Emil_Shanaty/open-webui-ai4me
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refac

Browse Source
This commit is contained in:
Timothy Jaeryang Baek
2026-03-17 17:58:01 -05:00
parent fcf7208352
commit de3317e26b
220 changed files with 17200 additions and 22836 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/open_webui/routers/knowledge.py
+137 -174
View File
@@ -50,7 +50,7 @@ PAGE_ITEM_COUNT = 30
# Knowledge Base Embedding
############################
KNOWLEDGE_BASES_COLLECTION = "knowledge-bases"
KNOWLEDGE_BASES_COLLECTION = 'knowledge-bases'
async def embed_knowledge_base_metadata(
@@ -61,24 +61,24 @@ async def embed_knowledge_base_metadata(
) -> bool:
"""Generate and store embedding for knowledge base."""
try:
content = f"{name}\n\n{description}" if description else name
content = f'{name}\n\n{description}' if description else name
embedding = await request.app.state.EMBEDDING_FUNCTION(content)
VECTOR_DB_CLIENT.upsert(
collection_name=KNOWLEDGE_BASES_COLLECTION,
items=[
{
"id": knowledge_base_id,
"text": content,
"vector": embedding,
"metadata": {
"knowledge_base_id": knowledge_base_id,
'id': knowledge_base_id,
'text': content,
'vector': embedding,
'metadata': {
'knowledge_base_id': knowledge_base_id,
},
}
],
)
return True
except Exception as e:
log.error(f"Failed to embed knowledge base {knowledge_base_id}: {e}")
log.error(f'Failed to embed knowledge base {knowledge_base_id}: {e}')
return False
@@ -91,7 +91,7 @@ def remove_knowledge_base_metadata_embedding(knowledge_base_id: str) -> bool:
)
return True
except Exception as e:
log.debug(f"Failed to remove embedding for {knowledge_base_id}: {e}")
log.debug(f'Failed to remove embedding for {knowledge_base_id}: {e}')
return False
@@ -104,7 +104,7 @@ class KnowledgeAccessListResponse(BaseModel):
total: int
@router.get("/", response_model=KnowledgeAccessListResponse)
@router.get('/', response_model=KnowledgeAccessListResponse)
async def get_knowledge_bases(
page: Optional[int] = 1,
user=Depends(get_verified_user),
@@ -118,23 +118,21 @@ async def get_knowledge_bases(
groups = Groups.get_groups_by_member_id(user.id, db=db)
user_group_ids = {group.id for group in groups}
if not user.role == "admin" or not BYPASS_ADMIN_ACCESS_CONTROL:
if not user.role == 'admin' or not BYPASS_ADMIN_ACCESS_CONTROL:
if groups:
filter["group_ids"] = [group.id for group in groups]
filter['group_ids'] = [group.id for group in groups]
filter["user_id"] = user.id
filter['user_id'] = user.id
result = Knowledges.search_knowledge_bases(
user.id, filter=filter, skip=skip, limit=limit, db=db
)
result = Knowledges.search_knowledge_bases(user.id, filter=filter, skip=skip, limit=limit, db=db)
# Batch-fetch writable knowledge IDs in a single query instead of N has_access calls
knowledge_base_ids = [knowledge_base.id for knowledge_base in result.items]
writable_knowledge_base_ids = AccessGrants.get_accessible_resource_ids(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_ids=knowledge_base_ids,
permission="write",
permission='write',
user_group_ids=user_group_ids,
db=db,
)
@@ -145,7 +143,7 @@ async def get_knowledge_bases(
