feat: update all OpenAI/ChatGPT refs + settings dropdown for fixed-value fields

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>

.env.demo

@@ -119,16 +119,44 @@ AUTHENTIK_CONFIG_URL=<ConfigUrlOfYourApp, e.g. https://authentik.example.com/app
 OAUTH_PROVIDER_NAME="Authentik SSO"
 
 # **AI/ML Services**
-# OpenAI
+# Select your AI provider: openai | azure | anthropic | gemini | ollama | openrouter | portkey | litellm
+AI_PROVIDER=openai
+# Model override (optional – falls back to OPENAI_MODEL when not set)
+# AI_MODEL=gpt-4o-mini
+
+# --- OpenAI (AI_PROVIDER=openai) ---
 OPENAI_API_KEY="<OPENAI_API_KEY>"
 OPENAI_BASE_URL=https://api.openai.com/v1
 OPENAI_MODEL=gpt-4o-mini
 
-# Azure AI
+# --- Anthropic Claude (AI_PROVIDER=anthropic) ---
-AZURE_REGION="eastus"
+# ANTHROPIC_API_KEY=sk-ant-...
-AZURE_ENDPOINT="https://<yourendpoint>.cognitiveservices.azure.com/"
+# AI_MODEL=claude-3-5-sonnet-20241022
-AZURE_AI_KEY=<AZURE_AI_KEY>
 
+# --- Google Gemini (AI_PROVIDER=gemini) ---
+# GEMINI_API_KEY=AIza...
+# AI_MODEL=gemini-1.5-pro
+
+# --- Ollama local LLMs (AI_PROVIDER=ollama) ---
+# OLLAMA_BASE_URL=http://localhost:11434
+# AI_MODEL=llama3.2
+
+# --- OpenRouter (AI_PROVIDER=openrouter) ---
+# OPENROUTER_API_KEY=sk-or-...
+# AI_MODEL=anthropic/claude-3.5-sonnet
+
+# --- Portkey AI Gateway (AI_PROVIDER=portkey) ---
+# PORTKEY_API_KEY=pk-...
+# PORTKEY_VIRTUAL_KEY=vk-...   # optional – routes to provider credentials in Portkey vault
+# PORTKEY_CONFIG=pc-...        # optional – saved Config ID for fallbacks / load balancing
+
+# --- Azure OpenAI (AI_PROVIDER=azure) ---
+# OPENAI_API_KEY=<azure-key>
+# OPENAI_BASE_URL=https://my-resource.openai.azure.com
+# AZURE_OPENAI_API_VERSION=2024-02-01
+# AI_MODEL=gpt-4o   # deployment name in Azure
+
+# Azure Document Intelligence (OCR – separate from AI provider above)
 # **Email Settings**
 EMAIL_HOST=smtp.example.com
 EMAIL_PORT=587

README.md

@@ -31,7 +31,7 @@
 
 DocuElevate automates the handling, extraction, and processing of documents using a variety of services, including:
 
-- **OpenAI** for metadata extraction and text refinement.
+- **AI Provider** (pluggable – OpenAI, Anthropic, Gemini, Ollama, OpenRouter, Portkey, and more) for metadata extraction and text refinement.
 - **Dropbox**, **Nextcloud**, and **Google Drive** for file storage and uploads.
 - **Paperless NGX** for document indexing and management.
 - **Azure Document Intelligence** for OCR on PDFs.
@@ -86,7 +86,7 @@ Documents enter DocuElevate through four possible channels:
 Every document goes through the following steps:
 1. **PDF Conversion**: Non-PDF files are converted to PDF format using Gotenberg
 2. **OCR Processing**: Azure Document Intelligence extracts text from images/scans
-3. **Metadata Extraction**: OpenAI analyzes document content to identify:
+3. **Metadata Extraction**: The configured AI provider analyzes document content to identify:
    - Document type (invoice, receipt, contract, etc.)
    - Key entities (dates, names, amounts, account numbers)
    - Important data points specific to the document type
@@ -116,8 +116,8 @@ Users can choose to send documents to any combination of these destinations thro
   - Manual uploads (via API or UI) to Dropbox, Nextcloud, Google Drive, or Paperless
 - **OCR Processing (Azure)**:
   - Extract text from scanned PDFs using Azure Document Intelligence
-- **Metadata Extraction (OpenAI)**:
+- **Metadata Extraction (AI Provider)**:
-  - Use GPT to classify, label, or otherwise enrich the text with structured metadata
+  - Use any supported AI provider (OpenAI, Anthropic, Gemini, Ollama, etc.) to classify, label, or otherwise enrich the text with structured metadata
 - **PDF Conversion (Gotenberg)**:
   - Convert non-PDF attachments (e.g., Word docs, images) into PDFs
 - **Document Management (Paperless NGX)**:
@@ -214,7 +214,8 @@ The following is a summary of the licenses used by our direct dependencies:
 | Uvicorn    | BSD     |
 | SQLAlchemy | MIT     |
 | Pydantic   | MIT     |
-| OpenAI     | MIT     |
+| openai     | MIT     |
+| litellm    | MIT     |
 | pypdf      | BSD     |
 | Requests   | Apache 2.0 |
 | puremagic  | MIT     |

