(test) proxy + s3 caching

litellm/tests/test_configs/test_cloudflare_azure_with_cache_config.yaml

@@ -5,3 +5,11 @@ model_list:
       api_base: https://gateway.ai.cloudflare.com/v1/0399b10e77ac6668c80404a5ff49eb37/litellm-test/azure-openai/openai-gpt-4-test-v-1
       api_key: os.environ/AZURE_API_KEY
       api_version: 2023-07-01-preview
+
+litellm_settings:
+  set_verbose: True
+  cache: True          # set cache responses to True
+  cache_params:        # set cache params for s3
+    type: s3
+    s3_bucket_name: cache-bucket-litellm   # AWS Bucket Name for S3
+    s3_region_name: us-west-2              # AWS Region Name for S3

litellm/tests/test_proxy_server_caching.py

@@ -82,9 +82,22 @@ def test_chat_completion(client_no_auth):
         print(response)
 
         content = response["choices"][0]["message"]["content"]
+        response1_id = response["id"]
 
         print("\n content", content)
 
         assert len(content) > 1
+
+        print("\nmaking 2nd request to proxy. Testing caching + non streaming")
+        response = client_no_auth.post("/v1/chat/completions", json=test_data)
+        print(f"response - {response.text}")
+        assert response.status_code == 200
+
+        response = response.json()
+        print(response)
+        response2_id = response["id"]
+        assert response1_id == response2_id
+        litellm.disable_cache()
+
     except Exception as e:
         pytest.fail(f"LiteLLM Proxy test failed. Exception - {str(e)}")