**knowledge_base.model_dump(),
write_access=(
user.id == knowledge_base.user_id
or (user.role == "admin" and BYPASS_ADMIN_ACCESS_CONTROL)
or (user.role == 'admin' and BYPASS_ADMIN_ACCESS_CONTROL)
or knowledge_base.id in writable_knowledge_base_ids
),
)
@@ -155,7 +153,7 @@ async def get_knowledge_bases(
)
@router.get("/search", response_model=KnowledgeAccessListResponse)
@router.get('/search', response_model=KnowledgeAccessListResponse)
async def search_knowledge_bases(
query: Optional[str] = None,
view_option: Optional[str] = None,
@@ -169,30 +167,28 @@ async def search_knowledge_bases(
filter = {}
if query:
filter["query"] = query
filter['query'] = query
if view_option:
filter["view_option"] = view_option
filter['view_option'] = view_option
groups = Groups.get_groups_by_member_id(user.id, db=db)
user_group_ids = {group.id for group in groups}
if not user.role == "admin" or not BYPASS_ADMIN_ACCESS_CONTROL:
if not user.role == 'admin' or not BYPASS_ADMIN_ACCESS_CONTROL:
if groups:
filter["group_ids"] = [group.id for group in groups]
filter['group_ids'] = [group.id for group in groups]
filter["user_id"] = user.id
filter['user_id'] = user.id
result = Knowledges.search_knowledge_bases(
user.id, filter=filter, skip=skip, limit=limit, db=db
)
result = Knowledges.search_knowledge_bases(user.id, filter=filter, skip=skip, limit=limit, db=db)
# Batch-fetch writable knowledge IDs in a single query instead of N has_access calls
knowledge_base_ids = [knowledge_base.id for knowledge_base in result.items]
writable_knowledge_base_ids = AccessGrants.get_accessible_resource_ids(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_ids=knowledge_base_ids,
permission="write",
permission='write',
user_group_ids=user_group_ids,
db=db,
)
@@ -203,7 +199,7 @@ async def search_knowledge_bases(
**knowledge_base.model_dump(),
write_access=(
user.id == knowledge_base.user_id
or (user.role == "admin" and BYPASS_ADMIN_ACCESS_CONTROL)
or (user.role == 'admin' and BYPASS_ADMIN_ACCESS_CONTROL)
or knowledge_base.id in writable_knowledge_base_ids
),
)
@@ -213,7 +209,7 @@ async def search_knowledge_bases(
)
@router.get("/search/files", response_model=KnowledgeFileListResponse)
@router.get('/search/files', response_model=KnowledgeFileListResponse)
async def search_knowledge_files(
query: Optional[str] = None,
page: Optional[int] = 1,
@@ -226,17 +222,15 @@ async def search_knowledge_files(
filter = {}
if query:
filter["query"] = query
filter['query'] = query
groups = Groups.get_groups_by_member_id(user.id, db=db)
if groups:
filter["group_ids"] = [group.id for group in groups]
filter['group_ids'] = [group.id for group in groups]
filter["user_id"] = user.id
filter['user_id'] = user.id
return Knowledges.search_knowledge_files(
filter=filter, skip=skip, limit=limit, db=db
)
return Knowledges.search_knowledge_files(filter=filter, skip=skip, limit=limit, db=db)
############################
@@ -244,7 +238,7 @@ async def search_knowledge_files(
############################
@router.post("/create", response_model=Optional[KnowledgeResponse])
@router.post('/create', response_model=Optional[KnowledgeResponse])
