Merge branch 'main' into litellm_embeddings_fix

Author: AlexsanderHamir

.circleci/config.yml

@@ -532,7 +532,7 @@ jobs:
           command: |
             pwd
             ls
-            python -m pytest -vv tests/router_unit_tests --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5
+            python -m pytest -vv tests/router_unit_tests --cov=litellm --cov-report=xml -x -s --junitxml=test-results/junit.xml --durations=5
           no_output_timeout: 120m
       - run:
           name: Rename the coverage files
@@ -1164,7 +1164,7 @@ jobs:
           command: |
             pwd
             ls
-            python -m pytest -vv tests/test_litellm --cov=litellm --cov-report=xml -s -v --junitxml=test-results/junit-litellm.xml --durations=10 -n 8
+            python -m pytest -vv tests/test_litellm --cov=litellm --cov-report=xml -v --junitxml=test-results/junit-litellm.xml --durations=10 -n 8
           no_output_timeout: 120m
       - run:
           name: Rename the coverage files
@@ -1396,7 +1396,7 @@ jobs:
           command: |
             pwd
             ls
-            python -m pytest -vv tests/image_gen_tests --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5
+            python -m pytest -vv tests/image_gen_tests --cov=litellm --cov-report=xml -x -v --junitxml=test-results/junit.xml --durations=5
           no_output_timeout: 120m
       - run:
           name: Rename the coverage files

docker/Dockerfile.dev

@@ -57,6 +57,9 @@ USER root
 # Install only runtime dependencies
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libssl3 \
+    libatomic1 \
+    nodejs \
+    npm \
     && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app

docs/my-website/docs/exception_mapping.md

@@ -112,6 +112,85 @@ except openai.APITimeoutError as e:
     print(f"should_retry: {should_retry}")
 ```
 
+## Advanced
+
+### Accessing Provider-Specific Error Details
+
+LiteLLM exceptions include a `provider_specific_fields` attribute that contains additional error information specific to each provider. This is particularly useful for Azure OpenAI, which provides detailed content filtering information.
+
+#### Azure OpenAI - Content Policy Violation Inner Error Access
+
+When Azure OpenAI returns content policy violations, you can access the detailed content filtering results through the `innererror` field:
+
+```python
+import litellm
+from litellm.exceptions import ContentPolicyViolationError
+
+try:
+    response = litellm.completion(
+        model="azure/gpt-4",
+        messages=[
+            {
+                "role": "user", 
+                "content": "Some content that might violate policies"
+            }
+        ]
+    )
+except ContentPolicyViolationError as e:
+    # Access Azure-specific error details
+    if e.provider_specific_fields and "innererror" in e.provider_specific_fields:
+        innererror = e.provider_specific_fields["innererror"]
+        
+        # Access content filter results
+        content_filter_result = innererror.get("content_filter_result", {})
+        
+        print(f"Content filter code: {innererror.get('code')}")
+        print(f"Hate filtered: {content_filter_result.get('hate', {}).get('filtered')}")
+        print(f"Violence severity: {content_filter_result.get('violence', {}).get('severity')}")
+        print(f"Sexual content filtered: {content_filter_result.get('sexual', {}).get('filtered')}")
+```
+
+**Example Response Structure:**
+
+When calling the LiteLLM proxy, content policy violations will return detailed filtering information:
+
+```json
+{
+  "error": {
+    "message": "litellm.ContentPolicyViolationError: AzureException - The response was filtered due to the prompt triggering Azure OpenAI's content management policy...",
+    "type": null,
+    "param": null,
+    "code": "400",
+    "provider_specific_fields": {
+      "innererror": {
+        "code": "ResponsibleAIPolicyViolation",
+        "content_filter_result": {
+          "hate": {
+            "filtered": true,
+            "severity": "high"
+          },
+          "jailbreak": {
+            "filtered": false,
+            "detected": false
+          },
+          "self_harm": {
+            "filtered": false,
+            "severity": "safe"
+          },
+          "sexual": {
+            "filtered": false,
+            "severity": "safe"
+          },
+          "violence": {
+            "filtered": true,
+            "severity": "medium"
+          }
+        }
+      }
+    }
+  }
+}
+
 ## Details 
 
 To see how it's implemented - [check out the code](https://github.com/BerriAI/litellm/blob/a42c197e5a6de56ea576c73715e6c7c6b19fa249/litellm/utils.py#L1217)

docs/my-website/docs/providers/azure/videos.md

@@ -25,7 +25,6 @@ LiteLLM supports Azure OpenAI's video generation models including Sora with full
 import os 
 os.environ["AZURE_OPENAI_API_KEY"] = "your-azure-api-key"
 os.environ["AZURE_OPENAI_API_BASE"] = "https://your-resource.openai.azure.com/"
-os.environ["AZURE_OPENAI_API_VERSION"] = "2024-02-15-preview"
 ```
 
