Merge pull request #3409 from BerriAI/litellm_revert_passing_langfuse_traces_alerts

fix - revert init langfuse client on slack alerts

litellm/integrations/slack_alerting.py

@@ -48,19 +48,6 @@ class SlackAlerting:
         self.internal_usage_cache = DualCache()
         self.async_http_handler = AsyncHTTPHandler()
         self.alert_to_webhook_url = alert_to_webhook_url
-        self.langfuse_logger = None
-
-        try:
-            from litellm.integrations.langfuse import LangFuseLogger
-
-            self.langfuse_logger = LangFuseLogger(
-                os.getenv("LANGFUSE_PUBLIC_KEY"),
-                os.getenv("LANGFUSE_SECRET_KEY"),
-                flush_interval=1,
-            )
-        except:
-            pass
-
         pass
 
     def update_values(
@@ -110,62 +97,8 @@ class SlackAlerting:
         start_time: Optional[datetime.datetime] = None,
         end_time: Optional[datetime.datetime] = None,
     ):
-        import uuid
-
-        # For now: do nothing as we're debugging why this is not working as expected
-        if request_data is not None:
-            trace_id = request_data.get("metadata", {}).get(
-                "trace_id", None
-            )  # get langfuse trace id
-            if trace_id is None:
-                trace_id = "litellm-alert-trace-" + str(uuid.uuid4())
-                request_data["metadata"]["trace_id"] = trace_id
-        elif kwargs is not None:
-            _litellm_params = kwargs.get("litellm_params", {})
-            trace_id = _litellm_params.get("metadata", {}).get(
-                "trace_id", None
-            )  # get langfuse trace id
-            if trace_id is None:
-                trace_id = "litellm-alert-trace-" + str(uuid.uuid4())
-                _litellm_params["metadata"]["trace_id"] = trace_id
-
-        # Log hanging request as an error on langfuse
-        if type == "hanging_request":
-            if self.langfuse_logger is not None:
-                _logging_kwargs = copy.deepcopy(request_data)
-                if _logging_kwargs is None:
-                    _logging_kwargs = {}
-                _logging_kwargs["litellm_params"] = {}
-                request_data = request_data or {}
-                _logging_kwargs["litellm_params"]["metadata"] = request_data.get(
-                    "metadata", {}
-                )
-                # log to langfuse in a separate thread
-                import threading
-
-                threading.Thread(
-                    target=self.langfuse_logger.log_event,
-                    args=(
-                        _logging_kwargs,
-                        None,
-                        start_time,
-                        end_time,
-                        None,
-                        print,
-                        "ERROR",
-                        "Requests is hanging",
-                    ),
-                ).start()
-
-        _langfuse_host = os.environ.get("LANGFUSE_HOST", "https://cloud.langfuse.com")
-        _langfuse_project_id = os.environ.get("LANGFUSE_PROJECT_ID")
-
-        # langfuse urls look like: https://us.cloud.langfuse.com/project/************/traces/litellm-alert-trace-ididi9dk-09292-************
-
-        _langfuse_url = (
-            f"{_langfuse_host}/project/{_langfuse_project_id}/traces/{trace_id}"
-        )
-        request_info += f"\n🪢 Langfuse Trace: {_langfuse_url}"
+        # do nothing for now
+        pass
         return request_info
 
     def _response_taking_too_long_callback(
@@ -242,10 +175,6 @@ class SlackAlerting:
         request_info = f"\nRequest Model: `{model}`\nAPI Base: `{api_base}`\nMessages: `{messages}`"
         slow_message = f"`Responses are slow - {round(time_difference_float,2)}s response time > Alerting threshold: {self.alerting_threshold}s`"
         if time_difference_float > self.alerting_threshold:
-            if "langfuse" in litellm.success_callback:
-                request_info = self._add_langfuse_trace_id_to_alert(
-                    request_info=request_info, kwargs=kwargs, type="slow_response"
-                )
             # add deployment latencies to alert
             if (
                 kwargs is not None

litellm/model_prices_and_context_window_backup.json

@@ -338,6 +338,18 @@
         "output_cost_per_second": 0.0001, 
         "litellm_provider": "azure"
     },
+    "azure/gpt-4-turbo-2024-04-09": {
+        "max_tokens": 4096,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00001,
+        "output_cost_per_token": 0.00003,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": true
+    },
     "azure/gpt-4-0125-preview": {
         "max_tokens": 4096,
         "max_input_tokens": 128000,
@@ -813,6 +825,7 @@
         "litellm_provider": "anthropic",
         "mode": "chat",
         "supports_function_calling": true,
+        "supports_vision": true,
         "tool_use_system_prompt_tokens": 264
     },
     "claude-3-opus-20240229": {
@@ -824,6 +837,7 @@
         "litellm_provider": "anthropic",
         "mode": "chat",
         "supports_function_calling": true,
+        "supports_vision": true,
         "tool_use_system_prompt_tokens": 395
     },
     "claude-3-sonnet-20240229": {
@@ -835,6 +849,7 @@
         "litellm_provider": "anthropic",
         "mode": "chat",
         "supports_function_calling": true,
+        "supports_vision": true,
         "tool_use_system_prompt_tokens": 159
     },
     "text-bison": {
@@ -1142,7 +1157,8 @@
         "output_cost_per_token": 0.000015,
         "litellm_provider": "vertex_ai-anthropic_models",
         "mode": "chat",
-        "supports_function_calling": true
+        "supports_function_calling": true,
+        "supports_vision": true
     },
     "vertex_ai/claude-3-haiku@20240307": {
         "max_tokens": 4096, 
@@ -1152,7 +1168,8 @@
         "output_cost_per_token": 0.00000125,
         "litellm_provider": "vertex_ai-anthropic_models",
         "mode": "chat",
-        "supports_function_calling": true
+        "supports_function_calling": true,
+        "supports_vision": true
     },
     "vertex_ai/claude-3-opus@20240229": {
         "max_tokens": 4096,
@@ -1162,7 +1179,8 @@
         "output_cost_per_token": 0.0000075,
         "litellm_provider": "vertex_ai-anthropic_models",
         "mode": "chat",
-        "supports_function_calling": true
+        "supports_function_calling": true,
+        "supports_vision": true
     },
     "textembedding-gecko": {
         "max_tokens": 3072,
@@ -1581,6 +1599,7 @@
         "litellm_provider": "openrouter",
         "mode": "chat",
         "supports_function_calling": true,
+        "supports_vision": true,
         "tool_use_system_prompt_tokens": 395
     },
     "openrouter/google/palm-2-chat-bison": {
@@ -1929,7 +1948,8 @@
         "output_cost_per_token": 0.000015,
         "litellm_provider": "bedrock",
         "mode": "chat",
-        "supports_function_calling": true
+        "supports_function_calling": true,
+        "supports_vision": true
     },
     "anthropic.claude-3-haiku-20240307-v1:0": {
         "max_tokens": 4096, 
@@ -1939,7 +1959,8 @@
         "output_cost_per_token": 0.00000125,
         "litellm_provider": "bedrock",
         "mode": "chat",
-        "supports_function_calling": true
+        "supports_function_calling": true,
+        "supports_vision": true
     },
     "anthropic.claude-3-opus-20240229-v1:0": {
         "max_tokens": 4096,
@@ -1949,7 +1970,8 @@
         "output_cost_per_token": 0.000075,
         "litellm_provider": "bedrock",
         "mode": "chat",
-        "supports_function_calling": true
+        "supports_function_calling": true,
+        "supports_vision": true
     },
     "anthropic.claude-v1": {
         "max_tokens": 8191,