async def create_new_knowledge(
request: Request,
form_data: KnowledgeForm,
@@ -254,8 +248,8 @@ async def create_new_knowledge(
# Database operations (has_permission, filter_allowed_access_grants, insert_new_knowledge) manage their own sessions.
# This prevents holding a connection during embed_knowledge_base_metadata()
# which makes external embedding API calls (1-5+ seconds).
if user.role != "admin" and not has_permission(
user.id, "workspace.knowledge", request.app.state.config.USER_PERMISSIONS
if user.role != 'admin' and not has_permission(
user.id, 'workspace.knowledge', request.app.state.config.USER_PERMISSIONS
):
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
@@ -267,7 +261,7 @@ async def create_new_knowledge(
user.id,
user.role,
form_data.access_grants,
"sharing.public_knowledge",
'sharing.public_knowledge',
)
knowledge = Knowledges.insert_new_knowledge(user.id, form_data)
@@ -293,13 +287,13 @@ async def create_new_knowledge(
############################
@router.post("/reindex", response_model=bool)
@router.post('/reindex', response_model=bool)
async def reindex_knowledge_files(
request: Request,
user=Depends(get_verified_user),
db: Session = Depends(get_session),
):
if user.role != "admin":
if user.role != 'admin':
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.UNAUTHORIZED,
@@ -307,18 +301,16 @@ async def reindex_knowledge_files(
knowledge_bases = Knowledges.get_knowledge_bases(db=db)
log.info(f"Starting reindexing for {len(knowledge_bases)} knowledge bases")
log.info(f'Starting reindexing for {len(knowledge_bases)} knowledge bases')
for knowledge_base in knowledge_bases:
try:
files = Knowledges.get_files_by_id(knowledge_base.id, db=db)
try:
if VECTOR_DB_CLIENT.has_collection(collection_name=knowledge_base.id):
VECTOR_DB_CLIENT.delete_collection(
collection_name=knowledge_base.id
)
VECTOR_DB_CLIENT.delete_collection(collection_name=knowledge_base.id)
except Exception as e:
log.error(f"Error deleting collection {knowledge_base.id}: {str(e)}")
log.error(f'Error deleting collection {knowledge_base.id}: {str(e)}')
continue # Skip, don't raise
failed_files = []
@@ -327,32 +319,26 @@ async def reindex_knowledge_files(
await run_in_threadpool(
process_file,
request,
ProcessFileForm(
file_id=file.id, collection_name=knowledge_base.id
),
ProcessFileForm(file_id=file.id, collection_name=knowledge_base.id),
user=user,
db=db,
)
except Exception as e:
log.error(
f"Error processing file {file.filename} (ID: {file.id}): {str(e)}"
)
failed_files.append({"file_id": file.id, "error": str(e)})
log.error(f'Error processing file {file.filename} (ID: {file.id}): {str(e)}')
failed_files.append({'file_id': file.id, 'error': str(e)})
continue
except Exception as e:
log.error(f"Error processing knowledge base {knowledge_base.id}: {str(e)}")
log.error(f'Error processing knowledge base {knowledge_base.id}: {str(e)}')
# Don't raise, just continue
continue
if failed_files:
log.warning(
f"Failed to process {len(failed_files)} files in knowledge base {knowledge_base.id}"
)
log.warning(f'Failed to process {len(failed_files)} files in knowledge base {knowledge_base.id}')
for failed in failed_files:
log.warning(f"File ID: {failed['file_id']}, Error: {failed['error']}")
log.warning(f'File ID: {failed["file_id"]}, Error: {failed["error"]}')
log.info(f"Reindexing completed.")
log.info(f'Reindexing completed.')
return True
@@ -361,7 +347,7 @@ async def reindex_knowledge_files(
############################
@router.post("/metadata/reindex", response_model=dict)
@router.post('/metadata/reindex', response_model=dict)
async def reindex_knowledge_base_metadata_embeddings(
request: Request,
user=Depends(get_admin_user),
@@ -374,15 +360,15 @@ async def reindex_knowledge_base_metadata_embeddings(
this entire operation would exhaust the connection pool.