 ### Basic Usage
@@ -37,7 +36,6 @@ import time
 
 os.environ["AZURE_OPENAI_API_KEY"] = "your-azure-api-key"
 os.environ["AZURE_OPENAI_API_BASE"] = "https://your-resource.openai.azure.com/"
-os.environ["AZURE_OPENAI_API_VERSION"] = "2024-02-15-preview"
 
 # Generate video
 response = video_generation(
@@ -53,8 +51,7 @@ print(f"Initial Status: {response.status}")
 # Check status until video is ready
 while True:
     status_response = video_status(
-        video_id=response.id,
-        custom_llm_provider="azure"
+        video_id=response.id
     )
 
     print(f"Current Status: {status_response.status}")
@@ -69,8 +66,7 @@ while True:
 
 # Download video content when ready
 video_bytes = video_content(
-    video_id=response.id,
-    custom_llm_provider="azure"
+    video_id=response.id
 )
 
 # Save to file
@@ -87,7 +83,6 @@ Here's how to call Azure video generation models with the LiteLLM Proxy Server
 ```bash
 export AZURE_OPENAI_API_KEY="your-azure-api-key"
 export AZURE_OPENAI_API_BASE="https://your-resource.openai.azure.com/"
-export AZURE_OPENAI_API_VERSION="2024-02-15-preview"
 ```
 
 ### 2. Start the proxy 
@@ -102,7 +97,6 @@ model_list:
       model: azure/sora-2
       api_key: os.environ/AZURE_OPENAI_API_KEY
       api_base: os.environ/AZURE_OPENAI_API_BASE
-      api_version: "2024-02-15-preview"
 ```
 
 </TabItem>
@@ -211,8 +205,7 @@ general_settings:
 ```python
 # Download video content
 video_bytes = video_content(
-    video_id="video_1234567890",
-    model="azure/sora-2"
+    video_id="video_1234567890"
 )
 
 # Save to file
@@ -243,8 +236,7 @@ def generate_and_download_video(prompt):
     
     # Step 3: Download video
     video_bytes = litellm.video_content(
-        video_id=video_id,
-        custom_llm_provider="azure"
+        video_id=video_id
     )
     
     # Step 4: Save to file
@@ -264,9 +256,9 @@ video_file = generate_and_download_video(
 ```python
 # Video editing with reference image
 response = litellm.video_remix(
+    video_id="video_456",
     prompt="Make the cat jump higher",
     input_reference=open("path/to/image.jpg", "rb"),  # Reference image as file object
-    custom_llm_provider="azure"
     seconds="8"
 )
 

docs/my-website/docs/providers/gemini.md

@@ -10,7 +10,7 @@ import TabItem from '@theme/TabItem';
 | Provider Route on LiteLLM | `gemini/` |
 | Provider Doc | [Google AI Studio ↗](https://aistudio.google.com/) |
 | API Endpoint for Provider | https://generativelanguage.googleapis.com |
-| Supported OpenAI Endpoints | `/chat/completions`, [`/embeddings`](../embedding/supported_embedding#gemini-ai-embedding-models), `/completions` |
+| Supported OpenAI Endpoints | `/chat/completions`, [`/embeddings`](../embedding/supported_embedding#gemini-ai-embedding-models), `/completions`, [`/videos`](./gemini/videos.md) |
 | Pass-through Endpoint | [Supported](../pass_through/google_ai_studio.md) |
 
 <br />