From f063e03a245540ec01800fe2e8a7f7dc489826d2 Mon Sep 17 00:00:00 2001
From: D2758695161 <13510221939@163.com>
Date: Fri, 8 May 2026 12:06:28 +0800
Subject: [PATCH] fix: add bucket prefix to Azure Blob SPN and SAS storage
 operations (#14347)

## Summary

Fixes file collision between different datasets when using Azure Blob
storage (SPN or SAS authentication).

## Bug

azure_spn_conn.py and zure_sas_conn.py ignored the ucket parameter
entirely, storing all files flat with just the filename. This caused
files with the same name from different datasets (knowledge bases) to
overwrite each other.

## Fix

Prepend bucket/ as a path prefix in all methods (put,
m, get, obj_exist, get_presigned_url, health) to match the behavior of
MinIO and S3 implementations.

## Changes

- **rag/utils/azure_spn_conn.py**: Added {bucket}/ prefix to file paths
in all operations
- **rag/utils/azure_sas_conn.py**: Same fix applied for consistency
(also noted in the original issue)

## Testing

Manual verification: files from different datasets now stored under
distinct bucket/ prefixes, preventing collisions.

Fixes #14159

Co-authored-by: Hunter <hunter@yitong.ai>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
---
 rag/utils/azure_sas_conn.py | 11 ++++++-----
 rag/utils/azure_spn_conn.py | 12 +++++++-----
 2 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/rag/utils/azure_sas_conn.py b/rag/utils/azure_sas_conn.py
index 96442a2f07..9d43bcbf54 100644
--- a/rag/utils/azure_sas_conn.py
+++ b/rag/utils/azure_sas_conn.py
@@ -49,7 +49,7 @@ class RAGFlowAzureSasBlob:
 
     def health(self):
         _bucket, fnm, binary = "txtxtxtxt1", "txtxtxtxt1", b"_t@@@1"
-        return self.conn.upload_blob(name=fnm, data=BytesIO(binary), length=len(binary))
+        return self.conn.upload_blob(name=f"{_bucket}/{fnm}", data=BytesIO(binary), length=len(binary))
 
     def put(self, bucket, fnm, binary, tenant_id=None):
         blob_name = f"{bucket}/{fnm}"
@@ -77,13 +77,14 @@ class RAGFlowAzureSasBlob:
                 logging.exception(f"fail get {blob_name}")
                 self.__open__()
                 time.sleep(1)
-        return
+        return None
 
     def obj_exist(self, bucket, fnm):
+        blob_name = f"{bucket}/{fnm}"
         try:
-            return self.conn.get_blob_client(f"{bucket}/{fnm}").exists()
+            return self.conn.get_blob_client(f"{blob_name}").exists()
         except Exception:
-            logging.exception(f"Fail put {bucket}/{fnm}")
+            logging.exception(f"Fail put {blob_name}")
         return False
 
     def get_presigned_url(self, bucket, fnm, expires):
@@ -95,4 +96,4 @@ class RAGFlowAzureSasBlob:
                 logging.exception(f"fail get {blob_name}")
                 self.__open__()
                 time.sleep(1)
-        return
+        return None
diff --git a/rag/utils/azure_spn_conn.py b/rag/utils/azure_spn_conn.py
index e19c2e1fe1..ac23ecb172 100644
--- a/rag/utils/azure_spn_conn.py
+++ b/rag/utils/azure_spn_conn.py
@@ -64,7 +64,7 @@ class RAGFlowAzureSpnBlob:
 
     def health(self):
         _bucket, fnm, binary = "txtxtxtxt1", "txtxtxtxt1", b"_t@@@1"
-        f = self.conn.create_file(fnm)
+        f = self.conn.create_file(f"{_bucket}/{fnm}")
         f.append_data(binary, offset=0, length=len(binary))
         return f.flush_data(len(binary))
 
@@ -83,10 +83,11 @@ class RAGFlowAzureSpnBlob:
         return None
 
     def rm(self, bucket, fnm):
+        blob = f"{bucket}/{fnm}"
         try:
-            self.conn.delete_file(f"{bucket}/{fnm}")
+            self.conn.delete_file(f"{blob}")
         except Exception:
-            logging.exception(f"Fail rm {bucket}/{fnm}")
+            logging.exception(f"Fail rm {blob}")
 
     def get(self, bucket, fnm):
         blob = f"{bucket}/{fnm}"
@@ -102,11 +103,12 @@ class RAGFlowAzureSpnBlob:
         return None
 
     def obj_exist(self, bucket, fnm):
+        blob = f"{bucket}/{fnm}"
         try:
-            client = self.conn.get_file_client(f"{bucket}/{fnm}")
+            client = self.conn.get_blob_client(f"{blob}")
             return client.exists()
         except Exception:
-            logging.exception(f"Fail put {bucket}/{fnm}")
+            logging.exception(f"Fail put {blob}")
         return False
 
     def get_presigned_url(self, bucket, fnm, expires):