From 7348956bf276dbbe04c2427d4ae2432bd77723ad Mon Sep 17 00:00:00 2001
From: Krrish Dholakia <krrishdholakia@gmail.com>
Date: Mon, 19 Feb 2024 14:17:52 -0800
Subject: [PATCH] docs(enterprise.md): add google text moderations to the docs

---
 docs/my-website/docs/proxy/enterprise.md      | 55 +++++++++++++++++++
 .../google_text_moderation.py                 | 19 ++++---
 2 files changed, 65 insertions(+), 9 deletions(-)

diff --git a/docs/my-website/docs/proxy/enterprise.md b/docs/my-website/docs/proxy/enterprise.md
index f881215e6..ad0691f48 100644
--- a/docs/my-website/docs/proxy/enterprise.md
+++ b/docs/my-website/docs/proxy/enterprise.md
@@ -13,6 +13,7 @@ Features here are behind a commercial license in our `/enterprise` folder. [**Se
 
 Features: 
 - [ ] Content Moderation with LlamaGuard 
+- [ ] Content Moderation with Google Text Moderations 
 - [ ] Tracking Spend for Custom Tags
  
 ## Content Moderation with LlamaGuard 
@@ -35,6 +36,60 @@ os.environ["AWS_SECRET_ACCESS_KEY"] = ""
 os.environ["AWS_REGION_NAME"] = ""
 ```
 
+## Content Moderation with Google Text Moderation 
+
+Requires your GOOGLE_APPLICATION_CREDENTIALS to be set in your .env (same as VertexAI).
+
+How to enable this in your config.yaml: 
+
+```yaml 
+litellm_settings:
+   callbacks: ["google_text_moderation"]
+```
+
+### Set custom confidence thresholds
+
+Google Moderations checks the test against several categories. [Source](https://cloud.google.com/natural-language/docs/moderating-text#safety_attribute_confidence_scores)
+
+#### Set global default confidence threshold
+
+By default this is set to 0.8. But you can override this in your config.yaml.
+
+```yaml
+litellm_settings: 
+    google_moderation_confidence_threshold: 0.4 
+```
+
+#### Set category-specific confidence threshold
+
+Set a category specific confidence threshold in your config.yaml. If none set, the global default will be used. 
+
+```yaml
+litellm_settings: 
+    toxic_confidence_threshold: 0.1
+```
+
+Here are the category specific values: 
+
+| Category | Setting |
+| -------- | -------- |
+| "toxic" | toxic_confidence_threshold: 0.1 | 
+| "insult" | insult_confidence_threshold: 0.1 | 
+| "profanity" | profanity_confidence_threshold: 0.1 | 
+| "derogatory" | derogatory_confidence_threshold: 0.1 | 
+| "sexual" | sexual_confidence_threshold: 0.1 | 
+| "death_harm_and_tragedy" | death_harm_and_tragedy_threshold: 0.1 | 
+| "violent" | violent_threshold: 0.1 | 
+| "firearms_and_weapons" | firearms_and_weapons_threshold: 0.1 | 
+| "public_safety" | public_safety_threshold: 0.1 | 
+| "health" | health_threshold: 0.1 | 
+| "religion_and_belief" | religion_and_belief_threshold: 0.1 | 
+| "illicit_drugs" | illicit_drugs_threshold: 0.1 | 
+| "war_and_conflict" | war_and_conflict_threshold: 0.1 | 
+| "politics" | politics_threshold: 0.1 | 
+| "finance" | finance_threshold: 0.1 | 
+| "legal" | legal_threshold: 0.1 |
+
 ## Tracking Spend for Custom Tags
 
 Requirements: 
diff --git a/enterprise/enterprise_hooks/google_text_moderation.py b/enterprise/enterprise_hooks/google_text_moderation.py
index a6a48a385..dad8bac45 100644
--- a/enterprise/enterprise_hooks/google_text_moderation.py
+++ b/enterprise/enterprise_hooks/google_text_moderation.py
@@ -60,14 +60,9 @@ class _ENTERPRISE_GoogleTextModeration(CustomLogger):
         self.language_document = language_v1.types.Document
         self.document_type = language_v1.types.Document.Type.PLAIN_TEXT
 
-        if hasattr(litellm, "google_moderation_confidence_threshold"):
-            default_confidence_threshold = (
-                litellm.google_moderation_confidence_threshold
-            )
-        else:
-            default_confidence_threshold = (
-                0.8  # by default require a high confidence (80%) to fail
-            )
+        default_confidence_threshold = (
+            litellm.google_moderation_confidence_threshold or 0.8
+        )  # by default require a high confidence (80%) to fail
 
         for category in self.confidence_categories:
             if hasattr(litellm, f"{category}_confidence_threshold"):
@@ -82,6 +77,13 @@ class _ENTERPRISE_GoogleTextModeration(CustomLogger):
                     f"{category}_confidence_threshold",
                     default_confidence_threshold,
                 )
+            set_confidence_value = getattr(
+                self,
+                f"{category}_confidence_threshold",
+            )
+            verbose_proxy_logger.info(
+                f"Google Text Moderation: {category}_confidence_threshold: {set_confidence_value}"
+            )
 
     def print_verbose(self, print_statement):
         try:
@@ -112,7 +114,6 @@ class _ENTERPRISE_GoogleTextModeration(CustomLogger):
 
             # Make the request
             response = self.client.moderate_text(request=request)
-            print(response)
             for category in response.moderation_categories:
                 category_name = category.name
                 category_name = category_name.lower()