"""
knowledge_bases = Knowledges.get_knowledge_bases()
log.info(f"Reindexing embeddings for {len(knowledge_bases)} knowledge bases")
log.info(f'Reindexing embeddings for {len(knowledge_bases)} knowledge bases')
success_count = 0
for kb in knowledge_bases:
if await embed_knowledge_base_metadata(request, kb.id, kb.name, kb.description):
success_count += 1
log.info(f"Embedding reindex complete: {success_count}/{len(knowledge_bases)}")
return {"total": len(knowledge_bases), "success": success_count}
log.info(f'Embedding reindex complete: {success_count}/{len(knowledge_bases)}')
return {'total': len(knowledge_bases), 'success': success_count}
############################
@@ -395,35 +381,32 @@ class KnowledgeFilesResponse(KnowledgeResponse):
write_access: Optional[bool] = False
@router.get("/{id}", response_model=Optional[KnowledgeFilesResponse])
async def get_knowledge_by_id(
id: str, user=Depends(get_verified_user), db: Session = Depends(get_session)
):
@router.get('/{id}', response_model=Optional[KnowledgeFilesResponse])
async def get_knowledge_by_id(id: str, user=Depends(get_verified_user), db: Session = Depends(get_session)):
knowledge = Knowledges.get_knowledge_by_id(id=id, db=db)
if knowledge:
if (
user.role == "admin"
user.role == 'admin'
or knowledge.user_id == user.id
or AccessGrants.has_access(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_id=knowledge.id,
permission="read",
permission='read',
db=db,
)
):
return KnowledgeFilesResponse(
**knowledge.model_dump(),
write_access=(
user.id == knowledge.user_id
or (user.role == "admin" and BYPASS_ADMIN_ACCESS_CONTROL)
or (user.role == 'admin' and BYPASS_ADMIN_ACCESS_CONTROL)
or AccessGrants.has_access(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_id=knowledge.id,
permission="write",
permission='write',
db=db,
)
),
@@ -445,7 +428,7 @@ async def get_knowledge_by_id(
############################
@router.post("/{id}/update", response_model=Optional[KnowledgeFilesResponse])
@router.post('/{id}/update', response_model=Optional[KnowledgeFilesResponse])
async def update_knowledge_by_id(
request: Request,
id: str,
@@ -467,11 +450,11 @@ async def update_knowledge_by_id(
knowledge.user_id != user.id
and not AccessGrants.has_access(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_id=knowledge.id,
permission="write",
permission='write',
)
and user.role != "admin"
and user.role != 'admin'
):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
@@ -483,7 +466,7 @@ async def update_knowledge_by_id(
user.id,
user.role,
form_data.access_grants,
"sharing.public_knowledge",
'sharing.public_knowledge',
)
knowledge = Knowledges.update_knowledge_by_id(id=id, form_data=form_data)
@@ -515,7 +498,7 @@ class KnowledgeAccessGrantsForm(BaseModel):
access_grants: list[dict]
@router.post("/{id}/access/update", response_model=Optional[KnowledgeFilesResponse])
@router.post('/{id}/access/update', response_model=Optional[KnowledgeFilesResponse])
async def update_knowledge_access_by_id(
request: Request,
id: str,
@@ -534,12 +517,12 @@ async def update_knowledge_access_by_id(
knowledge.user_id != user.id
and not AccessGrants.has_access(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_id=knowledge.id,
permission="write",
permission='write',
db=db,
)
and user.role != "admin"
and user.role != 'admin'
):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
@@ -551,10 +534,10 @@ async def update_knowledge_access_by_id(
user.id,
user.role,
form_data.access_grants,
"sharing.public_knowledge",
'sharing.public_knowledge',
)
AccessGrants.set_access_grants("knowledge", id, form_data.access_grants, db=db)
AccessGrants.set_access_grants('knowledge', id, form_data.access_grants, db=db)
return KnowledgeFilesResponse(
**Knowledges.get_knowledge_by_id(id=id, db=db).model_dump(),
@@ -567,7 +550,7 @@ async def update_knowledge_access_by_id(
############################
@router.get("/{id}/files", response_model=KnowledgeFileListResponse)
@router.get('/{id}/files', response_model=KnowledgeFileListResponse)
async def get_knowledge_files_by_id(