app/api/openai.py

@@ -1,5 +1,9 @@
 """
-OpenAI API endpoints
+AI provider and OpenAI API endpoints.
+
+Exposes two endpoints:
+- GET /api/ai/test   – tests the currently configured AI provider (generic, provider-agnostic)
+- GET /api/openai/test – backward-compatible alias that tests the OpenAI API specifically
 """
 
 import logging
@@ -146,3 +150,55 @@ async def test_openai_connection(request: Request):
     except Exception as e:
         logger.exception("Unexpected error testing OpenAI connection")
         return {"status": "error", "message": f"Unexpected error: {str(e)}"}
+
+
+@router.get("/ai/test")
+@require_login
+async def test_ai_provider_connection(request: Request):
+    """
+    Test the currently configured AI provider connection.
+
+    Uses ``get_ai_provider()`` to instantiate the active provider and sends a
+    minimal chat completion to verify that the credentials and endpoint are
+    reachable.  Works for all supported providers (OpenAI, Azure, Anthropic,
+    Gemini, Ollama, OpenRouter, Portkey, LiteLLM).
+    """
+    from app.utils.ai_provider import get_ai_provider
+
+    provider_name = settings.ai_provider
+    model = settings.ai_model or settings.openai_model
+
+    logger.info(f"Testing AI provider connection: provider={provider_name}, model={model}")
+
+    try:
+        provider = get_ai_provider()
+        response = provider.chat_completion(
+            messages=[{"role": "user", "content": "Reply with the single word: ok"}],
+            model=model,
+            temperature=0,
+            max_tokens=5,
+        )
+        logger.info(f"AI provider test successful: provider={provider_name}")
+        return {
+            "status": "success",
+            "message": f"AI provider '{provider_name}' is reachable and responding",
+            "provider": provider_name,
+            "model": model,
+            "response_preview": (response or "")[:50],
+        }
+    except ValueError as e:
+        # Configuration errors (missing keys, unknown provider)
+        logger.warning(f"AI provider configuration error: {e}")
+        return {
+            "status": "error",
+            "message": str(e),
+            "provider": provider_name,
+        }
+    except Exception as e:
+        detail = _get_exception_chain_detail(e)
+        logger.error(f"AI provider test failed for '{provider_name}': {detail}", exc_info=True)
+        return {
+            "status": "error",
+            "message": f"Connection failed: {detail}",
+            "provider": provider_name,
+        }

app/tasks/check_credentials.py

@@ -11,7 +11,7 @@ from app.api.google_drive import test_google_drive_token
 from app.api.onedrive import test_onedrive_token
 
 # Import the test functions from API routes
-from app.api.openai import test_openai_connection
+from app.api.openai import test_ai_provider_connection, test_openai_connection
 from app.celery_app import celery
 from app.config import settings
 
@@ -75,8 +75,17 @@ def unwrap_decorated_function(func):
 
 
 # Create synchronous versions of the test functions that bypass authentication
+def sync_test_ai_provider_connection():
+    """Synchronous wrapper for the AI provider test function that bypasses auth."""
+    inner_func = unwrap_decorated_function(test_ai_provider_connection)
+    request = MockRequest()
+    if inspect.iscoroutinefunction(inner_func):
+        return asyncio.run(inner_func(request))
+    return inner_func(request)
+
+
 def sync_test_openai_connection():
-    """Synchronous wrapper for the OpenAI test function that bypasses auth"""
+    """Synchronous wrapper for the OpenAI test function that bypasses auth."""
     # Get the original function without the @require_login decorator
     inner_func = unwrap_decorated_function(test_openai_connection)
     request = MockRequest()
@@ -139,10 +148,10 @@ def check_credentials():
     # Define services with their test functions and configuration status
     services = [
         {
-            "name": "OpenAI",
+            "name": "AI Provider",
-            "check_func": sync_test_openai_connection,
+            "check_func": sync_test_ai_provider_connection,
-            "configured": provider_status.get("OpenAI", {}).get("configured", False),
+            "configured": provider_status.get("AI Provider", {}).get("configured", False),
-            "config_issues": [],  # OpenAI isn't in storage_configs
+            "config_issues": [],
         },
         {
             "name": "Azure Document Intelligence",

app/utils/config_validator/providers.py

@@ -57,20 +57,69 @@ def get_provider_status() -> dict[str, dict[str, object]]:
         "test_endpoint": "/api/diagnostic/test-notification",
     }
 
