open-webui/backend/open_webui/utils
Classic298 d29685275b
perf: drop the full-payload deepcopy in the OpenAI to Ollama conversion (#27371)
convert_payload_openai_to_ollama deep-copied the entire request payload on every completion routed to an Ollama model, and again on every tool-call iteration. The cost of that copy scales with the number of messages and nested content parts in the history, so long chats pay the most, purely as CPU work before the request even leaves the server.

The function only ever mutates two things: it deletes keys on the top-level dict and on the nested options dict. convert_messages_openai_to_ollama already builds fresh message dicts. Shallow-copying exactly those two levels therefore preserves behavior while removing the whole-tree copy.

Benchmark (per conversion call):

| payload | before | after | speedup |
| --- | --- | --- | --- |
| 200-message text chat (~180 KB) | 0.22 ms | 0.057 ms | 4x |
| 20-message chat + 1 MB base64 image | 0.41 ms | 0.38 ms | 1.1x |

The image row barely moves because deepcopy shares immutable strings; the win comes from container-heavy histories, which are exactly the payloads that grow over a conversation's lifetime.

The output is byte-identical to the previous implementation (verified against it, including dict key order, root parameter hoisting, max_tokens remapping, stop handling and response_format precedence), and the caller's payload is left unmodified exactly as before.
2026-07-27 01:47:23 -04:00
..
access_control chore: format 2026-07-27 00:12:47 -04:00
images refac 2026-07-01 02:48:29 -05:00
mcp refac 2026-06-29 11:56:00 -05:00
telemetry refac(telemetry): drop deprecated semconv SpanAttributes subclass (#25784) 2026-06-29 02:05:34 -05:00
actions.py fix: enforce action availability and model access on the chat action route (#27243) 2026-07-23 12:23:05 -04:00
anthropic.py refac 2026-07-26 18:46:39 -04:00
asgi_middleware.py fix: report sub-second timings in the X-Process-Time header (#27368) 2026-07-23 18:09:23 -05:00
audit.py refac 2026-07-23 22:52:23 -04:00
auth.py fix: apply the verified-user role gate to WebSocket authentication (#27537) 2026-07-26 17:27:54 -04:00
automations.py chore: format 2026-07-27 00:12:47 -04:00
calendar.py feat: add repeat/recurrence dropdown to calendar event modal (#25865) 2026-06-29 02:16:19 -05:00
channels.py refac 2026-03-17 17:58:01 -05:00
chat.py perf: halve Redis round trips on model resolution and socket pools (#27225) 2026-07-23 21:32:01 -04:00
chat_fork.py refac 2026-07-23 02:54:56 -04:00
chat_id.py refac 2026-07-26 21:12:14 -04:00
chat_variables.py refac 2026-07-24 01:44:30 -04:00
code_interpreter.py refac: modernize type annotations (PEP 604 / PEP 585) 2026-05-12 17:10:15 +09:00
context_compaction.py refac 2026-07-27 01:13:09 -04:00
embeddings.py refac: modernize type annotations (PEP 604 / PEP 585) 2026-05-12 17:10:15 +09:00
files.py refac 2026-07-23 21:29:33 -04:00
filter.py refac 2026-07-23 12:48:14 -04:00
groups.py refac: modernize type annotations (PEP 604 / PEP 585) 2026-05-12 17:10:15 +09:00
headers.py chore: format 2026-07-27 00:12:47 -04:00
logger.py chore: format 2026-06-01 13:56:55 -07:00
memory.py refac 2026-07-01 03:35:46 -05:00
middleware.py refac 2026-07-27 01:13:09 -04:00
misc.py refac 2026-07-27 00:55:16 -04:00
model_ids.py refac 2026-07-26 23:09:22 -04:00
models.py fix: deny chained access to unregistered base models for non-admins (#26905) 2026-07-24 01:32:32 -05:00
notifications.py refac 2026-07-16 01:37:21 -04:00
oauth.py fix: route OAuth profile-picture fetch through the SSRF-safe session (#26699) 2026-07-27 00:56:24 -04:00
payload.py perf: drop the full-payload deepcopy in the OpenAI to Ollama conversion (#27371) 2026-07-27 01:47:23 -04:00
pdf_generator.py refac: modernize type annotations (PEP 604 / PEP 585) 2026-05-12 17:10:15 +09:00
plugin.py refac 2026-07-23 19:17:19 -04:00
rate_limit.py refac: modernize type annotations (PEP 604 / PEP 585) 2026-05-12 17:10:15 +09:00
redis.py fix: Set default Redis socket timeout to None (#27104) 2026-07-27 00:30:00 -04:00
response.py refac 2026-07-26 18:54:07 -04:00
sanitize.py refac 2026-03-17 17:58:01 -05:00
security_headers.py perf: stop recomputing static work in per-response ASGI middlewares (#27229) 2026-07-23 12:29:01 -04:00
session_pool.py perf: stream pure passthrough proxy responses by network chunk instead of by line (#27384) 2026-07-27 00:58:24 -04:00
subagents.py chore: format 2026-07-20 22:11:42 -04:00
task.py refac 2026-06-19 00:16:06 +02:00
terminals.py refac 2026-07-10 18:32:21 -05:00
timers.py fix: scope timer cancellation to the timer's owner (#27472) 2026-07-26 18:12:44 -04:00
tools.py refac 2026-07-27 00:34:25 -04:00
validate.py chore: format 2026-06-01 13:56:55 -07:00
valves.py refac 2026-06-29 12:29:10 -05:00
webhook.py refac 2026-07-26 17:58:01 -04:00