id: str,
query: Optional[str] = None,
@@ -578,7 +561,6 @@ async def get_knowledge_files_by_id(
user=Depends(get_verified_user),
db: Session = Depends(get_session),
):
knowledge = Knowledges.get_knowledge_by_id(id=id, db=db)
if not knowledge:
raise HTTPException(
@@ -587,13 +569,13 @@ async def get_knowledge_files_by_id(
)
if not (
user.role == "admin"
user.role == 'admin'
or knowledge.user_id == user.id
or AccessGrants.has_access(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_id=knowledge.id,
permission="read",
permission='read',
db=db,
)
):
@@ -609,17 +591,15 @@ async def get_knowledge_files_by_id(
filter = {}
if query:
filter["query"] = query
filter['query'] = query
if view_option:
filter["view_option"] = view_option
filter['view_option'] = view_option
if order_by:
filter["order_by"] = order_by
filter['order_by'] = order_by
if direction:
filter["direction"] = direction
filter['direction'] = direction
return Knowledges.search_files_by_id(
id, user.id, filter=filter, skip=skip, limit=limit, db=db
)
return Knowledges.search_files_by_id(id, user.id, filter=filter, skip=skip, limit=limit, db=db)
############################
@@ -631,7 +611,7 @@ class KnowledgeFileIdForm(BaseModel):
file_id: str
@router.post("/{id}/file/add", response_model=Optional[KnowledgeFilesResponse])
@router.post('/{id}/file/add', response_model=Optional[KnowledgeFilesResponse])
def add_file_to_knowledge_by_id(
request: Request,
id: str,
@@ -650,12 +630,12 @@ def add_file_to_knowledge_by_id(
knowledge.user_id != user.id
and not AccessGrants.has_access(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_id=knowledge.id,
permission="write",
permission='write',
db=db,
)
and user.role != "admin"
and user.role != 'admin'
):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
@@ -684,9 +664,7 @@ def add_file_to_knowledge_by_id(
)
# Add file to knowledge base
Knowledges.add_file_to_knowledge_by_id(
knowledge_id=id, file_id=form_data.file_id, user_id=user.id, db=db
)
Knowledges.add_file_to_knowledge_by_id(knowledge_id=id, file_id=form_data.file_id, user_id=user.id, db=db)
except Exception as e:
log.debug(e)
raise HTTPException(
@@ -706,7 +684,7 @@ def add_file_to_knowledge_by_id(
)
@router.post("/{id}/file/update", response_model=Optional[KnowledgeFilesResponse])
@router.post('/{id}/file/update', response_model=Optional[KnowledgeFilesResponse])
def update_file_from_knowledge_by_id(
request: Request,
id: str,
@@ -725,14 +703,13 @@ def update_file_from_knowledge_by_id(
knowledge.user_id != user.id
and not AccessGrants.has_access(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_id=knowledge.id,
permission="write",
permission='write',
db=db,
)
and user.role != "admin"
and user.role != 'admin'
):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
@@ -753,9 +730,7 @@ def update_file_from_knowledge_by_id(
)
# Remove content from the vector database
VECTOR_DB_CLIENT.delete(
collection_name=knowledge.id, filter={"file_id": form_data.file_id}
)
VECTOR_DB_CLIENT.delete(collection_name=knowledge.id, filter={'file_id': form_data.file_id})
# Add content to the vector database
try:
@@ -788,7 +763,7 @@ def update_file_from_knowledge_by_id(
############################
@router.post("/{id}/file/remove", response_model=Optional[KnowledgeFilesResponse])
@router.post('/{id}/file/remove', response_model=Optional[KnowledgeFilesResponse])
def remove_file_from_knowledge_by_id(
id: str,
form_data: KnowledgeFileIdForm,
@@ -807,12 +782,12 @@ def remove_file_from_knowledge_by_id(
knowledge.user_id != user.id
and not AccessGrants.has_access(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_id=knowledge.id,
permission="write",
permission='write',
db=db,
)
and user.role != "admin"
and user.role != 'admin'
):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
@@ -833,32 +808,30 @@ def remove_file_from_knowledge_by_id(
detail=ERROR_MESSAGES.NOT_FOUND,
)
Knowledges.remove_file_from_knowledge_by_id(
knowledge_id=id, file_id=form_data.file_id, db=db
)
Knowledges.remove_file_from_knowledge_by_id(knowledge_id=id, file_id=form_data.file_id, db=db)