-    # Add AI services first
+    # Add AI provider (dynamic – reflects whichever provider is configured)
-    providers["OpenAI"] = {
+    ai_provider_name = getattr(settings, "ai_provider", "openai").lower()
-        "name": "OpenAI",
+    model = getattr(settings, "ai_model", None) or getattr(settings, "openai_model", "gpt-4o-mini")
-        "icon": "fa-brands fa-openai",
+
-        "configured": bool(
+    # Determine whether the active provider has its required credentials set
-            getattr(settings, "openai_api_key", None) and str(getattr(settings, "openai_api_key", "")).startswith("sk-")
+    def _ai_configured() -> bool:
-        ),
+        if ai_provider_name in ("openai", "azure", "litellm"):
+            return bool(getattr(settings, "openai_api_key", None))
+        elif ai_provider_name == "anthropic":
+            return bool(getattr(settings, "anthropic_api_key", None))
+        elif ai_provider_name == "gemini":
+            return bool(getattr(settings, "gemini_api_key", None))
+        elif ai_provider_name == "ollama":
+            return bool(getattr(settings, "ollama_base_url", None))
+        elif ai_provider_name == "openrouter":
+            return bool(getattr(settings, "openrouter_api_key", None))
+        elif ai_provider_name == "portkey":
+            return bool(getattr(settings, "portkey_api_key", None))
+        return False
+
+    # Build provider-specific detail rows
+    def _ai_details() -> dict:
+        base = {"provider": ai_provider_name, "model": model}
+        if ai_provider_name in ("openai", "azure", "litellm"):
+            base["api_key"] = mask_sensitive_value(getattr(settings, "openai_api_key", None))
+            base["base_url"] = getattr(settings, "openai_base_url", "https://api.openai.com/v1")
+        elif ai_provider_name == "anthropic":
+            base["api_key"] = mask_sensitive_value(getattr(settings, "anthropic_api_key", None))
+        elif ai_provider_name == "gemini":
+            base["api_key"] = mask_sensitive_value(getattr(settings, "gemini_api_key", None))
+        elif ai_provider_name == "ollama":
+            base["base_url"] = getattr(settings, "ollama_base_url", "http://localhost:11434")
+        elif ai_provider_name == "openrouter":
+            base["api_key"] = mask_sensitive_value(getattr(settings, "openrouter_api_key", None))
+            base["base_url"] = getattr(settings, "openrouter_base_url", "https://openrouter.ai/api/v1")
+        elif ai_provider_name == "portkey":
+            base["api_key"] = mask_sensitive_value(getattr(settings, "portkey_api_key", None))
+            if getattr(settings, "portkey_virtual_key", None):
+                base["virtual_key"] = mask_sensitive_value(settings.portkey_virtual_key)
+            if getattr(settings, "portkey_config", None):
+                base["config"] = settings.portkey_config
+        return base
+
+    _PROVIDER_ICONS = {
+        "openai": "fa-brands fa-openai",
+        "azure": "fa-brands fa-microsoft",
+        "anthropic": "fa-solid fa-robot",
+        "gemini": "fa-brands fa-google",
+        "ollama": "fa-solid fa-server",
+        "openrouter": "fa-solid fa-route",
+        "portkey": "fa-solid fa-key",
+        "litellm": "fa-solid fa-layer-group",
+    }
+
+    providers["AI Provider"] = {
+        "name": "AI Provider",
+        "icon": _PROVIDER_ICONS.get(ai_provider_name, "fa-solid fa-microchip"),
+        "configured": _ai_configured(),
         "enabled": True,
-        "description": "AI-powered document analysis and metadata extraction",
+        "description": f"AI-powered metadata extraction and OCR refinement ({ai_provider_name})",
-        "details": {
+        "details": _ai_details(),
-            "api_key": mask_sensitive_value(getattr(settings, "openai_api_key", None)),
+        "testable": True,
-            "base_url": getattr(settings, "openai_base_url", "https://api.openai.com/v1"),
+        "test_endpoint": "/api/ai/test",
-            "model": getattr(settings, "openai_model", "gpt-4"),
-        },
     }
 
     providers["Azure AI"] = {

app/utils/config_validator/settings_display.py

@@ -170,9 +170,21 @@ def get_settings_for_display(show_values: bool = False) -> dict[str, list[dict[s
             "s3_acl",
         ],
         "AI Services": [
+            "ai_provider",
+            "ai_model",
             "openai_api_key",
             "openai_base_url",
             "openai_model",
+            "anthropic_api_key",
+            "gemini_api_key",
+            "ollama_base_url",
+            "openrouter_api_key",
+            "openrouter_base_url",
+            "portkey_api_key",
+            "portkey_virtual_key",
+            "portkey_config",
+            "portkey_base_url",
+            "azure_openai_api_version",
             "azure_ai_key",
             "azure_endpoint",
             "azure_region",

