diff --git a/assets/wechat.jpg b/assets/wechat.jpg
index 85c23dee1..d30306a13 100644
Binary files a/assets/wechat.jpg and b/assets/wechat.jpg differ
diff --git a/dbgpt/_version.py b/dbgpt/_version.py
index f22beb48e..9fe51180f 100644
--- a/dbgpt/_version.py
+++ b/dbgpt/_version.py
@@ -1 +1 @@
-version = "0.5.7"
+version = "0.5.8"
diff --git a/dbgpt/rag/embedding/embeddings.py b/dbgpt/rag/embedding/embeddings.py
index a73cd7890..401030e75 100644
--- a/dbgpt/rag/embedding/embeddings.py
+++ b/dbgpt/rag/embedding/embeddings.py
@@ -294,7 +294,7 @@ class HuggingFaceBgeEmbeddings(BaseModel, Embeddings):
         kwargs["client"] = sentence_transformers.SentenceTransformer(
             kwargs.get("model_name"),
             cache_folder=kwargs.get("cache_folder"),
-            **kwargs.get("model_kwargs"),
+            **(kwargs.get("model_kwargs") or {}),
         )
 
         super().__init__(**kwargs)
diff --git a/dbgpt/rag/embedding/rerank.py b/dbgpt/rag/embedding/rerank.py
index a226f89c8..482d77801 100644
--- a/dbgpt/rag/embedding/rerank.py
+++ b/dbgpt/rag/embedding/rerank.py
@@ -17,7 +17,7 @@ class CrossEncoderRerankEmbeddings(BaseModel, RerankEmbeddings):
 
     client: Any  #: :meta private:
     model_name: str = "BAAI/bge-reranker-base"
-    max_length: int
+    max_length: int = None    # type: ignore
     """Max length for input sequences. Longer sequences will be truncated. If None, max
         length of the model will be used"""
     """Model name to use."""
diff --git a/setup.py b/setup.py
index 2d4d3bf6f..015a83ded 100644
--- a/setup.py
+++ b/setup.py
@@ -19,7 +19,7 @@ with open("README.md", mode="r", encoding="utf-8") as fh:
 IS_DEV_MODE = os.getenv("IS_DEV_MODE", "true").lower() == "true"
 # If you modify the version, please modify the version in the following files:
 # dbgpt/_version.py
-DB_GPT_VERSION = os.getenv("DB_GPT_VERSION", "0.5.7")
+DB_GPT_VERSION = os.getenv("DB_GPT_VERSION", "0.5.8")
 
 BUILD_NO_CACHE = os.getenv("BUILD_NO_CACHE", "true").lower() == "true"
 LLAMA_CPP_GPU_ACCELERATION = (