# Remove content from the vector database
try:
VECTOR_DB_CLIENT.delete(
collection_name=knowledge.id, filter={"file_id": form_data.file_id}
collection_name=knowledge.id, filter={'file_id': form_data.file_id}
) # Remove by file_id first
VECTOR_DB_CLIENT.delete(
collection_name=knowledge.id, filter={"hash": file.hash}
collection_name=knowledge.id, filter={'hash': file.hash}
) # Remove by hash as well in case of duplicates
except Exception as e:
log.debug("This was most likely caused by bypassing embedding processing")
log.debug('This was most likely caused by bypassing embedding processing')
log.debug(e)
pass
if delete_file:
try:
# Remove the file's collection from vector database
file_collection = f"file-{form_data.file_id}"
file_collection = f'file-{form_data.file_id}'
if VECTOR_DB_CLIENT.has_collection(collection_name=file_collection):
VECTOR_DB_CLIENT.delete_collection(collection_name=file_collection)
except Exception as e:
log.debug("This was most likely caused by bypassing embedding processing")
log.debug('This was most likely caused by bypassing embedding processing')
log.debug(e)
pass
@@ -882,10 +855,8 @@ def remove_file_from_knowledge_by_id(
############################
@router.delete("/{id}/delete", response_model=bool)
async def delete_knowledge_by_id(
id: str, user=Depends(get_verified_user), db: Session = Depends(get_session)
):
@router.delete('/{id}/delete', response_model=bool)
async def delete_knowledge_by_id(id: str, user=Depends(get_verified_user), db: Session = Depends(get_session)):
knowledge = Knowledges.get_knowledge_by_id(id=id, db=db)
if not knowledge:
raise HTTPException(
@@ -897,34 +868,34 @@ async def delete_knowledge_by_id(
knowledge.user_id != user.id
and not AccessGrants.has_access(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_id=knowledge.id,
permission="write",
permission='write',
db=db,
)
and user.role != "admin"
and user.role != 'admin'
):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
)
log.info(f"Deleting knowledge base: {id} (name: {knowledge.name})")
log.info(f'Deleting knowledge base: {id} (name: {knowledge.name})')
# Get all models
models = Models.get_all_models(db=db)
log.info(f"Found {len(models)} models to check for knowledge base {id}")
log.info(f'Found {len(models)} models to check for knowledge base {id}')
# Update models that reference this knowledge base
for model in models:
if model.meta and hasattr(model.meta, "knowledge"):
if model.meta and hasattr(model.meta, 'knowledge'):
knowledge_list = model.meta.knowledge or []
# Filter out the deleted knowledge base
updated_knowledge = [k for k in knowledge_list if k.get("id") != id]
updated_knowledge = [k for k in knowledge_list if k.get('id') != id]
# If the knowledge list changed, update the model
if len(updated_knowledge) != len(knowledge_list):
log.info(f"Updating model {model.id} to remove knowledge base {id}")
log.info(f'Updating model {model.id} to remove knowledge base {id}')
model.meta.knowledge = updated_knowledge
# Create a ModelForm for the update
model_form = ModelForm(
@@ -957,10 +928,8 @@ async def delete_knowledge_by_id(
############################
@router.post("/{id}/reset", response_model=Optional[KnowledgeResponse])
async def reset_knowledge_by_id(
id: str, user=Depends(get_verified_user), db: Session = Depends(get_session)
):
@router.post('/{id}/reset', response_model=Optional[KnowledgeResponse])
async def reset_knowledge_by_id(id: str, user=Depends(get_verified_user), db: Session = Depends(get_session)):
knowledge = Knowledges.get_knowledge_by_id(id=id, db=db)
if not knowledge:
raise HTTPException(
@@ -972,12 +941,12 @@ async def reset_knowledge_by_id(
knowledge.user_id != user.id
and not AccessGrants.has_access(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_id=knowledge.id,
permission="write",
permission='write',
db=db,
)
and user.role != "admin"
and user.role != 'admin'
):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
@@ -999,7 +968,7 @@ async def reset_knowledge_by_id(
############################