app/utils/settings_service.py

@@ -136,15 +136,15 @@ SETTING_METADATA = {
     # AI Services
     "openai_api_key": {
         "category": "AI Services",
-        "description": "OpenAI API key for metadata extraction",
+        "description": "API key for the AI provider (required for OpenAI, Azure, LiteLLM; unused for Ollama)",
         "type": "string",
         "sensitive": True,
-        "required": True,
+        "required": False,
         "restart_required": False,
     },
     "openai_base_url": {
         "category": "AI Services",
-        "description": "OpenAI API base URL (default: https://api.openai.com/v1)",
+        "description": "API base URL – override for Azure endpoints, local proxies, or LiteLLM (default: https://api.openai.com/v1)",
         "type": "string",
         "sensitive": False,
         "required": False,
@@ -152,34 +152,132 @@ SETTING_METADATA = {
     },
     "openai_model": {
         "category": "AI Services",
-        "description": "OpenAI model to use (e.g., gpt-4o-mini)",
+        "description": "Fallback model name used when AI_MODEL is not set (e.g. gpt-4o-mini)",
         "type": "string",
         "sensitive": False,
         "required": False,
         "restart_required": False,
     },
-    "azure_ai_key": {
+    "ai_provider": {
         "category": "AI Services",
-        "description": "Azure AI key for document intelligence",
+        "description": "Active AI provider for metadata extraction and OCR refinement",
+        "type": "string",
+        "sensitive": False,
+        "required": False,
+        "restart_required": False,
+        "options": ["openai", "azure", "anthropic", "gemini", "ollama", "openrouter", "portkey", "litellm"],
+    },
+    "ai_model": {
+        "category": "AI Services",
+        "description": "Model name for the selected provider (overrides OPENAI_MODEL). E.g. gpt-4o, claude-3-5-sonnet-20241022, gemini-1.5-pro, llama3.2",
+        "type": "string",
+        "sensitive": False,
+        "required": False,
+        "restart_required": False,
+    },
+    "anthropic_api_key": {
+        "category": "AI Services",
+        "description": "Anthropic API key (required when AI_PROVIDER=anthropic)",
         "type": "string",
         "sensitive": True,
-        "required": True,
+        "required": False,
+        "restart_required": False,
+    },
+    "gemini_api_key": {
+        "category": "AI Services",
+        "description": "Google AI Studio API key (required when AI_PROVIDER=gemini)",
+        "type": "string",
+        "sensitive": True,
+        "required": False,
+        "restart_required": False,
+    },
+    "ollama_base_url": {
+        "category": "AI Services",
+        "description": "Ollama server URL for local LLM inference (used when AI_PROVIDER=ollama)",
+        "type": "string",
+        "sensitive": False,
+        "required": False,
+        "restart_required": False,
+    },
+    "openrouter_api_key": {
+        "category": "AI Services",
+        "description": "OpenRouter API key (required when AI_PROVIDER=openrouter)",
+        "type": "string",
+        "sensitive": True,
+        "required": False,
+        "restart_required": False,
+    },
+    "openrouter_base_url": {
+        "category": "AI Services",
+        "description": "OpenRouter gateway URL (default: https://openrouter.ai/api/v1)",
+        "type": "string",
+        "sensitive": False,
+        "required": False,
+        "restart_required": False,
+    },
+    "portkey_api_key": {
+        "category": "AI Services",
+        "description": "Portkey account API key (required when AI_PROVIDER=portkey)",
+        "type": "string",
+        "sensitive": True,
+        "required": False,
+        "restart_required": False,
+    },
+    "portkey_virtual_key": {
+        "category": "AI Services",
+        "description": "Portkey Virtual Key – routes to provider credentials stored in the Portkey vault (optional)",
+        "type": "string",
+        "sensitive": True,
+        "required": False,
+        "restart_required": False,
+    },
+    "portkey_config": {
+        "category": "AI Services",
+        "description": "Portkey Config ID for advanced routing, fallbacks, and load balancing (optional, e.g. pc-my-config-abc123)",
+        "type": "string",
+        "sensitive": False,
+        "required": False,
+        "restart_required": False,
+    },
+    "portkey_base_url": {
+        "category": "AI Services",
+        "description": "Portkey gateway URL (default: https://api.portkey.ai/v1; override for self-hosted deployments)",
+        "type": "string",
+        "sensitive": False,
+        "required": False,
+        "restart_required": False,
+    },
+    "azure_openai_api_version": {
+        "category": "AI Services",
+        "description": "Azure OpenAI API version string (used when AI_PROVIDER=azure, default: 2024-02-01)",
+        "type": "string",
+        "sensitive": False,
+        "required": False,
+        "restart_required": False,
+    },
+    # Azure Document Intelligence (OCR) – separate from the AI provider above
+    "azure_ai_key": {
+        "category": "AI Services",
+        "description": "Azure Document Intelligence API key for OCR processing",
+        "type": "string",
+        "sensitive": True,
+        "required": False,
         "restart_required": False,
     },
     "azure_region": {
         "category": "AI Services",
-        "description": "Azure region for AI services",
+        "description": "Azure region for Document Intelligence services (e.g., eastus)",
         "type": "string",
         "sensitive": False,
-        "required": True,
+        "required": False,
         "restart_required": False,
     },
     "azure_endpoint": {
         "category": "AI Services",
-        "description": "Azure AI endpoint URL",
+        "description": "Azure Document Intelligence endpoint URL",
         "type": "string",
         "sensitive": False,
-        "required": True,
+        "required": False,
         "restart_required": False,
     },
     # Storage Providers - Dropbox

