Skip to content

feat: model as first parameter in body for proxy routing efficiency #2400

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+46 −46
Open

feat: model as first parameter in body for proxy routing efficiency #2400

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/openai/resources/audio/speech.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,8 +100,8 @@ def create(
"/audio/speech",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"input": input,
"model": model,
"voice": voice,
"instructions": instructions,
"response_format": response_format,
Expand Down Expand Up @@ -191,8 +191,8 @@ async def create(
"/audio/speech",
body=await async_maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"input": input,
"model": model,
"voice": voice,
"instructions": instructions,
"response_format": response_format,
Expand Down
4 changes: 2 additions & 2 deletions src/openai/resources/audio/transcriptions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -313,8 +313,8 @@ def create(
) -> str | Transcription | TranscriptionVerbose | Stream[TranscriptionStreamEvent]:
body = deepcopy_minimal(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"file": file,
"model": model,
"chunking_strategy": chunking_strategy,
"include": include,
"language": language,
Expand Down Expand Up @@ -692,8 +692,8 @@ async def create(
) -> Transcription | TranscriptionVerbose | str | AsyncStream[TranscriptionStreamEvent]:
body = deepcopy_minimal(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"file": file,
"model": model,
"chunking_strategy": chunking_strategy,
"include": include,
"language": language,
Expand Down
4 changes: 2 additions & 2 deletions src/openai/resources/audio/translations.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,8 +146,8 @@ def create(
"""
body = deepcopy_minimal(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"file": file,
"model": model,
"prompt": prompt,
"response_format": response_format,
"temperature": temperature,
Expand Down Expand Up @@ -289,8 +289,8 @@ async def create(
"""
body = deepcopy_minimal(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"file": file,
"model": model,
"prompt": prompt,
"response_format": response_format,
"temperature": temperature,
Expand Down
8 changes: 4 additions & 4 deletions src/openai/resources/beta/assistants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,7 @@ def create(
"/assistants",
body=maybe_transform(
{
"model": model,
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"description": description,
"instructions": instructions,
"metadata": metadata,
Expand Down Expand Up @@ -360,10 +360,10 @@ def update(
f"/assistants/{assistant_id}",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"description": description,
"instructions": instructions,
"metadata": metadata,
"model": model,
"name": name,
"reasoning_effort": reasoning_effort,
"response_format": response_format,
Expand Down Expand Up @@ -605,7 +605,7 @@ async def create(
"/assistants",
body=await async_maybe_transform(
{
"model": model,
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"description": description,
"instructions": instructions,
"metadata": metadata,
Expand Down Expand Up @@ -809,10 +809,10 @@ async def update(
f"/assistants/{assistant_id}",
body=await async_maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"description": description,
"instructions": instructions,
"metadata": metadata,
"model": model,
"name": name,
"reasoning_effort": reasoning_effort,
"response_format": response_format,
Expand Down
4 changes: 2 additions & 2 deletions src/openai/resources/beta/chat/completions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -159,8 +159,8 @@ def parser(raw_completion: ChatCompletion) -> ParsedChatCompletion[ResponseForma
"/chat/completions",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"messages": messages,
"model": model,
"audio": audio,
"frequency_penalty": frequency_penalty,
"function_call": function_call,
Expand Down Expand Up @@ -438,8 +438,8 @@ def parser(raw_completion: ChatCompletion) -> ParsedChatCompletion[ResponseForma
"/chat/completions",
body=await async_maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing. # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"messages": messages,
"model": model,
"audio": audio,
"frequency_penalty": frequency_penalty,
"function_call": function_call,
Expand Down
4 changes: 2 additions & 2 deletions src/openai/resources/beta/realtime/sessions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,14 +179,14 @@ def create(
"/realtime/sessions",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"client_secret": client_secret,
"input_audio_format": input_audio_format,
"input_audio_noise_reduction": input_audio_noise_reduction,
"input_audio_transcription": input_audio_transcription,
"instructions": instructions,
"max_response_output_tokens": max_response_output_tokens,
"modalities": modalities,
"model": model,
"output_audio_format": output_audio_format,
"speed": speed,
"temperature": temperature,
Expand Down Expand Up @@ -364,14 +364,14 @@ async def create(
"/realtime/sessions",
body=await async_maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"client_secret": client_secret,
"input_audio_format": input_audio_format,
"input_audio_noise_reduction": input_audio_noise_reduction,
"input_audio_transcription": input_audio_transcription,
"instructions": instructions,
"max_response_output_tokens": max_response_output_tokens,
"modalities": modalities,
"model": model,
"output_audio_format": output_audio_format,
"speed": speed,
"temperature": temperature,
Expand Down
12 changes: 6 additions & 6 deletions src/openai/resources/beta/threads/runs/runs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -573,14 +573,14 @@ def create(
f"/threads/{thread_id}/runs",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"assistant_id": assistant_id,
"additional_instructions": additional_instructions,
"additional_messages": additional_messages,
"instructions": instructions,
"max_completion_tokens": max_completion_tokens,
"max_prompt_tokens": max_prompt_tokens,
