fix(parallel_request_limiter.py): handle tpm/rpm limits being null

tests/test_parallel_key_gen.py

@@ -0,0 +1,33 @@
+# What this tests ?
+## Tests /key/generate by making 10 parallel requests, and asserting all are successful
+import pytest
+import asyncio
+import aiohttp
+
+
+async def generate_key(session, i):
+    url = "http://0.0.0.0:4000/key/generate"
+    headers = {"Authorization": "Bearer sk-1234", "Content-Type": "application/json"}
+    data = {
+        "models": ["azure-models"],
+        "aliases": {"mistral-7b": "gpt-3.5-turbo"},
+        "duration": None,
+    }
+
+    async with session.post(url, headers=headers, json=data) as response:
+        status = response.status
+        response_text = await response.text()
+
+        print(f"Response {i} (Status code: {status}):")
+        print(response_text)
+        print()
+
+        if status != 200:
+            raise Exception(f"Request {i} did not return a 200 status code: {status}")
+
+
+@pytest.mark.asyncio
+async def test_key_gen():
+    async with aiohttp.ClientSession() as session:
+        tasks = [generate_key(session, i) for i in range(1, 11)]
+        await asyncio.gather(*tasks)