app/utils/setup_wizard.py

@@ -90,10 +90,21 @@ def get_required_settings() -> List[Dict[str, Any]]:
             "wizard_step": 2,
             "wizard_category": "Security",
         },
+        {
+            "key": "ai_provider",
+            "label": "AI Provider",
+            "description": "AI provider for metadata extraction and OCR refinement (openai, azure, anthropic, gemini, ollama, openrouter, portkey, litellm)",
+            "type": "string",
+            "sensitive": False,
+            "default": "openai",
+            "options": ["openai", "azure", "anthropic", "gemini", "ollama", "openrouter", "portkey", "litellm"],
+            "wizard_step": 3,
+            "wizard_category": "AI Services",
+        },
         {
             "key": "openai_api_key",
-            "label": "OpenAI API Key",
+            "label": "API Key (OpenAI / Azure / LiteLLM)",
-            "description": "API key for OpenAI services (metadata extraction)",
+            "description": "API key for OpenAI, Azure OpenAI, or LiteLLM (not required for Ollama)",
             "type": "string",
             "sensitive": True,
             "default": None,
@@ -101,32 +112,12 @@ def get_required_settings() -> List[Dict[str, Any]]:
             "wizard_category": "AI Services",
         },
         {
-            "key": "azure_ai_key",
+            "key": "openai_model",
-            "label": "Azure AI Key",
+            "label": "Default Model",
-            "description": "Azure AI key for document intelligence (OCR)",
+            "description": "Model name used when AI_MODEL is not set (e.g. gpt-4o-mini, claude-3-5-sonnet-20241022, llama3.2)",
-            "type": "string",
-            "sensitive": True,
-            "default": None,
-            "wizard_step": 3,
-            "wizard_category": "AI Services",
-        },
-        {
-            "key": "azure_region",
-            "label": "Azure Region",
-            "description": "Azure region for AI services (e.g., eastus)",
             "type": "string",
             "sensitive": False,
-            "default": "eastus",
+            "default": "gpt-4o-mini",
-            "wizard_step": 3,
-            "wizard_category": "AI Services",
-        },
-        {
-            "key": "azure_endpoint",
-            "label": "Azure Endpoint",
-            "description": "Azure AI endpoint URL",
-            "type": "string",
-            "sensitive": False,
-            "default": None,
             "wizard_step": 3,
             "wizard_category": "AI Services",
         },
@@ -147,8 +138,6 @@ def is_setup_required() -> bool:
         critical_settings = [
             ("session_secret", ["INSECURE_DEFAULT_FOR_DEVELOPMENT_ONLY_DO_NOT_USE_IN_PRODUCTION_MINIMUM_32_CHARS"]),
             ("admin_password", [None, "", "your_secure_password", "changeme", "admin"]),
-            ("openai_api_key", [None, "", "<OPENAI_API_KEY>", "test-key"]),
-            ("azure_ai_key", [None, "", "<AZURE_AI_KEY>", "test-key"]),
         ]
 
         for setting_key, invalid_values in critical_settings:

docs/DeploymentGuide.md

@@ -6,7 +6,7 @@ This guide provides instructions for deploying DocuElevate in various environmen
 
 - Docker and Docker Compose
 - Access to required external services (if configured):
-  - OpenAI API
+  - AI provider API key (OpenAI, Anthropic, Gemini, or other configured provider)
   - Azure Document Intelligence
   - Dropbox API
   - Nextcloud instance

docs/SettingsManagement.md

@@ -26,7 +26,7 @@ Settings are organized into logical categories for easy navigation:
 
