github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-08-25 17:21:00 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

perf: drop the full-payload deepcopy in the OpenAI to Ollama conversion (#27371)

Browse Source 
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.
This commit is contained in:
Classic298
2026-07-27 01:47:23 -04:00
committed by GitHub
parent 915ef7d079
commit d29685275b
1 changed files with 6 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/open_webui/utils/payload.py
+6 -5
View File
@@ -1,4 +1,3 @@
import copy
import json
from typing import Callable, Optional
@@ -307,9 +306,10 @@ def convert_payload_openai_to_ollama(openai_payload: dict) -> dict:
Returns:
dict: A modified payload compatible with the Ollama API.
"""
# Shallow copy metadata separately (may contain non-picklable objects)
# Only the top-level dict and the nested options dict are mutated below, so
# shallow copies suffice; deepcopy walked the entire message tree per call.
metadata = openai_payload.get('metadata')
openai_payload = copy.deepcopy({k: v for k, v in openai_payload.items() if k != 'metadata'})
openai_payload = {k: v for k, v in openai_payload.items() if k != 'metadata'}
if metadata is not None:
openai_payload['metadata'] = dict(metadata)
ollama_payload = {}
@@ -327,8 +327,9 @@ def convert_payload_openai_to_ollama(openai_payload: dict) -> dict:
# If there are advanced parameters in the payload, format them in Ollama's options field
if openai_payload.get('options'):
ollama_payload['options'] = openai_payload['options']
ollama_options = openai_payload['options']
# Copied before key deletions below so the caller's options stay intact
ollama_options = dict(openai_payload['options'])
ollama_payload['options'] = ollama_options
def parse_json(value: str) -> dict:
"""