Litellm Minor Fixes & Improvements (10/03/2024) (#6049)

* fix(proxy_server.py): remove spendlog fixes from proxy startup logic

Moves  https://github.com/BerriAI/litellm/pull/4794 to `/db_scripts` and cleans up some caching-related debug info (easier to trace debug logs)

* fix(langfuse_endpoints.py): Fixes https://github.com/BerriAI/litellm/issues/6041

* fix(azure.py): fix health checks for azure audio transcription models

Fixes https://github.com/BerriAI/litellm/issues/5999

* Feat: Add Literal AI Integration (#5653)

* feat: add Literal AI integration

* update readme

* Update README.md

* fix: address comments

* fix: remove literalai sdk

* fix: use HTTPHandler

* chore: add test

* fix: add asyncio lock

* fix(literal_ai.py): fix linting errors

* fix(literal_ai.py): fix linting errors

* refactor: cleanup

---------

Co-authored-by: Willy Douhard <willy.douhard@gmail.com>

tests/local_testing/test_literalai.py

@@ -0,0 +1,72 @@
+import os
+import sys
+
+sys.path.insert(0, os.path.abspath("../.."))
+
+import asyncio
+import logging
+
+import pytest
+
+import litellm
+from litellm._logging import verbose_logger
+from litellm.integrations.literal_ai import LiteralAILogger
+
+verbose_logger.setLevel(logging.DEBUG)
+
+litellm.set_verbose = True
+
+
+@pytest.mark.asyncio
+async def test_literalai_queue_logging():
+    try:
+        # Initialize LiteralAILogger
+        test_literalai_logger = LiteralAILogger()
+
+        litellm.callbacks = [test_literalai_logger]
+        test_literalai_logger.batch_size = 6
+        litellm.set_verbose = True
+
+        # Make multiple calls to ensure we don't hit the batch size
+        for _ in range(5):
+            response = await litellm.acompletion(
+                model="gpt-3.5-turbo",
+                messages=[{"role": "user", "content": "Test message"}],
+                max_tokens=10,
+                temperature=0.2,
+                mock_response="This is a mock response",
+            )
+
+        await asyncio.sleep(3)
+
+        # Check that logs are in the queue
+        assert len(test_literalai_logger.log_queue) == 5
+
+        # Now make calls to exceed the batch size
+        for _ in range(3):
+            await litellm.acompletion(
+                model="gpt-3.5-turbo",
+                messages=[{"role": "user", "content": "Test message"}],
+                max_tokens=10,
+                temperature=0.2,
+                mock_response="This is a mock response",
+            )
+
+        # Wait a short time for any asynchronous operations to complete
+        await asyncio.sleep(1)
+
+        print(
+            "Length of literalai log queue: {}".format(
+                len(test_literalai_logger.log_queue)
+            )
+        )
+        # Check that the queue was flushed after exceeding batch size
+        assert len(test_literalai_logger.log_queue) < 5
+
+        # Clean up
+        for cb in litellm.callbacks:
+            if isinstance(cb, LiteralAILogger):
+                await cb.async_httpx_client.client.aclose()
+
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")