@router.post("/{id}/files/batch/add", response_model=Optional[KnowledgeFilesResponse])
@router.post('/{id}/files/batch/add', response_model=Optional[KnowledgeFilesResponse])
async def add_files_to_knowledge_batch(
request: Request,
id: str,
@@ -1021,12 +990,12 @@ async def add_files_to_knowledge_batch(
knowledge.user_id != user.id
and not AccessGrants.has_access(
user_id=user.id,
resource_type="knowledge",
resource_type='knowledge',
resource_id=knowledge.id,
permission="write",
permission='write',
db=db,
)
and user.role != "admin"
and user.role != 'admin'
):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
@@ -1034,7 +1003,7 @@ async def add_files_to_knowledge_batch(
)
# Batch-fetch all files to avoid N+1 queries
log.info(f"files/batch/add - {len(form_data)} files")
log.info(f'files/batch/add - {len(form_data)} files')
file_ids = [form.file_id for form in form_data]
files = Files.get_files_by_ids(file_ids, db=db)
@@ -1044,7 +1013,7 @@ async def add_files_to_knowledge_batch(
if missing_ids:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=f"File {missing_ids[0]} not found",
detail=f'File {missing_ids[0]} not found',
)
# Process files
@@ -1056,27 +1025,23 @@ async def add_files_to_knowledge_batch(
db=db,
)
except Exception as e:
log.error(
f"add_files_to_knowledge_batch: Exception occurred: {e}", exc_info=True
)
log.error(f'add_files_to_knowledge_batch: Exception occurred: {e}', exc_info=True)
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
# Only add files that were successfully processed
successful_file_ids = [r.file_id for r in result.results if r.status == "completed"]
successful_file_ids = [r.file_id for r in result.results if r.status == 'completed']
for file_id in successful_file_ids:
Knowledges.add_file_to_knowledge_by_id(
knowledge_id=id, file_id=file_id, user_id=user.id, db=db
)
Knowledges.add_file_to_knowledge_by_id(knowledge_id=id, file_id=file_id, user_id=user.id, db=db)
# If there were any errors, include them in the response
if result.errors:
error_details = [f"{err.file_id}: {err.error}" for err in result.errors]
error_details = [f'{err.file_id}: {err.error}' for err in result.errors]
return KnowledgeFilesResponse(
**knowledge.model_dump(),
files=Knowledges.get_file_metadatas_by_id(knowledge.id, db=db),
warnings={
"message": "Some files failed to process",
"errors": error_details,
'message': 'Some files failed to process',
'errors': error_details,
},
)
@@ -1091,10 +1056,8 @@ async def add_files_to_knowledge_batch(
############################
@router.get("/{id}/export")
async def export_knowledge_by_id(
id: str, user=Depends(get_admin_user), db: Session = Depends(get_session)
):
@router.get('/{id}/export')
async def export_knowledge_by_id(id: str, user=Depends(get_admin_user), db: Session = Depends(get_session)):
"""
Export a knowledge base as a zip file containing .txt files.
Admin only.
@@ -1111,24 +1074,24 @@ async def export_knowledge_by_id(
# Create zip file in memory
zip_buffer = io.BytesIO()
with zipfile.ZipFile(zip_buffer, "w", zipfile.ZIP_DEFLATED) as zf:
with zipfile.ZipFile(zip_buffer, 'w', zipfile.ZIP_DEFLATED) as zf:
for file in files:
content = file.data.get("content", "") if file.data else ""
content = file.data.get('content', '') if file.data else ''
if content:
# Use original filename with .txt extension
filename = file.filename
if not filename.endswith(".txt"):
filename = f"{filename}.txt"
if not filename.endswith('.txt'):
filename = f'{filename}.txt'
zf.writestr(filename, content)
zip_buffer.seek(0)
# Sanitize knowledge name for filename
safe_name = "".join(c if c.isalnum() or c in " -_" else "_" for c in knowledge.name)
zip_filename = f"{safe_name}.zip"
safe_name = ''.join(c if c.isalnum() or c in ' -_' else '_' for c in knowledge.name)
zip_filename = f'{safe_name}.zip'
return StreamingResponse(
zip_buffer,
media_type="application/zip",
headers={"Content-Disposition": f"attachment; filename={zip_filename}"},
media_type='application/zip',
headers={'Content-Disposition': f'attachment; filename={zip_filename}'},
)