Merge branch 'main' into litellm_team_id_support

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

@@ -174,6 +174,31 @@ response = completion(
     messages=[{ "content": "Hello, how are you?","role": "user"}]
 )
 ```
+
+### Set `ssl_verify=False`
+
+This is done by setting your own `httpx.Client` 
+
+- For `litellm.completion` set `litellm.client_session=httpx.Client(verify=False)`
+- For `litellm.acompletion` set `litellm.aclient_session=AsyncClient.Client(verify=False)`
+```python
+import litellm, httpx
+
+# for completion
+litellm.client_session = httpx.Client(verify=False)
+response = litellm.completion(
+    model="gpt-3.5-turbo",
+    messages=messages,
+)
+
+# for acompletion
+litellm.aclient_session = httpx.AsyncClient(verify=False)
+response = litellm.acompletion(
+    model="gpt-3.5-turbo",
+    messages=messages,
+)
+```
+
 ### Using Helicone Proxy with LiteLLM
 ```python
 import os 

litellm/__init__.py

@@ -2,7 +2,7 @@
 import threading, requests, os
 from typing import Callable, List, Optional, Dict, Union, Any
 from litellm.caching import Cache
-from litellm._logging import set_verbose, _turn_on_debug
+from litellm._logging import set_verbose, _turn_on_debug, verbose_logger
 from litellm.proxy._types import KeyManagementSystem
 import httpx
 import dotenv

litellm/tests/test_proxy_server.py

@@ -225,9 +225,6 @@ def test_health(client_no_auth):
     try:
         response = client_no_auth.get("/health")
         assert response.status_code == 200
-        result = response.json()
-        print("\n response from health:", result)
-        assert result["unhealthy_count"] == 0
     except Exception as e:
         pytest.fail(f"LiteLLM Proxy test failed. Exception - {str(e)}")
 

model_prices_and_context_window.json

@@ -125,6 +125,15 @@
         "litellm_provider": "openai",
         "mode": "chat"
     },
+    "gpt-3.5-turbo-0125": {
+        "max_tokens": 16385,
+        "max_input_tokens": 16385,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.0000005,
+        "output_cost_per_token": 0.0000015,
+        "litellm_provider": "openai",
+        "mode": "chat"
+    },
     "gpt-3.5-turbo-16k": {
         "max_tokens": 16385,
         "max_input_tokens": 16385,

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "1.20.10"
+version = "1.20.11"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT"
@@ -63,7 +63,7 @@ requires = ["poetry-core", "wheel"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.commitizen]
-version = "1.20.10"
+version = "1.20.11"
 version_files = [
     "pyproject.toml:^version"
 ]