enh: enable selecting individual files from collection

backend/open_webui/apps/webui/models/files.py

@@ -50,6 +50,14 @@ class FileModel(BaseModel):
 ####################
 
 
+class FileMeta(BaseModel):
+    name: Optional[str] = None
+    content_type: Optional[str] = None
+    size: Optional[int] = None
+
+    model_config = ConfigDict(extra="allow")
+
+
 class FileModelResponse(BaseModel):
     id: str
     user_id: str
@@ -57,12 +65,19 @@ class FileModelResponse(BaseModel):
 
     filename: str
     data: Optional[dict] = None
-    meta: dict
+    meta: FileMeta
 
     created_at: int  # timestamp in epoch
     updated_at: int  # timestamp in epoch
 
 
+class FileMetadataResponse(BaseModel):
+    id: str
+    meta: dict
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+
 class FileForm(BaseModel):
     id: str
     hash: Optional[str] = None
@@ -104,6 +119,19 @@ class FilesTable:
             except Exception:
                 return None
 
+    def get_file_metadata_by_id(self, id: str) -> Optional[FileMetadataResponse]:
+        with get_db() as db:
+            try:
+                file = db.get(File, id)
+                return FileMetadataResponse(
+                    id=file.id,
+                    meta=file.meta,
+                    created_at=file.created_at,
+                    updated_at=file.updated_at,
+                )
+            except Exception:
+                return None
+
     def get_files(self) -> list[FileModel]:
         with get_db() as db:
             return [FileModel.model_validate(file) for file in db.query(File).all()]
@@ -118,6 +146,21 @@ class FilesTable:
                 .all()
             ]
 
+    def get_file_metadatas_by_ids(self, ids: list[str]) -> list[FileMetadataResponse]:
+        with get_db() as db:
+            return [
+                FileMetadataResponse(
+                    id=file.id,
+                    meta=file.meta,
+                    created_at=file.created_at,
+                    updated_at=file.updated_at,
+                )
+                for file in db.query(File)
+                .filter(File.id.in_(ids))
+                .order_by(File.updated_at.desc())
+                .all()
+            ]
+
     def get_files_by_user_id(self, user_id: str) -> list[FileModel]:
         with get_db() as db:
             return [

backend/open_webui/apps/webui/models/knowledge.py

@@ -6,6 +6,10 @@ import uuid
 
 from open_webui.apps.webui.internal.db import Base, get_db
 from open_webui.env import SRC_LOG_LEVELS
+
+from open_webui.apps.webui.models.files import FileMetadataResponse
+
+
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Column, String, Text, JSON
 
@@ -64,6 +68,8 @@ class KnowledgeResponse(BaseModel):
     created_at: int  # timestamp in epoch
     updated_at: int  # timestamp in epoch
 
+    files: Optional[list[FileMetadataResponse | dict]] = None
+
 
 class KnowledgeForm(BaseModel):
     name: str

backend/open_webui/apps/webui/routers/files.py

@@ -213,7 +213,7 @@ async def update_file_data_content_by_id(
 ############################
 
 
-@router.get("/{id}/content", response_model=Optional[FileModel])
+@router.get("/{id}/content")
 async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
     file = Files.get_file_by_id(id)
 
@@ -239,7 +239,7 @@ async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
         )
 
 
-@router.get("/{id}/content/{file_name}", response_model=Optional[FileModel])
+@router.get("/{id}/content/{file_name}")
 async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
     file = Files.get_file_by_id(id)
 
@@ -251,7 +251,10 @@ async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
             # Check if the file already exists in the cache
             if file_path.is_file():
                 print(f"file_path: {file_path}")
-                return FileResponse(file_path)
+                headers = {
+                    "Content-Disposition": f'attachment; filename="{file.meta.get("name", file.filename)}"'
+                }
+                return FileResponse(file_path, headers=headers)
             else:
                 raise HTTPException(
                     status_code=status.HTTP_404_NOT_FOUND,

backend/open_webui/apps/webui/routers/knowledge.py

@@ -48,7 +48,12 @@ async def get_knowledge_items(
             )
     else:
         return [
-            KnowledgeResponse(**knowledge.model_dump())
+            KnowledgeResponse(
+                **knowledge.model_dump(),
+                files=Files.get_file_metadatas_by_ids(
+                    knowledge.data.get("file_ids", []) if knowledge.data else []
+                ),
+            )
             for knowledge in Knowledges.get_knowledge_items()
         ]