adai/MemoryBear
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(multimodal): support tenant-aware document image storage and improve image placeholder labeling

Browse Source 
- Pass workspace_id to multimodal_service.process_files across app_chat_service, draft_run_service
- Fetch tenant_id from workspace in multimodal_service for proper file storage scoping
- Update image placeholder format from "[第N页 第M张图片]" to "[图片 第N页 第M张图片]" for clarity
- Add strict URL preservation rules to system prompt for agents handling document images
- Refactor _save_doc_image_to_storage to accept explicit tenant_id and workspace_id instead of inferring from FileMetadata
This commit is contained in:
Timebomb2018
2026-04-24 15:56:06 +08:00
parent 2c2551e15c
commit 74be09340c
3 changed files with 23 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
api/app/services/app_chat_service.py
View File

@@ -170,7 +170,8 @@ class AppChatService:
fu_config = fu_config.model_dump()
doc_img_recognition = isinstance(fu_config, dict) and fu_config.get("document_image_recognition", False)
processed_files = await multimodal_service.process_files(
files, document_image_recognition=doc_img_recognition
files, document_image_recognition=doc_img_recognition,
workspace_id=workspace_id
)
logger.info(f"处理了 {len(processed_files)} 个文件")
if doc_img_recognition and "vision" in (api_key_obj.capability or []) and any(
@@ -462,7 +463,8 @@ class AppChatService:
fu_config = fu_config.model_dump()
doc_img_recognition = isinstance(fu_config, dict) and fu_config.get("document_image_recognition", False)
processed_files = await multimodal_service.process_files(
files, document_image_recognition=doc_img_recognition
files, document_image_recognition=doc_img_recognition,
workspace_id=workspace_id
)
logger.info(f"处理了 {len(processed_files)} 个文件")
if doc_img_recognition and "vision" in (api_key_obj.capability or []) and any(