superbrain-server 1.0.2-beta.0

package/bin/superbrain.js

@@ -0,0 +1,196 @@
+#!/usr/bin/env node
+const fs = require('fs');
+const path = require('path');
+const os = require('os');
+const { spawnSync, spawn } = require('child_process');
+
+const pkgMeta = require('../package.json');
+const TARGET_DIR = path.join(os.homedir(), '.superbrain-server');
+const PAYLOAD_DIR = path.join(__dirname, '../payload');
+
+// Files that should NEVER be overwritten during an unpack/upgrade if they already exist in the target
+const PROTECTED_FILES = [
+  'superbrain.db',
+  'superbrain.db-shm',
+  'superbrain.db-wal',
+  'token.txt',
+  '.env',
+  '.api_keys',
+  'localtunnel.log',
+  'localtunnel_enabled.txt',
+  '.setup_done',
+  'config/instagram_session.json',
+  'config/.api_keys',
+  'config/localtunnel_enabled.txt',
+  'config/localtunnel.log'
+];
+
+function log(msg) {
+  console.log(`\x1b[36m✨ [SuperBrain CLI]\x1b[0m ${msg}`);
+}
+
+function warn(msg) {
+  console.log(`\x1b[33m⚠️ [SuperBrain CLI]\x1b[0m ${msg}`);
+}
+
+function errorOut(msg) {
+  console.log(`\x1b[31m❌ [SuperBrain CLI]\x1b[0m ${msg}`);
+  process.exit(1);
+}
+
+function parsePythonVersion(rawText) {
+  const match = (rawText || '').match(/Python\s+(\d+)\.(\d+)\.(\d+)/i);
+  if (!match) return null;
+  return {
+    major: Number(match[1]),
+    minor: Number(match[2]),
+    patch: Number(match[3]),
+  };
+}
+
+function isSupportedPython(version) {
+  if (!version) return false;
+  if (version.major > 3) return true;
+  return version.major === 3 && version.minor >= 10;
+}
+
+// Check if Python binaries are accessible
+function getPythonCommand() {
+  const candidates = os.platform() === 'win32'
+    ? [
+      { cmd: 'py', args: ['-3', '--version'], execPrefix: ['-3'] },
+      { cmd: 'python', args: ['--version'], execPrefix: [] },
+      { cmd: 'python3', args: ['--version'], execPrefix: [] },
+    ]
+    : [
+      { cmd: 'python3', args: ['--version'], execPrefix: [] },
+      { cmd: 'python', args: ['--version'], execPrefix: [] },
+    ];
+  
+  for (const candidate of candidates) {
+    try {
+      const res = spawnSync(candidate.cmd, candidate.args, { encoding: 'utf-8', timeout: 5000 });
+      const combinedOutput = `${res.stdout || ''}\n${res.stderr || ''}`.trim();
+      const version = parsePythonVersion(combinedOutput);
+
+      if (res.status === 0 && isSupportedPython(version)) {
+        return {
+          command: candidate.cmd,
+          execPrefix: candidate.execPrefix,
+          version,
+        };
+      }
+    } catch (e) {
+      // Command missing
+    }
+  }
+  return null;
+}
+
+function safeUnpack() {
+  if (!fs.existsSync(TARGET_DIR)) {
+    fs.mkdirSync(TARGET_DIR, { recursive: true });
+  }
+
+  log(`Unpacking server core to ${TARGET_DIR} ...`);
+
+  // Recursively copy files from payload
+  function copyRecursive(src, dest) {
+    const stat = fs.statSync(src);
+    if (stat.isDirectory()) {
+      if (!fs.existsSync(dest)) fs.mkdirSync(dest);
+      for (const child of fs.readdirSync(src)) {
+        copyRecursive(path.join(src, child), path.join(dest, child));
+      }
+    } else {
+      // It's a file
+      const relativePath = path.relative(TARGET_DIR, dest).replace(/\\/g, '/');
+      const isProtected = PROTECTED_FILES.includes(relativePath);
+      
+      if (isProtected && fs.existsSync(dest)) {
+        // Skip overwriting user's database or tokens
+        return;
+      }
+      fs.copyFileSync(src, dest);
+    }
+  }
+
+  if (!fs.existsSync(PAYLOAD_DIR)) {
+    errorOut("Payload directory missing inside npm package!");
+  }
+  
+  copyRecursive(PAYLOAD_DIR, TARGET_DIR);
+
+  // Write out version explicitly
+  fs.writeFileSync(path.join(TARGET_DIR, 'VERSION'), pkgMeta.version, 'utf-8');
+  log(`Extraction complete (v${pkgMeta.version}). Data persisted cleanly.`);
+}
+
+function checkUpgrades() {
+  const versionFile = path.join(TARGET_DIR, 'VERSION');
+  let currentVersion = '0.0.0';
+  if (fs.existsSync(versionFile)) {
+    currentVersion = fs.readFileSync(versionFile, 'utf-8').trim();
+  }
+
+  if (currentVersion !== pkgMeta.version) {
+    log(`Version mismatch detected (Local: ${currentVersion} -> NPM: ${pkgMeta.version}). Auto-upgrading...`);
+    safeUnpack();
+  }
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// EXECUTOR
+// ─────────────────────────────────────────────────────────────────────────────
+
+// 1. Python check
+const pythonInfo = getPythonCommand();
+if (!pythonInfo) {
+  errorOut('Could not find Python >= 3.10 on this system. Please install Python 3.10+ to run SuperBrain.');
+}
+
+// 2. Safe unpack/upgrade
+checkUpgrades();
+
+// 3. Command Routing logic
+const userArgs = process.argv.slice(2);
+let targetScript = 'start.py';
+let finalArgs = userArgs;
+
+if (userArgs.length > 0) {
+  const cmd = userArgs[0].toLowerCase();
+  if (cmd === 'reset') {
+    targetScript = 'reset.py';
+    finalArgs = userArgs.slice(1); // remove 'reset' from arguments passed to python
+  } else if (cmd === '-h' || cmd === '--help') {
+    console.log(`
+  SuperBrain Server Wrapper (v${pkgMeta.version})
+
+  Usage:
+    superbrain-server               -> Starts the backend engine
+    superbrain-server reset         -> Open Reset Menu
+    superbrain-server reset --all   -> Force complete wipe
+    `);
+    process.exit(0);
+  }
+}
+
+// 4. Execution
+log(`Spinning up Python Engine via ${targetScript} (Python ${pythonInfo.version.major}.${pythonInfo.version.minor}.${pythonInfo.version.patch})...`);
+const child = spawn(pythonInfo.command, [...pythonInfo.execPrefix, targetScript, ...finalArgs], {
+  cwd: TARGET_DIR,
+  stdio: 'inherit'
+});
+
+// 5. Zombie Protection
+function handleShutdown(signal) {
+  warn(`Received ${signal}. Shutting down Python engine...`);
+  child.kill('SIGINT'); 
+}
+
+process.on('SIGINT', () => handleShutdown('SIGINT'));
+process.on('SIGTERM', () => handleShutdown('SIGTERM'));
+
+child.on('close', (code) => {
+  process.exit(code || 0);
+});

