diff --git a/README.md b/README.md
index 75094d39db..f6d14bb840 100644
--- a/README.md
+++ b/README.md
@@ -168,7 +168,7 @@ Star Dify on GitHub and be instantly notified of new releases.
 > Before installing Dify, make sure your machine meets the following minimum system requirements:
 > 
 >- CPU >= 2 Core
->- RAM >= 4GB
+>- RAM >= 4 GiB
 
 </br>
 
diff --git a/README_CN.md b/README_CN.md
index 4553524ce5..689f98ccf4 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -174,7 +174,7 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
 在安装 Dify 之前，请确保您的机器满足以下最低系统要求：
 
 - CPU >= 2 Core
-- RAM >= 4GB
+- RAM >= 4 GiB
 
 ### 快速启动
 
diff --git a/api/services/enterprise/base.py b/api/services/enterprise/base.py
index 7d4fdfd2d0..380051b40d 100644
--- a/api/services/enterprise/base.py
+++ b/api/services/enterprise/base.py
@@ -1,4 +1,5 @@
 import os
+from urllib.parse import urljoin
 
 import requests
 
@@ -15,8 +16,7 @@ class EnterpriseRequest:
     @classmethod
     def send_request(cls, method, endpoint, json=None, params=None):
         headers = {"Content-Type": "application/json", "Enterprise-Api-Secret-Key": cls.secret_key}
-
-        url = f"{cls.base_url}{endpoint}"
+        url = urljoin(cls.base_url, endpoint)
         response = requests.request(method, url, json=json, params=params, headers=headers, proxies=cls.proxies)
 
         return response.json()
diff --git a/api/tests/unit_tests/core/model_runtime/model_providers/wenxin/test_text_embedding.py b/api/tests/unit_tests/core/model_runtime/model_providers/wenxin/test_text_embedding.py
index 5b159b49b6..a301f56d75 100644
--- a/api/tests/unit_tests/core/model_runtime/model_providers/wenxin/test_text_embedding.py
+++ b/api/tests/unit_tests/core/model_runtime/model_providers/wenxin/test_text_embedding.py
@@ -1,3 +1,5 @@
+import string
+
 import numpy as np
 
 from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
@@ -31,7 +33,7 @@ def test_max_chunks():
     max_chunks = embedding_model._get_max_chunks(model, credentials)
     embedding_model._create_text_embedding = _create_text_embedding
 
-    texts = ["0123456789" for i in range(0, max_chunks * 2)]
+    texts = [string.digits for i in range(0, max_chunks * 2)]
     result: TextEmbeddingResult = embedding_model.invoke(model, credentials, texts, "test")
     assert len(result.embeddings) == max_chunks * 2