refactor: fix imports

tests/local_testing/test_amazing_vertex_completion.py

@@ -8,6 +8,8 @@ load_dotenv()
 import io
 import os
 
+from tests.local_testing.test_streaming import streaming_format_tests
+
 sys.path.insert(
     0, os.path.abspath("../..")
 )  # Adds the parent directory to the system path
@@ -32,7 +34,7 @@ from litellm.llms.vertex_ai_and_google_ai_studio.gemini.vertex_and_google_ai_stu
     _gemini_convert_messages_with_history,
 )
 from litellm.llms.vertex_ai_and_google_ai_studio.vertex_llm_base import VertexBase
-from litellm.tests.test_streaming import streaming_format_tests
+
 
 litellm.num_retries = 3
 litellm.cache = None
@@ -931,7 +933,7 @@ async def test_gemini_pro_function_calling_httpx(model, sync_mode):
             pytest.fail("An unexpected exception occurred - {}".format(str(e)))
 
 
-from litellm.tests.test_completion import response_format_tests
+from tests.local_testing.test_completion import response_format_tests
 
 
 @pytest.mark.parametrize(

tests/local_testing/test_anthropic_prompt_caching.py

@@ -9,6 +9,8 @@ load_dotenv()
 import io
 import os
 
+from tests.local_testing.test_streaming import streaming_format_tests
+
 sys.path.insert(
     0, os.path.abspath("../..")
 )  # Adds the parent directory to the system path
@@ -374,8 +376,6 @@ async def test_anthropic_api_prompt_caching_no_headers():
 @pytest.mark.asyncio()
 @pytest.mark.flaky(retries=3, delay=1)
 async def test_anthropic_api_prompt_caching_streaming():
-    from litellm.tests.test_streaming import streaming_format_tests
-
     response = await litellm.acompletion(
         model="anthropic/claude-3-5-sonnet-20240620",
         messages=[

tests/local_testing/test_completion_cost.py

@@ -829,7 +829,7 @@ def test_vertex_ai_embedding_completion_cost(caplog):
 #     """
 #     Relevant issue - https://github.com/BerriAI/litellm/issues/4630
 #     """
-#     from litellm.tests.test_amazing_vertex_completion import load_vertex_ai_credentials
+#     from tests.local_testing.test_amazing_vertex_completion import load_vertex_ai_credentials
 
 #     load_vertex_ai_credentials()
 #     os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"

tests/local_testing/test_proxy_server.py

@@ -235,7 +235,7 @@ async def test_team_disable_guardrails(mock_acompletion, client_no_auth):
         assert e.code == str(403)
 
 
-from litellm.tests.test_custom_callback_input import CompletionCustomHandler
+from tests.local_testing.test_custom_callback_input import CompletionCustomHandler
 
 
 @mock_patch_acompletion()
@@ -815,7 +815,7 @@ from litellm.proxy._types import (
 )
 from litellm.proxy.management_endpoints.internal_user_endpoints import new_user
 from litellm.proxy.management_endpoints.team_endpoints import team_member_add
-from litellm.tests.test_key_generate_prisma import prisma_client
+from tests.local_testing.test_key_generate_prisma import prisma_client
 
 
 @pytest.mark.parametrize(

tests/local_testing/test_sagemaker.py

@@ -9,6 +9,8 @@ load_dotenv()
 import io
 import os
 
+from tests.local_testing.test_streaming import streaming_format_tests
+
 sys.path.insert(
     0, os.path.abspath("../..")
 )  # Adds the parent directory to the system path
@@ -130,8 +132,6 @@ async def test_completion_sagemaker_messages_api(sync_mode):
 @pytest.mark.flaky(retries=3, delay=1)
 async def test_completion_sagemaker_stream(sync_mode, model):
     try:
-        from litellm.tests.test_streaming import streaming_format_tests
-
         litellm.set_verbose = False
         print("testing sagemaker")
         verbose_logger.setLevel(logging.DEBUG)

tests/local_testing/test_streaming.py

@@ -1145,7 +1145,9 @@ def test_completion_claude_stream_bad_key():
 
 @pytest.mark.parametrize("provider", ["vertex_ai_beta"])  # ""
 def test_vertex_ai_stream(provider):
-    from litellm.tests.test_amazing_vertex_completion import load_vertex_ai_credentials
+    from tests.local_testing.test_amazing_vertex_completion import (
+        load_vertex_ai_credentials,
+    )
 
     load_vertex_ai_credentials()
     litellm.set_verbose = True
@@ -3949,7 +3951,7 @@ def test_unit_test_perplexity_citations_chunk():
 @pytest.mark.flaky(retries=3, delay=1)
 def test_streaming_tool_calls_valid_json_str(model):
     if "vertex_ai" in model:
-        from litellm.tests.test_amazing_vertex_completion import (
+        from tests.local_testing.test_amazing_vertex_completion import (
             load_vertex_ai_credentials,
         )
 

tests/local_testing/test_text_completion.py

@@ -4114,7 +4114,7 @@ async def test_async_text_completion_chat_model_stream():
 async def test_completion_codestral_fim_api(model):
     try:
         if model == "vertex_ai/codestral@2405":
-            from litellm.tests.test_amazing_vertex_completion import (
+            from tests.local_testing.test_amazing_vertex_completion import (
                 load_vertex_ai_credentials,
             )
 
@@ -4158,7 +4158,7 @@ async def test_completion_codestral_fim_api(model):
 async def test_completion_codestral_fim_api_stream(model):
     try:
         if model == "vertex_ai/codestral@2405":
-            from litellm.tests.test_amazing_vertex_completion import (
+            from tests.local_testing.test_amazing_vertex_completion import (
                 load_vertex_ai_credentials,
             )
 

tests/local_testing/test_token_counter.py

@@ -21,8 +21,8 @@ from litellm import (
     get_modified_max_tokens,
     token_counter,
 )
-from litellm.tests.large_text import text
-from litellm.tests.messages_with_counts import (
+from tests.local_testing.large_text import text
+from tests.local_testing.messages_with_counts import (
     MESSAGES_TEXT,
     MESSAGES_WITH_IMAGES,
     MESSAGES_WITH_TOOLS,