package/package.json

@@ -0,0 +1,23 @@
+{
+  "name": "superbrain-server",
+  "version": "1.0.2-beta.0",
+  "description": "1-Line Auto-Installer and Server Execution wrapper for SuperBrain",
+  "main": "index.js",
+  "bin": {
+    "superbrain-server": "bin/superbrain.js"
+  },
+  "scripts": {
+    "build": "node scripts/build.js"
+  },
+  "keywords": [
+    "superbrain",
+    "server"
+  ],
+  "author": "sidinsearch",
+  "license": "MIT",
+  "dependencies": {},
+  "files": [
+    "bin/",
+    "payload/"
+  ]
+}

package/payload/.dockerignore

@@ -0,0 +1,45 @@
+# Git and local metadata
+.git
+.gitignore
+
+# Python caches and virtual environments
+.venv
+venv
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.pytest_cache
+.mypy_cache
+
+# Local runtime data
+superbrain.db
+superbrain.db-shm
+superbrain.db-wal
+token.txt
+.setup_done
+.env
+*.env
+
+# Secrets/config generated at runtime
+.api_keys
+config/.api_keys
+config/ngrok_token.txt
+config/test_credentials.txt
+config/localtunnel.log
+
+# Logs and transient artifacts
+logs/
+temp/
+error_log_utf8.txt
+failures.txt
+final_test.txt
+test_results.txt
+yt_error.txt
+err.json
+
+# Build outputs
+*.apk
+
+# Optional local uploads
+static/uploads/