 - **Core**: Database, Redis, working directory, external hostname, debug mode
 - **Authentication**: Login settings, session secrets, OAuth configuration
-- **AI Services**: OpenAI and Azure AI configuration
+- **AI Services**: AI provider selection and credentials (OpenAI, Azure, Anthropic, Gemini, Ollama, OpenRouter, Portkey, LiteLLM)
 - **Storage Providers**: Dropbox, Google Drive, OneDrive, S3, FTP, SFTP, WebDAV, Nextcloud, Paperless
 - **Email**: SMTP configuration for sending emails
 - **IMAP**: Email ingestion configuration (supports multiple accounts)
@@ -152,7 +152,8 @@ Removes a setting from the database (reverts to environment variable or default)
 POST /api/settings/bulk-update
 [
   {"key": "debug", "value": "true"},
-  {"key": "openai_model", "value": "gpt-4"}
+  {"key": "ai_provider", "value": "anthropic"},
+  {"key": "openai_model", "value": "claude-3-5-sonnet-20241022"}
 ]
 ```
 

docs/UserGuide.md

@@ -150,7 +150,7 @@ View the complete processing history with a timeline showing:
 - Timestamps for each operation
 
 **Retry Processing**: If a file's processing has failed, you can use the "Retry Processing" button to reprocess the entire file. This is useful when:
-- External API services (like OpenAI) had temporary issues
+- External API services (like the configured AI provider) had temporary issues
 - Network connectivity was lost during processing
 - Configuration has been updated and you want to reprocess with new settings
 

frontend/templates/about.html

@@ -18,7 +18,8 @@
       for everyone, whether you're a small startup or a large enterprise.
     </p>
     <p class="text-gray-600">
-      We harness the power of OpenAI for metadata extraction and text refinement, integrate seamlessly
+      We harness the power of pluggable AI providers (OpenAI, Anthropic Claude, Google Gemini, Ollama,
+      OpenRouter, Portkey, and more) for metadata extraction and text refinement, integrate seamlessly
       with Dropbox, Nextcloud, and Paperless NGX for storage and indexing, leverage Azure Document
       Intelligence for OCR, and even use Gotenberg for file-to-PDF conversions.
     </p>
@@ -33,7 +34,7 @@
         <ul class="list-disc list-inside text-gray-600 ml-2">
           <li>Simple and secure file uploads with drag & drop support</li>
           <li>OCR powered by Azure Document Intelligence</li>
-          <li>Automated metadata extraction using OpenAI</li>
+          <li>Automated metadata extraction using a pluggable AI provider</li>
           <li>PDF conversion for various file formats via Gotenberg</li>
           <li>Intelligent document classification and date extraction</li>
         </ul>

frontend/templates/settings.html

@@ -139,8 +139,21 @@
                   Enable {{ setting.key.replace('_', ' ').title() }}
                 </label>
               </div>
+              {% elif setting.metadata.options %}
+              <!-- Dropdown Select for fields with a fixed list of values -->
+              <select
+                id="{{ setting.key }}"
+                name="{{ setting.key }}"
+                x-model="formData['{{ setting.key }}']"
+                class="setting-input w-full px-3 py-2 border border-gray-300 rounded-md shadow-sm focus:outline-none focus:ring-blue-500 focus:border-blue-500"
+              >
+                <option value="">— select —</option>
+                {% for opt in setting.metadata.options %}
+                <option value="{{ opt }}">{{ opt }}</option>
+                {% endfor %}
+              </select>
               {% else %}
-              <!-- Text Input -->
+              <!-- Text / Password Input -->
               <div class="relative">
                 {% if setting.metadata.sensitive %}
                 <!-- Sensitive Field with Show/Hide Toggle -->

frontend/templates/setup_wizard.html

@@ -92,7 +92,7 @@
           <div class="border-b border-gray-200 pb-6 last:border-b-0">
             <label for="{{ setting.key }}" class="block text-sm font-medium text-gray-900 mb-1">
               {{ setting.label }}
-              {% if setting.default is none or setting.key in ['admin_password', 'openai_api_key', 'azure_ai_key', 'azure_endpoint'] %}
+              {% if setting.default is none or setting.key in ['admin_password'] %}
               <span class="text-red-600">*</span>
               {% endif %}
             </label>
@@ -129,7 +129,18 @@
               />
             </div>
             {% else %}
-            <!-- Regular input -->
+            <!-- Regular input or select -->
+            {% if setting.options %}
+            <select
+              id="{{ setting.key }}"
+              name="{{ setting.key }}"
+              class="wizard-input w-full px-4 py-3 border border-gray-300 rounded-md shadow-sm focus:outline-none focus:ring-2 focus:ring-indigo-500 focus:border-transparent"
+            >
+              {% for opt in setting.options %}
+              <option value="{{ opt }}" {% if setting.current_value == opt %}selected{% elif not setting.current_value and opt == setting.default %}selected{% endif %}>{{ opt }}</option>
+              {% endfor %}
+            </select>
+            {% else %}
             <input
               type="{% if setting.sensitive %}password{% else %}text{% endif %}"
               id="{{ setting.key }}"
@@ -137,9 +148,10 @@
               value="{{ setting.current_value if setting.current_value else '' }}"
               class="wizard-input w-full px-4 py-3 border border-gray-300 rounded-md shadow-sm focus:outline-none focus:ring-2 focus:ring-indigo-500 focus:border-transparent"
               placeholder="{{ setting.description }}"
-              {% if setting.default is none or setting.key in ['admin_password', 'openai_api_key', 'azure_ai_key', 'azure_endpoint'] %}required{% endif %}
+              {% if setting.default is none or setting.key in ['admin_password'] %}required{% endif %}
             />
             {% endif %}
+            {% endif %}
 
