Fix: aliyun oss need to use s3 signature_version (#12766)

### What problem does this PR solve?

Aliyun OSS do not support boto s4 signature_version which will lead to
an error:

```
botocore.exceptions.ClientError: An error occurred (InvalidArgument) when calling the PutObject operation: aws-chunked encoding is not supported with the specified x-amz-content-sha256 value
```

According to aliyun oss docs, oss_conn need to use s3 signature_version.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

conf/service_conf.yaml

@@ -68,9 +68,11 @@ user_default_llm:
 # oss:
 #   access_key: 'access_key'
 #   secret_key: 'secret_key'
-#   endpoint_url: 'http://oss-cn-hangzhou.aliyuncs.com'
+#   endpoint_url: 'https://s3.oss-cn-hangzhou.aliyuncs.com'
 #   region: 'cn-hangzhou'
 #   bucket: 'bucket_name'
+#   signature_version: 's3'
+#   addressing_style: 'virtual'
 # azure:
 #   auth_type: 'sas'
 #   container_url: 'container_url'

docker/.env

@@ -227,6 +227,7 @@ EMBEDDING_BATCH_SIZE=${EMBEDDING_BATCH_SIZE:-16}
 # ENDPOINT=http://oss-cn-hangzhou.aliyuncs.com
 # REGION=cn-hangzhou
 # BUCKET=ragflow65536
+# 
 
 # A user registration switch:
 # - Enable registration: 1

docker/service_conf.yaml.template

@@ -81,6 +81,8 @@ user_default_llm:
 #   region: '${REGION}'
 #   bucket: '${BUCKET}'
 #   prefix_path: '${OSS_PREFIX_PATH}'
+#   signature_version: 's3'
+#   addressing_style: 'virtual'
 # azure:
 #   auth_type: 'sas'
 #   container_url: 'container_url'

rag/utils/oss_conn.py

@@ -16,7 +16,6 @@
 import logging
 import boto3
 from botocore.exceptions import ClientError
-from botocore.config import Config
 import time
 from io import BytesIO
 from common.decorator import singleton
@@ -34,6 +33,8 @@ class RAGFlowOSS:
         self.region = self.oss_config.get('region', None)
         self.bucket = self.oss_config.get('bucket', None)
         self.prefix_path = self.oss_config.get('prefix_path', None)
+        self.signature_version = self.oss_config.get('signature_version', None)
+        self.addressing_style = self.oss_config.get('addressing_style', None)
         self.__open__()
 
     @staticmethod
@@ -62,6 +63,15 @@ class RAGFlowOSS:
             pass
 
         try:
+            config_kwargs = {}
+
+            if self.signature_version:
+                config_kwargs['signature_version'] = self.signature_version
+            if self.addressing_style:
+                config_kwargs['s3'] = {
+                    'addressing_style': self.addressing_style
+                }
+
             # Reference：https://help.aliyun.com/zh/oss/developer-reference/use-amazon-s3-sdks-to-access-oss
             self.conn = boto3.client(
                 's3',
@@ -69,7 +79,7 @@ class RAGFlowOSS:
                 aws_access_key_id=self.access_key,
                 aws_secret_access_key=self.secret_key,
                 endpoint_url=self.endpoint_url,
-                config=Config(s3={"addressing_style": "virtual"}, signature_version='v4')
+                config=config_kwargs
             )
         except Exception:
             logging.exception(f"Fail to connect at region {self.region}")