package/payload/.env.example

@@ -0,0 +1,58 @@
+# ────────────────────────────────────────────────────────────────────────────────
+# SuperBrain Environment Configuration Template
+# ────────────────────────────────────────────────────────────────────────────────
+# Copy this file to .env and fill in your actual values
+# NEVER commit .env file to version control
+# ────────────────────────────────────────────────────────────────────────────────
+
+# ──── Application Settings ────
+ENVIRONMENT=production
+DEBUG=false
+LOG_LEVEL=INFO
+
+# ──── Server Configuration ────
+HOST=0.0.0.0
+PORT=5000
+WORKERS=4
+API_PORT=5000
+
+# ──── Database Configuration ────
+DATABASE_PATH=superbrain.db
+DATABASE_TIMEOUT=30
+
+# ──── AI Provider API Keys ────
+# Get these from the respective provider accounts
+GROQ_API_KEY=
+GEMINI_API_KEY=
+OPENROUTER_API_KEY=
+
+# ──── Whisper Configuration ────
+# Options: tiny, base, small, medium, large
+WHISPER_MODEL=base
+WHISPER_USE_CLOUD=true
+
+# ──── Instagram Credentials ────
+# Use a bot account or app-specific credentials, NOT your personal account
+INSTAGRAM_USERNAME=
+INSTAGRAM_PASSWORD=
+
+# ──── File Upload Configuration ────
+MAX_UPLOAD_SIZE=52428800
+UPLOAD_DIR=static/uploads
+TEMP_DIR=temp
+
+# ──── Request Timeout Settings ────
+REQUEST_TIMEOUT=60
+ANALYSIS_TIMEOUT=120
+MAX_RETRIES=3
+RETRY_DELAY=5
+
+# ──── Feature Flags ────
+ENABLE_METRICS=true
+ENABLE_HEALTH_CHECK=true
+ENABLE_API_DOCS=false
+
+# ────────────────────────────────────────────────────────────────────────────────
+# NOTE: Update only the values you need
+# Leave blank if optional or use defaults
+# ────────────────────────────────────────────────────────────────────────────────

package/payload/Dockerfile

@@ -0,0 +1,73 @@
+# ────────────────────────────────────────────────────────────────────────────────
+# Multi-stage build for optimized image size
+# ────────────────────────────────────────────────────────────────────────────────
+
+FROM python:3.11-slim as builder
+
+WORKDIR /app
+
+# Install system build dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    gcc \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements
+COPY requirements.txt .
+
+# Build dependencies in separate layer
+RUN pip install --user --no-cache-dir -r requirements.txt
+
+
+# ────────────────────────────────────────────────────────────────────────────────
+# Final production image
+# ────────────────────────────────────────────────────────────────────────────────
+
+FROM python:3.11-slim
+
+LABEL maintainer="SuperBrain <sidinsearch@gmail.com>"
+LABEL description="SuperBrain API - AI-powered content analysis and archival"
+LABEL version="1.0.0"
+
+WORKDIR /app
+
+# ──── Install runtime dependencies only ────
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    ffmpeg \
+    libmagic1 \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# ──── Copy Python dependencies from builder ────
+COPY --from=builder /root/.local /root/.local
+
+# ──── Set environment variables ────
+ENV PATH=/root/.local/bin:$PATH \
+    PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    ENVIRONMENT=production \
+    WORKERS=2
+
+# ──── Copy application code ────
+COPY . .
+
+# ──── Create necessary directories with proper permissions ────
+RUN mkdir -p temp config static logs data && \
+    chmod 755 temp config static logs data
+
+# ──── Health check ────
+HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
+    CMD curl -f http://localhost:5000/health || exit 1
+
+# ──── Run as non-root user for security ────
+RUN useradd -m -u 1000 appuser && \
+    chown -R appuser:appuser /app
+
+USER appuser
+
+# ──── Expose port ────
+EXPOSE 5000
+
+# ──── Run the application ────
+CMD ["sh", "-c", "python -m uvicorn api:app --host 0.0.0.0 --port 5000 --workers ${WORKERS:-2} --loop uvloop --no-access-log"]

