Litellm dev 10 22 2024 (#6384)

* fix(utils.py): add 'disallowed_special' for token counting on .encode()

Fixes error when '<
endoftext
>' in string

* Revert "(fix) standard logging metadata + add unit testing  (#6366)" (#6381)

This reverts commit 8359cb6fa9.

* add new 35 mode lcard (#6378)

* Add claude 3 5 sonnet 20241022 models for all provides (#6380)

* Add Claude 3.5 v2 on Amazon Bedrock and Vertex AI.

* added anthropic/claude-3-5-sonnet-20241022

* add new 35 mode lcard

---------

Co-authored-by: Paul Gauthier <paul@paulg.com>
Co-authored-by: lowjiansheng <15527690+lowjiansheng@users.noreply.github.com>

* test(skip-flaky-google-context-caching-test): google is not reliable. their sample code is also not working

* Fix metadata being overwritten in speech() (#6295)

* fix: adding missing redis cluster kwargs (#6318)

Co-authored-by: Ali Arian <ali.arian@breadfinancial.com>

* Add support for `max_completion_tokens` in Azure OpenAI (#6376)

Now that Azure supports `max_completion_tokens`, no need for special handling for this param and let it pass thru. More details: https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=python-secure#api-support

* build(model_prices_and_context_window.json): add voyage-finance-2 pricing

Closes https://github.com/BerriAI/litellm/issues/6371

* build(model_prices_and_context_window.json): fix llama3.1 pricing model name on map

Closes https://github.com/BerriAI/litellm/issues/6310

* feat(realtime_streaming.py): just log specific events

Closes https://github.com/BerriAI/litellm/issues/6267

* fix(utils.py): more robust checking if unmapped vertex anthropic model belongs to that family of models

Fixes https://github.com/BerriAI/litellm/issues/6383

* Fix Ollama stream handling for tool calls with None content (#6155)

* test(test_max_completions): update test now that azure supports 'max_completion_tokens'

* fix(handler.py): fix linting error

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Low Jian Sheng <15527690+lowjiansheng@users.noreply.github.com>
Co-authored-by: David Manouchehri <david.manouchehri@ai.moda>
Co-authored-by: Paul Gauthier <paul@paulg.com>
Co-authored-by: John HU <hszqqq12@gmail.com>
Co-authored-by: Ali Arian <113945203+ali-arian@users.noreply.github.com>
Co-authored-by: Ali Arian <ali.arian@breadfinancial.com>
Co-authored-by: Anand Taralika <46954145+taralika@users.noreply.github.com>
Co-authored-by: Nolan Tremelling <34580718+NolanTrem@users.noreply.github.com>

tests/llm_translation/test_max_completion_tokens.py

@@ -235,7 +235,7 @@ def test_all_model_configs():
         optional_params={},
         api_version="2022-12-01",
         drop_params=False,
-    ) == {"max_tokens": 10}
+    ) == {"max_completion_tokens": 10}
 
     from litellm.llms.bedrock.chat.converse_transformation import AmazonConverseConfig
 

tests/llm_translation/test_optional_params.py

@@ -775,3 +775,12 @@ def test_hosted_vllm_tool_param():
     )
     assert "tools" not in optional_params
     assert "tool_choice" not in optional_params
+
+
+def test_unmapped_vertex_anthropic_model():
+    optional_params = get_optional_params(
+        model="claude-3-5-sonnet-v250@20241022",
+        custom_llm_provider="vertex_ai",
+        max_retries=10,
+    )
+    assert "max_retries" not in optional_params

tests/local_testing/test_completion_cost.py

@@ -2587,3 +2587,50 @@ async def test_test_completion_cost_gpt4o_audio_output_from_model(stream):
     total_output_cost = output_audio_cost + output_text_cost
 
     assert round(cost, 2) == round(total_input_cost + total_output_cost, 2)
+
+
+def test_completion_cost_azure_ai_meta():
+    """
+    Relevant issue: https://github.com/BerriAI/litellm/issues/6310
+    """
+    from litellm import ModelResponse
+
+    os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
+    litellm.model_cost = litellm.get_model_cost_map(url="")
+
+    litellm.set_verbose = True
+    response = {
+        "id": "cmpl-55db75e0b05344058b0bd8ee4e00bf84",
+        "choices": [
+            {
+                "finish_reason": "stop",
+                "index": 0,
+                "logprobs": None,
+                "message": {
+                    "content": 'Here\'s one:\n\nWhy did the Linux kernel go to therapy?\n\nBecause it had a lot of "core" issues!\n\nHope that one made you laugh!',
+                    "refusal": None,
+                    "role": "assistant",
+                    "audio": None,
+                    "function_call": None,
+                    "tool_calls": [],
+                },
+            }
+        ],
+        "created": 1729243714,
+        "model": "azure_ai/Meta-Llama-3.1-70B-Instruct",
+        "object": "chat.completion",
+        "service_tier": None,
+        "system_fingerprint": None,
+        "usage": {
+            "completion_tokens": 32,
+            "prompt_tokens": 16,
+            "total_tokens": 48,
+            "completion_tokens_details": None,
+            "prompt_tokens_details": None,
+        },
+    }
+
+    model_response = ModelResponse(**response)
+    cost = completion_cost(model_response, custom_llm_provider="azure_ai")
+
+    assert cost > 0

tests/local_testing/test_token_counter.py

@@ -375,3 +375,7 @@ def test_img_url_token_counter(img_url):
 
     assert width is not None
     assert height is not None
+
+
+def test_token_encode_disallowed_special():
+    encode(model="gpt-3.5-turbo", text="Hello, world! <|endoftext|>")