github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-08-24 14:23:59 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

perf: deduplicate repeated config fetches in Ollama request handlers (#27226)

Browse Source 
The per-request Ollama handlers (chat, generate, embed, embeddings,
and the OpenAI-compat completions/chat-completions/messages/responses
endpoints) fetched 'ollama.api_configs' up to three times and
'ollama.base_urls' separately within a single request — the .get()
default-argument pattern made the second api_configs fetch
unconditional, and get_api_key() triggered a third. Up to four
sequential SELECTs per request collapse to one.

A new get_ollama_connection_config() helper fetches base_urls and
api_configs together in one batched Config.get_many where both are
needed; handlers that only need api_configs fetch it once into a
local. Admin operations (pull/push/copy/delete) and the TTL-cached
model-list path are deliberately left untouched.

Resolution semantics (str(idx) key first, url-key legacy fallback,
same defaults) are unchanged.


Claude-Session: https://claude.ai/code/session_01MHg5zs1VBjvRWQ54qHpfYD

Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Classic298
2026-07-23 12:48:55 -04:00
committed by GitHub
co-authored by Claude
parent 85664f650c
commit da7097565c
1 changed files with 33 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/open_webui/routers/ollama.py
+33 -34
View File
@@ -365,6 +365,12 @@ def resolve_api_config(api_configs: dict, idx: int, url: str) -> dict:
return api_configs.get(str(idx), api_configs.get(url, {}))
async def get_ollama_connection_config() -> tuple[list, dict]:
"""Base URLs and per-connection API configs in one batched SELECT."""
config = await Config.get_many('ollama.base_urls', 'ollama.api_configs')
return config.get('ollama.base_urls', []), config.get('ollama.api_configs', {})
@cached(
ttl=MODELS_CACHE_TTL,
# key_builder (not key) is the per-call hook in aiocache 0.12; `key=` is a
@@ -881,12 +887,10 @@ async def embed(
raise HTTPException(status_code=400, detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model))
url_idx = random.choice(models[model]['urls'])
url = (await Config.get('ollama.base_urls', []))[url_idx]
api_config = (await Config.get('ollama.api_configs', {})).get(
str(url_idx),
(await Config.get('ollama.api_configs', {})).get(url, {}),
)
key = get_api_key(url_idx, url, (await Config.get('ollama.api_configs', {})))
base_urls, api_configs = await get_ollama_connection_config()
url = base_urls[url_idx]
api_config = api_configs.get(str(url_idx), api_configs.get(url, {}))
key = get_api_key(url_idx, url, api_configs)
prefix_id = api_config.get('prefix_id')
if prefix_id:
@@ -935,12 +939,10 @@ async def embeddings(
raise HTTPException(status_code=400, detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model))
url_idx = random.choice(models[model]['urls'])
url = (await Config.get('ollama.base_urls', []))[url_idx]
api_config = (await Config.get('ollama.api_configs', {})).get(
str(url_idx),
(await Config.get('ollama.api_configs', {})).get(url, {}),
)
key = get_api_key(url_idx, url, (await Config.get('ollama.api_configs', {})))
base_urls, api_configs = await get_ollama_connection_config()
url = base_urls[url_idx]
api_config = api_configs.get(str(url_idx), api_configs.get(url, {}))
key = get_api_key(url_idx, url, api_configs)
prefix_id = api_config.get('prefix_id')
if prefix_id:
@@ -994,11 +996,9 @@ async def generate_completion(
raise HTTPException(status_code=400, detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model))
url_idx = random.choice(models[model]['urls'])
url = (await Config.get('ollama.base_urls', []))[url_idx]
api_config = (await Config.get('ollama.api_configs', {})).get(
str(url_idx),
(await Config.get('ollama.api_configs', {})).get(url, {}),
)
base_urls, api_configs = await get_ollama_connection_config()
url = base_urls[url_idx]
api_config = api_configs.get(str(url_idx), api_configs.get(url, {}))
prefix_id = api_config.get('prefix_id')
if prefix_id:
@@ -1007,7 +1007,7 @@ async def generate_completion(
return await send_request(
f'{url}/api/generate',
payload=form_data.model_dump_json(exclude_none=True).encode(),
key=get_api_key(url_idx, url, (await Config.get('ollama.api_configs', {}))),