             {% if setting.value_source == 'db' %}
             <span class="inline-flex items-center px-2 py-0.5 rounded text-xs font-medium bg-green-100 text-green-800 mt-1">DB</span>

frontend/templates/status_dashboard.html

@@ -174,11 +174,11 @@
                       Configure Now
                     </a>
                   {% endif %}
-                {% elif name == "OpenAI" %}
+                {% elif name == "AI Provider" %}
                   {% if provider.configured %}
                     <button
                       class="test-provider-btn inline-flex items-center px-2.5 py-1.5 border border-gray-300 text-xs font-medium rounded text-gray-700 bg-white hover:bg-gray-50 focus:outline-none focus:ring-2 focus:ring-offset-2 focus:ring-indigo-500"
-                      data-provider="openai">
+                      data-provider="ai_provider">
                       Test Connection
                     </button>
                   {% endif %}
@@ -521,8 +521,8 @@ document.addEventListener('DOMContentLoaded', function() {
         endpoint = '/api/onedrive/test-token';
       } else if (provider === 'google_drive') {
         endpoint = '/api/google-drive/test-token';
-      } else if (provider === 'openai') {
+      } else if (provider === 'ai_provider') {
-        endpoint = '/api/openai/test';
+        endpoint = '/api/ai/test';
       } else if (provider === 'azure') {
         endpoint = '/api/azure/test';
       }

tests/test_check_credentials.py

@@ -12,6 +12,7 @@ from app.tasks.check_credentials import (
     get_failure_state,
     save_failure_state,
     sync_test_azure_connection,
+    sync_test_ai_provider_connection,
     sync_test_openai_connection,
     unwrap_decorated_function,
 )
@@ -205,7 +206,7 @@ class TestCheckCredentialsTask:
     @patch("app.tasks.check_credentials.get_failure_state")
     @patch("app.tasks.check_credentials.get_provider_status")
     @patch("app.tasks.check_credentials.validate_storage_configs")
-    @patch("app.tasks.check_credentials.sync_test_openai_connection")
+    @patch("app.tasks.check_credentials.sync_test_ai_provider_connection")
     @patch("app.tasks.check_credentials.sync_test_azure_connection")
     @patch("app.tasks.check_credentials.sync_test_dropbox_token")
     @patch("app.tasks.check_credentials.sync_test_google_drive_token")
@@ -216,7 +217,7 @@ class TestCheckCredentialsTask:
         mock_gdrive,
         mock_dropbox,
         mock_azure,
-        mock_openai,
+        mock_ai_provider,
         mock_storage_configs,
         mock_provider_status,
         mock_get_state,
@@ -225,7 +226,7 @@ class TestCheckCredentialsTask:
         """Test checks all configured services."""
         mock_get_state.return_value = {}
         mock_provider_status.return_value = {
-            "OpenAI": {"configured": True},
+            "AI Provider": {"configured": True},
             "Azure AI": {"configured": True},
             "Dropbox": {"configured": True},
             "Google Drive": {"configured": True},
@@ -234,7 +235,7 @@ class TestCheckCredentialsTask:
         mock_storage_configs.return_value = {"dropbox": [], "google_drive": [], "onedrive": []}
 
         # All tests succeed
-        mock_openai.return_value = {"status": "success"}
+        mock_ai_provider.return_value = {"status": "success"}
         mock_azure.return_value = {"status": "success"}
         mock_dropbox.return_value = {"status": "success"}
         mock_gdrive.return_value = {"status": "success"}
@@ -249,14 +250,14 @@ class TestCheckCredentialsTask:
     @patch("app.tasks.check_credentials.get_failure_state")
     @patch("app.tasks.check_credentials.get_provider_status")
     @patch("app.tasks.check_credentials.validate_storage_configs")
-    @patch("app.tasks.check_credentials.sync_test_openai_connection")
+    @patch("app.tasks.check_credentials.sync_test_ai_provider_connection")
     def test_tracks_failures(
-        self, mock_openai, mock_storage_configs, mock_provider_status, mock_get_state, mock_save_state
+        self, mock_ai_provider, mock_storage_configs, mock_provider_status, mock_get_state, mock_save_state
     ):
         """Test tracks credential failures."""
         mock_get_state.return_value = {}
         mock_provider_status.return_value = {
-            "OpenAI": {"configured": True},
+            "AI Provider": {"configured": True},
             "Azure AI": {"configured": False},
             "Dropbox": {"configured": False},
             "Google Drive": {"configured": False},
@@ -264,7 +265,7 @@ class TestCheckCredentialsTask:
         }
         mock_storage_configs.return_value = {}
 
-        mock_openai.return_value = {"status": "error", "message": "Invalid API key"}
+        mock_ai_provider.return_value = {"status": "error", "message": "Invalid API key"}
 
         result = check_credentials()
 
@@ -281,7 +282,7 @@ class TestCheckCredentialsTask:
         """Test skips unconfigured services."""
         mock_get_state.return_value = {}
         mock_provider_status.return_value = {
-            "OpenAI": {"configured": False},
+            "AI Provider": {"configured": False},
             "Azure AI": {"configured": False},
             "Dropbox": {"configured": False},
             "Google Drive": {"configured": False},
@@ -298,15 +299,15 @@ class TestCheckCredentialsTask:
     @patch("app.tasks.check_credentials.get_failure_state")
     @patch("app.tasks.check_credentials.get_provider_status")
     @patch("app.tasks.check_credentials.validate_storage_configs")
-    @patch("app.tasks.check_credentials.sync_test_openai_connection")
+    @patch("app.tasks.check_credentials.sync_test_ai_provider_connection")
     @patch("app.tasks.check_credentials.notify_credential_failure")
     def test_sends_notifications_on_failure(
-        self, mock_notify, mock_openai, mock_storage_configs, mock_provider_status, mock_get_state, mock_save_state
+        self, mock_notify, mock_ai_provider, mock_storage_configs, mock_provider_status, mock_get_state, mock_save_state