"metadata": metadata,
"model": model,
"parallel_tool_calls": parallel_tool_calls,
"reasoning_effort": reasoning_effort,
"response_format": response_format,
Expand Down Expand Up @@ -976,14 +976,14 @@ def create_and_stream(
f"/threads/{thread_id}/runs",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"assistant_id": assistant_id,
"additional_instructions": additional_instructions,
"additional_messages": additional_messages,
"instructions": instructions,
"max_completion_tokens": max_completion_tokens,
"max_prompt_tokens": max_prompt_tokens,
"metadata": metadata,
"model": model,
"response_format": response_format,
"temperature": temperature,
"tool_choice": tool_choice,
Expand Down Expand Up @@ -1163,14 +1163,14 @@ def stream(
f"/threads/{thread_id}/runs",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"assistant_id": assistant_id,
"additional_instructions": additional_instructions,
"additional_messages": additional_messages,
"instructions": instructions,
"max_completion_tokens": max_completion_tokens,
"max_prompt_tokens": max_prompt_tokens,
"metadata": metadata,
"model": model,
"response_format": response_format,
"temperature": temperature,
"tool_choice": tool_choice,
Expand Down Expand Up @@ -2007,14 +2007,14 @@ async def create(
f"/threads/{thread_id}/runs",
body=await async_maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"assistant_id": assistant_id,
"additional_instructions": additional_instructions,
"additional_messages": additional_messages,
"instructions": instructions,
"max_completion_tokens": max_completion_tokens,
"max_prompt_tokens": max_prompt_tokens,
"metadata": metadata,
"model": model,
"parallel_tool_calls": parallel_tool_calls,
"reasoning_effort": reasoning_effort,
"response_format": response_format,
Expand Down Expand Up @@ -2409,14 +2409,14 @@ def create_and_stream(
f"/threads/{thread_id}/runs",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"assistant_id": assistant_id,
"additional_instructions": additional_instructions,
"additional_messages": additional_messages,
"instructions": instructions,
"max_completion_tokens": max_completion_tokens,
"max_prompt_tokens": max_prompt_tokens,
"metadata": metadata,
"model": model,
"response_format": response_format,
"temperature": temperature,
"tool_choice": tool_choice,
Expand Down Expand Up @@ -2596,14 +2596,14 @@ def stream(
f"/threads/{thread_id}/runs",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"assistant_id": assistant_id,
"additional_instructions": additional_instructions,
"additional_messages": additional_messages,
"instructions": instructions,
"max_completion_tokens": max_completion_tokens,
"max_prompt_tokens": max_prompt_tokens,
"metadata": metadata,
"model": model,
"response_format": response_format,
"temperature": temperature,
"tool_choice": tool_choice,
Expand Down
8 changes: 4 additions & 4 deletions src/openai/resources/beta/threads/threads.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -707,12 +707,12 @@ def create_and_run(
"/threads/runs",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"assistant_id": assistant_id,
"instructions": instructions,
"max_completion_tokens": max_completion_tokens,
"max_prompt_tokens": max_prompt_tokens,
"metadata": metadata,
"model": model,
"parallel_tool_calls": parallel_tool_calls,
"response_format": response_format,
"stream": stream,
Expand Down Expand Up @@ -888,12 +888,12 @@ def create_and_run_stream(
"/threads/runs",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"assistant_id": assistant_id,
"instructions": instructions,
"max_completion_tokens": max_completion_tokens,
"max_prompt_tokens": max_prompt_tokens,
"metadata": metadata,
"model": model,
"parallel_tool_calls": parallel_tool_calls,
"response_format": response_format,
"temperature": temperature,
Expand Down Expand Up @@ -1565,12 +1565,12 @@ async def create_and_run(
"/threads/runs",
body=await async_maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"assistant_id": assistant_id,
"instructions": instructions,
"max_completion_tokens": max_completion_tokens,
"max_prompt_tokens": max_prompt_tokens,
"metadata": metadata,
"model": model,
"parallel_tool_calls": parallel_tool_calls,
"response_format": response_format,
"stream": stream,
Expand Down Expand Up @@ -1750,12 +1750,12 @@ def create_and_run_stream(
"/threads/runs",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"assistant_id": assistant_id,
"instructions": instructions,
"max_completion_tokens": max_completion_tokens,
"max_prompt_tokens": max_prompt_tokens,
"metadata": metadata,
"model": model,
"parallel_tool_calls": parallel_tool_calls,
"response_format": response_format,
"temperature": temperature,
Expand Down
4 changes: 2 additions & 2 deletions src/openai/resources/chat/completions/completions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -926,8 +926,8 @@ def create(
"/chat/completions",
body=maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"messages": messages,
"model": model,
"audio": audio,
"frequency_penalty": frequency_penalty,
"function_call": function_call,
Expand Down Expand Up @@ -2029,8 +2029,8 @@ async def create(
"/chat/completions",
body=await async_maybe_transform(
{
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"messages": messages,
"model": model,
"audio": audio,
"frequency_penalty": frequency_penalty,
"function_call": function_call,
Expand Down
4 changes: 2 additions & 2 deletions src/openai/resources/completions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -542,7 +542,7 @@ def create(
"/completions",
body=maybe_transform(
{
"model": model,
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"prompt": prompt,
"best_of": best_of,
"echo": echo,
Expand Down Expand Up @@ -1092,7 +1092,7 @@ async def create(
"/completions",
body=await async_maybe_transform(
{
"model": model,
"model": model, # Always set model as the first field in the payload. In some proxies, this is used for routing. We don't want to read all messages specifically big ones for routing.
"prompt": prompt,
"best_of": best_of,
"echo": echo,
Expand Down
Loading