Merge branch 'feat/rag-2' of https://github.com/langgenius/dify into feat/rag-2

api/core/datasource/utils/message_transformer.py

@@ -1,6 +1,6 @@
 import logging
 from collections.abc import Generator
-from mimetypes import guess_extension
+from mimetypes import guess_extension, guess_type
 from typing import Optional
 
 from core.datasource.datasource_file_manager import DatasourceFileManager
@@ -57,10 +57,13 @@ class DatasourceFileMessageTransformer:
             elif message.type == DatasourceMessage.MessageType.BLOB:
                 # get mime type and save blob to storage
                 meta = message.meta or {}
-
-                mimetype = meta.get("mime_type", "application/octet-stream")
                 # get filename from meta
                 filename = meta.get("file_name", None)
+
+                mimetype = meta.get("mime_type")
+                if not mimetype:
+                    mimetype = guess_type(filename)[0] or "application/octet-stream"
+                
                 # if message is str, encode it to bytes
 
                 if not isinstance(message.message, DatasourceMessage.BlobMessage):

api/core/file/file_manager.py

@@ -72,7 +72,9 @@ def to_prompt_message_content(
 
 
 def download(f: File, /):
-    if f.transfer_method in (FileTransferMethod.TOOL_FILE, FileTransferMethod.LOCAL_FILE):
+    if f.transfer_method in (FileTransferMethod.TOOL_FILE, 
+                             FileTransferMethod.LOCAL_FILE, 
+                             FileTransferMethod.DATASOURCE_FILE):
         return _download_file_content(f._storage_key)
     elif f.transfer_method == FileTransferMethod.REMOTE_URL:
         response = ssrf_proxy.get(f.remote_url, follow_redirects=True)