fix: stream GET /chats/all to prevent OOM on large chat histories (#24461)
Convert the /chats/all endpoint from loading all user chats into memory at once to a streaming NDJSON response that fetches chats in batches of 100. This prevents Out-of-Memory crashes for users with large chat histories. Backend: Added async generator that paginates through chats with short-lived DB sessions per batch (critical for SQLite lock release). Frontend: Updated getAllChats to consume the NDJSON stream via ReadableStream reader, accumulating results for the export file. Ref: open-webui#22206
This commit is contained in:
1 parent
6082e1adae
commit
55d1db1f38
2 files changed
+78
-24
No files matched your search
@@ -676,11 +676,46 @@ async def get_user_pinned_chats(user=Depends(get_verified_user), db: AsyncSessio
|
|||||||
# GetChats
|
# GetChats
|
||||||
############################
|
############################
|
||||||
|
|
||||||
|
CHAT_EXPORT_BATCH_SIZE = 100
|
||||||
|
|
||||||
@router.get('/all', response_model=list[ChatResponse])
|
|
||||||
async def get_user_chats(user=Depends(get_verified_user), db: AsyncSession = Depends(get_async_session)):
|
async def generate_chat_export_ndjson(user_id: str):
|
||||||
result = await Chats.get_chats_by_user_id(user.id, db=db)
|
"""
|
||||||
return [ChatResponse(**chat.model_dump()) for chat in result.items]
|
Async generator that streams all user chats as NDJSON (one JSON object per line).
|
||||||
|
|
||||||
|
Uses short-lived DB sessions per batch to avoid holding locks for the
|
||||||
|
entire duration, which is critical for SQLite environments.
|
||||||
|
"""
|
||||||
|
skip = 0
|
||||||
|
|
||||||
|
while True:
|
||||||
|
result = await Chats.get_chats_by_user_id(
|
||||||
|
user_id,
|
||||||
|
skip=skip,
|
||||||
|
limit=CHAT_EXPORT_BATCH_SIZE,
|
||||||
|
db=None,
|
||||||
|
)
|
||||||
|
if not result.items:
|
||||||
|
break
|
||||||
|
|
||||||
|
for chat in result.items:
|
||||||
|
try:
|
||||||
|
yield ChatResponse(**chat.model_dump()).model_dump_json() + '\n'
|
||||||
|
except Exception as e:
|
||||||
|
log.exception(f'Error serializing chat {chat.id}: {e}')
|
||||||
|
|
||||||
|
if len(result.items) < CHAT_EXPORT_BATCH_SIZE:
|
||||||
|
break
|
||||||
|
|
||||||
|
skip += CHAT_EXPORT_BATCH_SIZE
|
||||||
|
|
||||||
|
|
||||||
|
@router.get('/all')
|
||||||
|
async def get_user_chats(user=Depends(get_verified_user)):
|
||||||
|
return StreamingResponse(
|
||||||
|
generate_chat_export_ndjson(user.id),
|
||||||
|
media_type='application/x-ndjson',
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
############################
|
############################
|
||||||
|
|||||||
+39
-20
@@ -301,34 +301,53 @@ export const getSharedChatList = async (token: string = '', page: number = 1, fi
|
|||||||
};
|
};
|
||||||
|
|
||||||
export const getAllChats = async (token: string) => {
|
export const getAllChats = async (token: string) => {
|
||||||
let error = null;
|
|
||||||
|
|
||||||
const res = await fetch(`${WEBUI_API_BASE_URL}/chats/all`, {
|
const res = await fetch(`${WEBUI_API_BASE_URL}/chats/all`, {
|
||||||
method: 'GET',
|
method: 'GET',
|
||||||
headers: {
|
headers: {
|
||||||
Accept: 'application/json',
|
Accept: 'application/x-ndjson',
|
||||||
'Content-Type': 'application/json',
|
|
||||||
...(token && { authorization: `Bearer ${token}` })
|
...(token && { authorization: `Bearer ${token}` })
|
||||||
}
|
}
|
||||||
})
|
});
|
||||||
.then(async (res) => {
|
|
||||||
if (!res.ok) throw await res.json();
|
|
||||||
return res.json();
|
|
||||||
})
|
|
||||||
.then((json) => {
|
|
||||||
return json;
|
|
||||||
})
|
|
||||||
.catch((err) => {
|
|
||||||
error = err;
|
|
||||||
console.error(err);
|
|
||||||
return null;
|
|
||||||
});
|
|
||||||
|
|
||||||
if (error) {
|
if (!res.ok) {
|
||||||
throw error;
|
const err = await res.json();
|
||||||
|
console.error(err);
|
||||||
|
throw err;
|
||||||
}
|
}
|
||||||
|
|
||||||
return res;
|
const reader = res.body?.getReader();
|
||||||
|
if (!reader) {
|
||||||
|
throw new Error('Response body is not readable');
|
||||||
|
}
|
||||||
|
|
||||||
|
const decoder = new TextDecoder();
|
||||||
|
const chats: object[] = [];
|
||||||
|
let buffer = '';
|
||||||
|
|
||||||
|
while (true) {
|
||||||
|
const { done, value } = await reader.read();
|
||||||
|
if (done) break;
|
||||||
|
|
||||||
|
buffer += decoder.decode(value, { stream: true });
|
||||||
|
const lines = buffer.split('\n');
|
||||||
|
// Keep the last potentially incomplete line in the buffer
|
||||||
|
buffer = lines.pop() ?? '';
|
||||||
|
|
||||||
|
for (const line of lines) {
|
||||||
|
const trimmed = line.trim();
|
||||||
|
if (trimmed) {
|
||||||
|
chats.push(JSON.parse(trimmed));
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Process any remaining data in the buffer
|
||||||
|
const remaining = buffer.trim();
|
||||||
|
if (remaining) {
|
||||||
|
chats.push(JSON.parse(remaining));
|
||||||
|
}
|
||||||
|
|
||||||
|
return chats;
|
||||||
};
|
};
|
||||||
|
|
||||||
export const getChatListBySearchText = async (token: string, text: string, page: number = 1) => {
|
export const getChatListBySearchText = async (token: string, text: string, page: number = 1) => {
|
||||||
|
|||||||
Reference in new issue
Block a user