36 Commits

Author SHA1 Message Date
Timothy Jaeryang Baek
bb0f898b43 refac 2026-07-31 17:41:14 -04:00
Classic298
72fdf238a8 perf: optional orjson JSON codec behind ENABLE_ORJSON (#27583)
Swap the JSON encoder/decoder used across the backend from stdlib json to
orjson when ENABLE_ORJSON is set — HTTP request bodies, JSONResponse
bodies, upstream provider responses, SSE chunks, and socket.io/Redis
payloads.

The flag defaults to off, in which case the app uses stdlib json and
engineio's codec verbatim, so default behaviour is unchanged.

- json_codec exports JSONCodec (stdlib json or the orjson codec) and
  SOCKETIO_JSON (engineio's codec or the orjson codec); call sites import
  JSONCodec and stay implementation-agnostic
- apply_orjson_http_json() is a no-op when the flag is off, leaving
  starlette's Request.json / JSONResponse.render untouched
- the orjson codec falls back to the stdlib for inputs orjson rejects
  (non-str dict keys, ints beyond 64 bits, NaN literals)
- orjson is imported only when the flag is on
- FastAPI(default_response_class=...) is deliberately not used: an
  explicit default disables the Pydantic direct-to-bytes fast path for
  response_model routes
2026-07-27 03:45:37 -04:00
Timothy Jaeryang Baek
ba556bd8f0 refac 2026-07-27 02:49:08 -04:00
Timothy Jaeryang Baek
df94268e89 refac 2026-07-26 18:54:07 -04:00
Timothy Jaeryang Baek
95391221df refac 2026-06-23 23:35:44 +02:00
Timothy Jaeryang Baek
6d0295588e refac: modernize type annotations (PEP 604 / PEP 585) 2026-05-12 17:10:15 +09:00
Timothy Jaeryang Baek
d6b73ea2f2 refac 2026-04-24 16:31:02 +09:00
Timothy Jaeryang Baek
ade617efa8 refac 2026-03-24 04:49:48 -05:00
Timothy Jaeryang Baek
de3317e26b refac 2026-03-17 17:58:01 -05:00
Timothy Jaeryang Baek
0b867590a8 refac 2026-02-23 18:23:34 -06:00
Timothy Jaeryang Baek
f4e99c80f6 refac: "tool_calls" finish reason support 2026-02-16 00:53:01 -06:00
Timothy Jaeryang Baek
f376d4f378 chore: format 2026-02-11 16:24:11 -06:00
Timothy Jaeryang Baek
8fd5c06e5b refac 2026-02-10 12:23:08 -06:00
Tim Baek
7bb3a827bb refac 2026-02-01 08:10:25 +04:00
Tim Baek
96f106319e refac 2026-02-01 07:59:02 +04:00
EntropyYue
260137fc12 fix: ollama tool call 2025-07-18 06:11:53 +08:00
Timothy Jaeryang Baek
a28bec865b refac 2025-06-10 13:16:44 +04:00
Timothy Jaeryang Baek
b7a91b1963 refac: ollama response 2025-06-10 13:10:31 +04:00
Timothy Jaeryang Baek
5e35aab292 chore: format 2025-06-05 01:12:28 +04:00
henry
04da2b05f6 convert embedding function name to be more consistence 2025-06-04 18:24:27 +02:00
henry
8f6c3f46d6 payload and response modifed for compatibility 2025-06-04 16:11:40 +02:00
Simone
a8859a8145 Fix on ollama to openai conversion - stream can return a single message with content 2025-02-20 21:25:32 +01:00
Timothy Jaeryang Baek
eeb00a5ca2 chore: format 2025-02-20 01:01:29 -08:00
Simone
074ce356de Added OpenAI usagerequested keys 2025-02-19 15:28:39 +01:00
Timothy Jaeryang Baek
eb568695e7 chore: format 2025-02-13 00:13:33 -08:00
Simone
b0ade6c04c Fixed typo 2025-02-13 07:04:02 +01:00
Simone
7dc000a6b9 added support for API tool_calls if stream false 2025-02-12 09:11:26 +01:00
Timothy Jaeryang Baek
0f12c4d14f fix: ollama tool calling
Co-Authored-By: Simone <6941100+seniorsimo@users.noreply.github.com>
2025-02-10 12:18:49 -08:00
Timothy Jaeryang Baek
7766a08b70 refac: ollama tool calls 2025-02-04 21:42:49 -08:00
Timothy Jaeryang Baek
8727b91664 fix: display usage for non-streaming ollama response 2025-01-29 21:07:22 -08:00
Timothy Jaeryang Baek
46bcf98ef2 fix: usage stats 2024-12-30 15:52:07 -08:00
Timothy Jaeryang Baek
e3937ada38 fix: ollama usage 2024-12-26 20:35:14 -08:00
Timothy Jaeryang Baek
f9a05dd1e1 refac 2024-12-12 23:31:08 -08:00
Timothy J. Baek
fc71f441c4 refac 2024-10-21 13:45:28 -07:00
Timothy J. Baek
3a0a1aca11 refac: task ollama stream support 2024-09-21 01:07:57 +02:00
Timothy J. Baek
41926172d3 fix/refac: use ollama /api/chat endpoint for tasks 2024-09-21 00:30:13 +02:00