package/payload/analyzers/audio_transcribe.py

@@ -0,0 +1,225 @@
+#!/usr/bin/env python3
+"""
+Audio Transcriber — Multi-language Support
+Primary:  Groq Whisper API  (whisper-large-v3-turbo → whisper-large-v3)
+Fallback: Local OpenAI Whisper (model from config/whisper_model.txt, default: base)
+"""
+
+import os
+import sys
+from pathlib import Path
+
+# ── API key loader (mirrors model_router.py) ─────────────────────────────────
+
+_CONFIG_DIR = Path(__file__).resolve().parent.parent / "config"
+
+
+def _load_local_model() -> str:
+    """Return the Whisper model name saved by start.py, defaulting to 'base'."""
+    cfg = _CONFIG_DIR / "whisper_model.txt"
+    if cfg.exists():
+        model = cfg.read_text().strip()
+        if model:
+            return model
+    return "base"
+
+
+def _load_groq_key():
+    key = os.environ.get("GROQ_API_KEY")
+    if key:
+        return key
+    keys_file = _CONFIG_DIR / ".api_keys"
+    if keys_file.exists():
+        for line in keys_file.read_text(encoding="utf-8").splitlines():
+            line = line.strip()
+            if line.startswith("GROQ_API_KEY="):
+                v = line.split("=", 1)[1].strip()
+                return v or None
+    return None
+
+
+LANGUAGE_NAMES = {
+    "en": "English", "hi": "Hindi", "es": "Spanish", "fr": "French",
+    "de": "German", "it": "Italian", "pt": "Portuguese", "ru": "Russian",
+    "ja": "Japanese", "ko": "Korean", "zh": "Chinese", "ar": "Arabic",
+    "tr": "Turkish", "vi": "Vietnamese", "th": "Thai", "id": "Indonesian",
+    "nl": "Dutch", "pl": "Polish", "uk": "Ukrainian", "bn": "Bengali",
+    "ta": "Tamil", "te": "Telugu", "mr": "Marathi", "gu": "Gujarati",
+    "kn": "Kannada", "ml": "Malayalam", "pa": "Punjabi", "ur": "Urdu",
+}
+
+VALID_EXTENSIONS = {".mp3", ".wav", ".m4a", ".ogg", ".flac", ".aac", ".webm", ".mp4"}
+
+# Groq Whisper API max file size (25 MB)
+GROQ_MAX_BYTES = 25 * 1024 * 1024
+
+
+# ── Transcription backends ────────────────────────────────────────────────────
+
+def _transcribe_groq(audio_path, api_key):
+    """
+    Transcribe using Groq Whisper API.
+    Tries whisper-large-v3-turbo first (fast, multilingual),
+    then whisper-large-v3 (highest accuracy).
+    Returns (text, language_code). Raises on failure.
+    """
+    from groq import Groq
+
+    client = Groq(api_key=api_key)
+
+    file_size = audio_path.stat().st_size
+    if file_size > GROQ_MAX_BYTES:
+        raise ValueError(
+            f"File too large for Groq API ({file_size / 1024 / 1024:.1f} MB > 25 MB). "
+            "Using local fallback."
+        )
+
+    models = [
+        ("whisper-large-v3-turbo", "fast multilingual"),
+        ("whisper-large-v3",       "highest accuracy"),
+    ]
+
+    last_err = None
+    for model_id, label in models:
+        try:
+            print(f"  🌐 Groq Whisper [{label}] …")
+            with open(audio_path, "rb") as f:
+                response = client.audio.transcriptions.create(
+                    model=model_id,
+                    file=(audio_path.name, f),
+                    response_format="verbose_json",
+                )
+            text = (response.text or "").strip()
+            lang = getattr(response, "language", None) or "unknown"
+            return text, lang
+        except Exception as e:
+            print(f"  ⚠️  Groq {model_id} failed: {e}")
+            last_err = e
+
+    raise RuntimeError(f"All Groq Whisper models failed. Last error: {last_err}")
+
+
+def _transcribe_local(audio_path):
+    """
+    Transcribe using local OpenAI Whisper.
+    Model is read from config/whisper_model.txt (set by start.py), default 'base'.
