feat(guardrails): add Microsoft Purview DLP guardrail

.circleci/config.yml

@@ -2541,7 +2541,6 @@ jobs:
           paths:
             - litellm-docker-database.tar.zst
 
-
   test_bad_database_url:
     machine:
       image: ubuntu-2204:2024.04.1

litellm/litellm_core_utils/prompt_templates/common_utils.py

@@ -1204,12 +1204,8 @@ def get_last_user_message(messages: List[AllMessageValues]) -> Optional[str]:
         {"role": "assistant", "content": "I'm good, thank you!"},
         {"role": "user", "content": "What is the weather in Tokyo?"},
     ]
-    get_user_prompt(messages) -> "What is the weather in Tokyo?"
+    get_last_user_message(messages) -> "What is the weather in Tokyo?"
     """
-    from litellm.litellm_core_utils.prompt_templates.common_utils import (
-        convert_content_list_to_str,
-    )
-
     if not messages:
         return None
 

litellm/proxy/guardrails/guardrail_hooks/azure/base.py

@@ -2,6 +2,9 @@
 from typing import TYPE_CHECKING, Any, Dict, List, Optional
 
 from litellm._logging import verbose_proxy_logger
+from litellm.litellm_core_utils.prompt_templates.common_utils import (
+    get_last_user_message,
+)
 from litellm.llms.custom_httpx.http_handler import (
     get_async_httpx_client,
     httpxSpecialProvider,
@@ -134,32 +137,4 @@ def get_user_prompt(self, messages: List["AllMessageValues"]) -> Optional[str]:
         ]
         get_user_prompt(messages) -> "What is the weather in Tokyo?"
         """
-        from litellm.litellm_core_utils.prompt_templates.common_utils import (
-            convert_content_list_to_str,
-        )
-
-        if not messages:
-            return None
-
-        # Iterate from the end to find the last consecutive block of user messages
-        user_messages = []
-        for message in reversed(messages):
-            if message.get("role") == "user":
-                user_messages.append(message)
-            else:
-                # Stop when we hit a non-user message
-                break
-
-        if not user_messages:
-            return None
-
-        # Reverse to get the messages in chronological order
-        user_messages.reverse()
-
-        user_prompt = ""
-        for message in user_messages:
-            text_content = convert_content_list_to_str(message)
-            user_prompt += text_content + "\n"
-
-        result = user_prompt.strip()
-        return result if result else None
+        return get_last_user_message(messages)

litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/__init__.py

@@ -0,0 +1,57 @@
+from typing import TYPE_CHECKING
+
+from litellm.types.guardrails import SupportedGuardrailIntegrations
+
+from .purview_dlp import MicrosoftPurviewDLPGuardrail
+
+if TYPE_CHECKING:
+    from litellm.types.guardrails import Guardrail, LitellmParams
+
+
+def initialize_guardrail(litellm_params: "LitellmParams", guardrail: "Guardrail"):
+    import litellm
+
+    tenant_id = getattr(litellm_params, "tenant_id", None)
+    client_id = getattr(litellm_params, "client_id", None)
+
+    # client_secret can be passed via the standard api_key field or as
+    # a dedicated client_secret parameter.
+    client_secret = litellm_params.api_key or getattr(
+        litellm_params, "client_secret", None
+    )
+
+    if not tenant_id:
+        raise ValueError("Microsoft Purview: tenant_id is required")
+    if not client_id:
+        raise ValueError("Microsoft Purview: client_id is required")
+    if not client_secret:
+        raise ValueError("Microsoft Purview: client_secret (or api_key) is required")
+
+    guardrail_name = guardrail.get("guardrail_name")
+    if not guardrail_name:
+        raise ValueError("Microsoft Purview: guardrail_name is required")
+
+    purview_guardrail = MicrosoftPurviewDLPGuardrail(
+        guardrail_name=guardrail_name,
+        tenant_id=str(tenant_id),
+        client_id=str(client_id),
+        client_secret=str(client_secret),
+        purview_app_name=str(
+            getattr(litellm_params, "purview_app_name", None) or "LiteLLM"
+        ),
+        user_id_field=str(getattr(litellm_params, "user_id_field", None) or "user_id"),
+        event_hook=litellm_params.mode,
+        default_on=litellm_params.default_on,
+    )
+
+    litellm.logging_callback_manager.add_litellm_callback(purview_guardrail)
+    return purview_guardrail
+
+
+guardrail_initializer_registry = {
+    SupportedGuardrailIntegrations.MICROSOFT_PURVIEW.value: initialize_guardrail,
+}
+
+guardrail_class_registry = {
+    SupportedGuardrailIntegrations.MICROSOFT_PURVIEW.value: MicrosoftPurviewDLPGuardrail,
+}