gemini Draw API listening on http://localhost:${apiPort}`);
+});