Litellm dev 12 12 2024 (#7203)

* fix(azure/): support passing headers to azure openai endpoints

Fixes https://github.com/BerriAI/litellm/issues/6217

* fix(utils.py): move default tokenizer to just openai

hf tokenizer makes network calls when trying to get the tokenizer - this slows down execution time calls

* fix(router.py): fix pattern matching router - add generic "*" to it as well

Fixes issue where generic "*" model access group wouldn't show up

* fix(pattern_match_deployments.py): match to more specific pattern

match to more specific pattern

allows setting generic wildcard model access group and excluding specific models more easily

* fix(proxy_server.py): fix _delete_deployment to handle base case where db_model list is empty

don't delete all router models  b/c of empty list

Fixes https://github.com/BerriAI/litellm/issues/7196

* fix(anthropic/): fix handling response_format for anthropic messages with anthropic api

* fix(fireworks_ai/): support passing response_format + tool call in same message

Addresses https://github.com/BerriAI/litellm/issues/7135

* Revert "fix(fireworks_ai/): support passing response_format + tool call in same message"

This reverts commit 6a30dc6929.

* test: fix test

* fix(replicate/): fix replicate default retry/polling logic

* test: add unit testing for router pattern matching

* test: update test to use default oai tokenizer

* test: mark flaky test

* test: skip flaky test

litellm/utils.py

@@ -1214,7 +1214,9 @@ def client(original_function):  # noqa: PLR0915
 
 
 @lru_cache(maxsize=128)
-def _select_tokenizer(model: str):
+def _select_tokenizer(
+    model: str,
+):
     if model in litellm.cohere_models and "command-r" in model:
         # cohere
         cohere_tokenizer = Tokenizer.from_pretrained(
@@ -1235,19 +1237,10 @@ def _select_tokenizer(model: str):
         return {"type": "huggingface_tokenizer", "tokenizer": tokenizer}
     # default - tiktoken
     else:
-        tokenizer = None
-        if (
-            model in litellm.open_ai_chat_completion_models
-            or model in litellm.open_ai_text_completion_models
-            or model in litellm.open_ai_embedding_models
-        ):
-            return {"type": "openai_tokenizer", "tokenizer": encoding}
-
-        try:
-            tokenizer = Tokenizer.from_pretrained(model)
-            return {"type": "huggingface_tokenizer", "tokenizer": tokenizer}
-        except Exception:
-            return {"type": "openai_tokenizer", "tokenizer": encoding}
+        return {
+            "type": "openai_tokenizer",
+            "tokenizer": encoding,
+        }  # default to openai tokenizer
 
 
 def encode(model="", text="", custom_tokenizer: Optional[dict] = None):