+    Returns (text, language_code).
+    """
+    import whisper  # type: ignore
+
+    model_name = _load_local_model()
+    print(f"  💻 Loading local Whisper model ({model_name}) …")
+    model = whisper.load_model(model_name)
+    print("  ✓  Local model loaded")
+
+    result = model.transcribe(
+        str(audio_path),
+        fp16=False,
+        task="transcribe",
+        verbose=False,
+    )
+    text = result["text"].strip()
+    lang = result.get("language", "unknown")
+    return text, lang
+
+
+# ── Main entry point ──────────────────────────────────────────────────────────
+
+def transcribe_audio(audio_path):
+    """Transcribe audio file — Groq Whisper primary, local Whisper fallback."""
+
+    print("=" * 70)
+    print("🎙️  AUDIO TRANSCRIBER — Multi-Language  (Groq → Local fallback)")
+    print("=" * 70)
+    print()
+
+    path = Path(audio_path)
+    if not path.exists():
+        print(f"❌ File not found: {audio_path}")
+        return
+
+    if path.suffix.lower() not in VALID_EXTENSIONS:
+        print(f"❌ Unsupported file type: {path.suffix}")
+        print(f"   Supported: {', '.join(sorted(VALID_EXTENSIONS))}")
+        return
+
+    print(f"🎧 File: {path.name}  ({path.stat().st_size / 1024:.1f} KB)")
+    print()
+
+    text = ""
+    lang_code = "unknown"
+    backend_used = ""
+
+    # ── 1. Try Groq Whisper API ───────────────────────────────────────────────
+    api_key = _load_groq_key()
+    if api_key:
+        try:
+            text, lang_code = _transcribe_groq(path, api_key)
+            backend_used = "Groq Whisper API"
+        except Exception as e:
+            print(f"  ⚠️  Groq transcription failed: {e}")
+            print("  🔁 Falling back to local Whisper …")
+            print()
+    else:
+        print("  ℹ️  GROQ_API_KEY not set — using local Whisper directly")
+        print()
+
+    # ── 2. Local Whisper fallback ─────────────────────────────────────────────
+    if not text:
+        try:
+            text, lang_code = _transcribe_local(path)
+            backend_used = f"Local Whisper ({_load_local_model()})"
+        except Exception as e:
+            print(f"❌ Local Whisper also failed: {e}")
+            import traceback
+            traceback.print_exc()
+            return
+
+    # ── Print results ─────────────────────────────────────────────────────────
+    lang_name = LANGUAGE_NAMES.get(lang_code, lang_code.title())
+
+    print()
+    print("=" * 70)
+    print("📊 TRANSCRIPTION RESULTS")
+    print("=" * 70)
+    print()
+    print(f"🔧 Backend:           {backend_used}")
+    print(f"🌍 Detected Language: {lang_name} ({lang_code})")
+    print()
+    print("📝 TRANSCRIBED TEXT:")
+    print("-" * 70)
+    print(text)
+    print("-" * 70)
+    print()
+    print(f"ℹ️  Words: {len(text.split())}")
+    print()
+    print("=" * 70)
+    print("✅ Transcription complete!")
+    print("=" * 70)
+
+
+def main():
+    """CLI entry point."""
+    if len(sys.argv) > 1:
+        audio_path = sys.argv[1]
+    else:
+        print("=" * 70)
+        print("🎙️  AUDIO TRANSCRIBER — Multi-Language")
+        print("=" * 70)
+        print()
+        print("Supports: English, Hindi, Spanish, French, German, Italian,")
+        print("          Portuguese, Russian, Japanese, Korean, Chinese, Arabic,")
+        print("          and 85+ more languages!")
+        print()
+        audio_path = input("📂 Enter audio file path: ").strip()
+
+    audio_path = audio_path.strip('"').strip("'").strip()
+    if not audio_path:
+        print("❌ No path provided!")
+        return
+
+    transcribe_audio(audio_path)
+
+
+if __name__ == "__main__":
+    main()