     ):
         """Test sends notifications on credential failure."""
         mock_get_state.return_value = {}
         mock_provider_status.return_value = {
-            "OpenAI": {"configured": True},
+            "AI Provider": {"configured": True},
             "Azure AI": {"configured": False},
             "Dropbox": {"configured": False},
             "Google Drive": {"configured": False},
@@ -314,7 +315,7 @@ class TestCheckCredentialsTask:
         }
         mock_storage_configs.return_value = {}
 
-        mock_openai.return_value = {"status": "error", "message": "Invalid API key"}
+        mock_ai_provider.return_value = {"status": "error", "message": "Invalid API key"}
 
         check_credentials()
 
@@ -324,16 +325,16 @@ class TestCheckCredentialsTask:
     @patch("app.tasks.check_credentials.get_failure_state")
     @patch("app.tasks.check_credentials.get_provider_status")
     @patch("app.tasks.check_credentials.validate_storage_configs")
-    @patch("app.tasks.check_credentials.sync_test_openai_connection")
+    @patch("app.tasks.check_credentials.sync_test_ai_provider_connection")
     @patch("app.tasks.check_credentials.notify_credential_failure")
     def test_suppresses_notifications_after_threshold(
-        self, mock_notify, mock_openai, mock_storage_configs, mock_provider_status, mock_get_state, mock_save_state
+        self, mock_notify, mock_ai_provider, mock_storage_configs, mock_provider_status, mock_get_state, mock_save_state
     ):
         """Test suppresses notifications after failure threshold."""
         # Existing state with 4 failures
-        mock_get_state.return_value = {"OpenAI": {"count": 4, "last_notified": 12345}}
+        mock_get_state.return_value = {"AI Provider": {"count": 4, "last_notified": 12345}}
         mock_provider_status.return_value = {
-            "OpenAI": {"configured": True},
+            "AI Provider": {"configured": True},
             "Azure AI": {"configured": False},
             "Dropbox": {"configured": False},
             "Google Drive": {"configured": False},
@@ -341,7 +342,7 @@ class TestCheckCredentialsTask:
         }
         mock_storage_configs.return_value = {}
 
-        mock_openai.return_value = {"status": "error", "message": "Invalid API key"}
+        mock_ai_provider.return_value = {"status": "error", "message": "Invalid API key"}
 
         check_credentials()
 
@@ -352,15 +353,15 @@ class TestCheckCredentialsTask:
     @patch("app.tasks.check_credentials.get_failure_state")
     @patch("app.tasks.check_credentials.get_provider_status")
     @patch("app.tasks.check_credentials.validate_storage_configs")
-    @patch("app.tasks.check_credentials.sync_test_openai_connection")
+    @patch("app.tasks.check_credentials.sync_test_ai_provider_connection")
     def test_tracks_recovery(
-        self, mock_openai, mock_storage_configs, mock_provider_status, mock_get_state, mock_save_state
+        self, mock_ai_provider, mock_storage_configs, mock_provider_status, mock_get_state, mock_save_state
     ):
         """Test tracks service recovery."""
         # Existing state with failures
-        mock_get_state.return_value = {"OpenAI": {"count": 2, "last_notified": 12345}}
+        mock_get_state.return_value = {"AI Provider": {"count": 2, "last_notified": 12345}}
         mock_provider_status.return_value = {
-            "OpenAI": {"configured": True},
+            "AI Provider": {"configured": True},
             "Azure AI": {"configured": False},
             "Dropbox": {"configured": False},
             "Google Drive": {"configured": False},
@@ -369,7 +370,7 @@ class TestCheckCredentialsTask:
         mock_storage_configs.return_value = {}
 
         # Service is now valid
-        mock_openai.return_value = {"status": "success"}
+        mock_ai_provider.return_value = {"status": "success"}
 
         result = check_credentials()
 
@@ -379,14 +380,14 @@ class TestCheckCredentialsTask:
     @patch("app.tasks.check_credentials.get_failure_state")
     @patch("app.tasks.check_credentials.get_provider_status")
     @patch("app.tasks.check_credentials.validate_storage_configs")
-    @patch("app.tasks.check_credentials.sync_test_openai_connection")
+    @patch("app.tasks.check_credentials.sync_test_ai_provider_connection")
     def test_handles_exception_during_check(
-        self, mock_openai, mock_storage_configs, mock_provider_status, mock_get_state, mock_save_state
+        self, mock_ai_provider, mock_storage_configs, mock_provider_status, mock_get_state, mock_save_state
     ):
         """Test handles exception during credential check."""
         mock_get_state.return_value = {}
         mock_provider_status.return_value = {
-            "OpenAI": {"configured": True},
+            "AI Provider": {"configured": True},
             "Azure AI": {"configured": False},
             "Dropbox": {"configured": False},
             "Google Drive": {"configured": False},
@@ -394,11 +395,11 @@ class TestCheckCredentialsTask:
         }
         mock_storage_configs.return_value = {}
 
-        mock_openai.side_effect = Exception("Network error")
+        mock_ai_provider.side_effect = Exception("Network error")
 
         result = check_credentials()
 
         # Should still complete and record the error
         assert result["failures"] == 1
-        assert "OpenAI" in result["results"]
+        assert "AI Provider" in result["results"]
-        assert result["results"]["OpenAI"]["status"] == "error"
+        assert result["results"]["AI Provider"]["status"] == "error"

tests/test_views_status.py

@@ -35,7 +35,7 @@ class TestStatusDashboard:
 
         mock_exists.return_value = False
         mock_providers.return_value = {
-            "OpenAI": {"configured": True, "status": "success"},
+            "AI Provider": {"configured": True, "status": "success"},
             "Azure AI": {"configured": False},
         }
         mock_settings.version = "1.0.0"