(test) semantic caching

litellm/tests/test_caching.py

@@ -995,21 +995,29 @@ def test_redis_semantic_cache_completion():
     random_number = random.randint(
         1, 100000
     )  # add a random number to ensure it's always adding / reading from cache
-    messages = [
-        {"role": "user", "content": f"write a one sentence poem about: {random_number}"}
-    ]
+
+    print("testing semantic caching")
     litellm.cache = Cache(
         type="redis-semantic",
         host=os.environ["REDIS_HOST"],
         port=os.environ["REDIS_PORT"],
         password=os.environ["REDIS_PASSWORD"],
-        similarity_threshold=0.5,
+        similarity_threshold=0.8,
     )
-    print("test2 for Redis Caching - non streaming")
-    response1 = completion(model="gpt-3.5-turbo", messages=messages, max_tokens=20)
-    # response2 = completion(
-    #     model="gpt-3.5-turbo", messages=messages,max_tokens=20
-    # )
+    response1 = completion(
+        model="gpt-3.5-turbo",
+        messages=[
+            {
+                "role": "user",
+                "content": f"write a one sentence poem about: {random_number}",
+            }
+        ],
+        max_tokens=20,
+    )
+    print(f"response1: {response1}")
+
+    assert response1.id == "chatcmpl-8p5GejSWLJ1pDI1lfhc6Idhwd2bDJ"
+    # assert response1.choices[0].message == 1
 
 
 # test_redis_cache_completion()