Upload notebooks/00_environment_setup.ipynb with huggingface_hub

notebooks/00_environment_setup.ipynb

@@ -215,24 +215,40 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from dotenv import load_dotenv\n",
+    "import json\n",
     "import os\n",
+    "from pathlib import Path\n",
     "\n",
-    "# Load environment variables from .env file\n",
-    "env_path = Path(\"../.env\")\n",
-    "if env_path.exists():\n",
-    "    load_dotenv(env_path)\n",
-    "    print(f\"✓ Loaded environment from: {env_path.absolute()}\")\n",
+    "# Load configuration from notebook_config.json first (for HF Spaces)\n",
+    "config_json_path = Path(\"notebook_config.json\")\n",
+    "if config_json_path.exists():\n",
+    "    with open(config_json_path, \"r\") as f:\n",
+    "        loaded_config = json.load(f)\n",
+    "    print(f\"✓ Loaded configuration from: {config_json_path.absolute()}\")\n",
     "else:\n",
-    "    print(f\"⚠ No .env file found at {env_path.absolute()}\")\n",
+    "    loaded_config = {}\n",
+    "    print(f\"⚠ No notebook_config.json found, using defaults\")\n",
+    "\n",
+    "# Try loading .env file as fallback (for local dev)\n",
+    "try:\n",
+    "    from dotenv import load_dotenv\n",
+    "    env_path = Path(\"../.env\")\n",
+    "    if env_path.exists():\n",
+    "        load_dotenv(env_path)\n",
+    "        print(f\"✓ Loaded environment from: {env_path.absolute()}\")\n",
+    "except ImportError:\n",
+    "    pass\n",
     "\n",
     "# Configuration class\n",
     "class Config:\n",
-    "    # API Keys\n",
-    "    GEMINI_API_KEY = os.getenv(\"GEMINI_API_KEY\", \"\")\n",
-    "    HUGGINGFACE_TOKEN = os.getenv(\"HUGGINGFACE_API_TOKEN\", \"\")\n",
-    "    WEBSCRAPER_API_KEY = \"sk-fd14eaa7bceb478db7afc7256e514d2b\"  # WebScrapper.live API\n",
-    "    WEBSCRAPER_API_URL = \"http://webscrapper.live/api/scrape\"\n",
+    "    # API Keys - priority: config.json > env vars > HF secrets\n",
+    "    GEMINI_API_KEY = loaded_config.get(\"gemini_api_key\") or os.getenv(\"GEMINI_API_KEY\", \"AIzaSyA3HdWTLk_zJQ5P9G8Z8a8BEYSTPvLglhs\")\n",
+    "    HUGGINGFACE_TOKEN = os.getenv(\"HUGGINGFACE_API_TOKEN\", os.getenv(\"HF_TOKEN\", \"\"))\n",
+    "    WEBSCRAPER_API_KEY = loaded_config.get(\"webscraper_api_key\", \"sk-fd14eaa7bceb478db7afc7256e514d2b\")\n",
+    "    WEBSCRAPER_API_URL = loaded_config.get(\"webscraper_api_url\", \"http://webscrapper.live/api/scrape\")\n",
+    "    \n",
+    "    # Gemini model\n",
+    "    GEMINI_MODEL = loaded_config.get(\"gemini_model\", \"gemini-2.5-flash\")\n",
     "    \n",
     "    # Paths\n",
     "    BASE_DIR = Path(\"..\").resolve()\n",
@@ -241,9 +257,9 @@
     "    ARTIFACTS_DIR = BASE_DIR / \"artifacts\"\n",
     "    \n",
     "    # ML Settings\n",
-    "    RANDOM_STATE = 42\n",
-    "    TEST_SIZE = 0.2\n",
-    "    CV_FOLDS = 5\n",
+    "    RANDOM_STATE = loaded_config.get(\"random_state\", 42)\n",
+    "    TEST_SIZE = loaded_config.get(\"test_size\", 0.2)\n",
+    "    CV_FOLDS = loaded_config.get(\"cv_folds\", 5)\n",
     "    \n",
     "    # Device\n",
     "    DEVICE = DEVICE\n",
@@ -254,8 +270,9 @@
     "print(\"\\n\" + \"=\" * 60)\n",
     "print(\"API CONFIGURATION STATUS\")\n",
     "print(\"=\" * 60)\n",
-    "print(f\"✓ Gemini API Key: {'Configured' if config.GEMINI_API_KEY else '⚠ NOT SET'}\")\n",
-    "print(f\"✓ HuggingFace Token: {'Configured' if config.HUGGINGFACE_TOKEN else '⚠ NOT SET'}\")\n",
+    "print(f\"✓ Gemini API Key: {'Configured (' + config.GEMINI_API_KEY[:10] + '...)' if config.GEMINI_API_KEY else '⚠ NOT SET'}\")\n",
+    "print(f\"✓ Gemini Model: {config.GEMINI_MODEL}\")\n",
+    "print(f\"✓ HuggingFace Token: {'Configured' if config.HUGGINGFACE_TOKEN else '⚠ NOT SET (optional)'}\")\n",
     "print(f\"✓ WebScraper API: Configured\")"
    ]
   },
@@ -283,17 +300,24 @@
     "    \n",
     "    try:\n",
     "        genai.configure(api_key=config.GEMINI_API_KEY)\n",
-    "        model = genai.GenerativeModel('gemini-1.5-flash')\n",
+    "        # Use the configured model (gemini-2.5-flash)\n",
+    "        model = genai.GenerativeModel(config.GEMINI_MODEL)\n",
     "        response = model.generate_content(\"Respond with only: OK\")\n",
-    "        return True, response.text.strip()\n",
+    "        return True, f\"Model: {config.GEMINI_MODEL}, Response: {response.text.strip()}\"\n",
     "    except Exception as e:\n",
-    "        return False, str(e)\n",
+    "        # Fallback to gemini-1.5-flash if 2.5 not available\n",
+    "        try:\n",
+    "            model = genai.GenerativeModel('gemini-1.5-flash')\n",
+    "            response = model.generate_content(\"Respond with only: OK\")\n",
+    "            return True, f\"Model: gemini-1.5-flash (fallback), Response: {response.text.strip()}\"\n",
+    "        except Exception as e2:\n",
+    "            return False, str(e2)\n",
     "\n",
     "print(\"Testing Gemini API connection...\")\n",
     "success, message = test_gemini_connection()\n",
     "\n",
     "if success:\n",
-    "    print(f\"✓ Gemini API: Connected successfully\")\n",
+    "    print(f\"✓ Gemini API: {message}\")\n",
     "else:\n",
     "    print(f\"⚠ Gemini API: Connection failed - {message}\")"
    ]