key=get_api_key(url_idx, url, api_configs),
user=user,
stream=True,
)
@@ -1129,7 +1129,8 @@ async def generate_chat_completion(
await check_model_access(user, None, bypass_filter)
url, url_idx = await get_ollama_url(request, payload['model'], url_idx, user)
api_config = resolve_api_config((await Config.get('ollama.api_configs', {})), url_idx, url)
api_configs = await Config.get('ollama.api_configs', {})
api_config = resolve_api_config(api_configs, url_idx, url)
prefix_id = api_config.get('prefix_id')
if prefix_id:
@@ -1138,7 +1139,7 @@ async def generate_chat_completion(
return await send_request(
f'{url}/api/chat',
payload=json.dumps(payload),
key=get_api_key(url_idx, url, (await Config.get('ollama.api_configs', {}))),
key=get_api_key(url_idx, url, api_configs),
user=user,
stream=form_data.stream,
content_type='application/x-ndjson',
@@ -1225,7 +1226,8 @@ async def generate_openai_completion(
await check_model_access(user, None)
url, url_idx = await get_ollama_url(request, payload['model'], url_idx, user)
api_config = resolve_api_config((await Config.get('ollama.api_configs', {})), url_idx, url)
api_configs = await Config.get('ollama.api_configs', {})
api_config = resolve_api_config(api_configs, url_idx, url)
prefix_id = api_config.get('prefix_id')
if prefix_id:
@@ -1234,7 +1236,7 @@ async def generate_openai_completion(
return await send_request(
f'{url}/v1/completions',
payload=json.dumps(payload),
key=get_api_key(url_idx, url, (await Config.get('ollama.api_configs', {}))),
key=get_api_key(url_idx, url, api_configs),
user=user,
stream=payload.get('stream', False),
metadata=metadata,
@@ -1334,7 +1336,8 @@ async def generate_openai_chat_completion(
await check_model_access(user, None)
url, url_idx = await get_ollama_url(request, payload['model'], url_idx, user)
api_config = resolve_api_config((await Config.get('ollama.api_configs', {})), url_idx, url)
api_configs = await Config.get('ollama.api_configs', {})
api_config = resolve_api_config(api_configs, url_idx, url)
prefix_id = api_config.get('prefix_id')
if prefix_id:
@@ -1343,7 +1346,7 @@ async def generate_openai_chat_completion(
return await send_request(
f'{url}/v1/chat/completions',
payload=json.dumps(payload),
key=get_api_key(url_idx, url, (await Config.get('ollama.api_configs', {}))),
key=get_api_key(url_idx, url, api_configs),
user=user,
stream=payload.get('stream', False),
metadata=metadata,
@@ -1385,10 +1388,8 @@ async def generate_anthropic_messages(
await check_model_access(user, None)
url, url_idx = await get_ollama_url(request, payload['model'], url_idx, user)
api_config = (await Config.get('ollama.api_configs', {})).get(
str(url_idx),
(await Config.get('ollama.api_configs', {})).get(url, {}), # Legacy support
)
api_configs = await Config.get('ollama.api_configs', {})
api_config = api_configs.get(str(url_idx), api_configs.get(url, {})) # Legacy support
prefix_id = api_config.get('prefix_id', None)
if prefix_id:
@@ -1397,7 +1398,7 @@ async def generate_anthropic_messages(
return await send_request(
f'{url}/v1/messages',
payload=json.dumps(payload),
key=get_api_key(url_idx, url, (await Config.get('ollama.api_configs', {}))),
key=get_api_key(url_idx, url, api_configs),
user=user,
stream=payload.get('stream', False),
content_type='text/event-stream' if payload.get('stream', False) else None,
@@ -1445,10 +1446,8 @@ async def generate_responses(
await check_model_access(user, None)
url, url_idx = await get_ollama_url(request, payload['model'], url_idx, user)
api_config = (await Config.get('ollama.api_configs', {})).get(
str(url_idx),
(await Config.get('ollama.api_configs', {})).get(url, {}), # Legacy support
)
api_configs = await Config.get('ollama.api_configs', {})
api_config = api_configs.get(str(url_idx), api_configs.get(url, {})) # Legacy support
prefix_id = api_config.get('prefix_id', None)
if prefix_id:
@@ -1457,7 +1456,7 @@ async def generate_responses(
return await send_request(
f'{url}/v1/responses',
payload=json.dumps(payload),
key=get_api_key(url_idx, url, (await Config.get('ollama.api_configs', {}))),
key=get_api_key(url_idx, url, api_configs),
user=user,
stream=payload.get('stream', False),
content_type='text/event-stream' if payload.get('stream', False) else None,