LiteLLM Minor Fixes & Improvements (01/16/2025) - p2 (#7828)

* fix(vertex_ai/gemini/transformation.py): handle 'http://' image urls

* test: add base test for `http:` url's

* fix(factory.py/get_image_details): follow redirects

allows http calls to work

* fix(codestral/): fix stream chunk parsing on last chunk of stream

* Azure ad token provider (#6917)

* Update azure.py

Added optional parameter azure ad token provider

* Added parameter to main.py

* Found token provider arg location

* Fixed embeddings

* Fixed ad token provider

---------

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>

* fix: fix linting errors

* fix(main.py): leave out o1 route for azure ad token provider, for now

get v0 out for sync azure gpt route to begin with

* test: skip http:// test for fireworks ai

model does not support it

* refactor: cleanup dead code

* fix: revert http:// url passthrough for gemini

google ai studio raises errors

* test: fix test

---------

Co-authored-by: bahtman <anton@baht.dk>

tests/llm_translation/base_llm_unit_tests.py

@@ -461,8 +461,15 @@ class BaseLLMChatTest(ABC):
         pass
 
     @pytest.mark.parametrize("detail", [None, "low", "high"])
+    @pytest.mark.parametrize(
+        "image_url",
+        [
+            "http://img1.etsystatic.com/260/0/7813604/il_fullxfull.4226713999_q86e.jpg",
+            "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
+        ],
+    )
     @pytest.mark.flaky(retries=4, delay=1)
-    def test_image_url(self, detail):
+    def test_image_url(self, detail, image_url):
         litellm.set_verbose = True
         from litellm.utils import supports_vision
 
@@ -472,6 +479,10 @@ class BaseLLMChatTest(ABC):
         base_completion_call_args = self.get_base_completion_call_args()
         if not supports_vision(base_completion_call_args["model"], None):
             pytest.skip("Model does not support image input")
+        elif "http://" in image_url and "fireworks_ai" in base_completion_call_args.get(
+            "model"
+        ):
+            pytest.skip("Model does not support http:// input")
 
         messages = [
             {
@@ -481,7 +492,7 @@ class BaseLLMChatTest(ABC):
                     {
                         "type": "image_url",
                         "image_url": {
-                            "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
+                            "url": image_url,
                         },
                     },
                 ],