release: 1.52.0

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "1.51.2"
+  ".": "1.52.0"
 }

.stats.yml

@@ -1,2 +1,2 @@
 configured_endpoints: 68
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-52b934aee6468039ec7f4ce046a282b5fbce114afc708e70f17121df654f71da.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-8729aaa35436531ab453224af10e67f89677db8f350f0346bb3537489edea649.yml

CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 1.52.0 (2024-10-17)
+
+Full Changelog: [v1.51.2...v1.52.0](https://github.com/openai/openai-python/compare/v1.51.2...v1.52.0)
+
+### Features
+
+* **api:** add gpt-4o-audio-preview model for chat completions ([#1796](https://github.com/openai/openai-python/issues/1796)) ([fbf1e0c](https://github.com/openai/openai-python/commit/fbf1e0c25c4d163f06b61a43d1a94ce001033a7b))
+
 ## 1.51.2 (2024-10-08)
 
 Full Changelog: [v1.51.1...v1.51.2](https://github.com/openai/openai-python/compare/v1.51.1...v1.51.2)

api.md

@@ -39,16 +39,20 @@ Types:
 from openai.types.chat import (
     ChatCompletion,
     ChatCompletionAssistantMessageParam,
+    ChatCompletionAudio,
+    ChatCompletionAudioParam,
     ChatCompletionChunk,
     ChatCompletionContentPart,
     ChatCompletionContentPartImage,
+    ChatCompletionContentPartInputAudio,
     ChatCompletionContentPartRefusal,
     ChatCompletionContentPartText,
     ChatCompletionFunctionCallOption,
     ChatCompletionFunctionMessageParam,
     ChatCompletionMessage,
     ChatCompletionMessageParam,
     ChatCompletionMessageToolCall,
+    ChatCompletionModality,
     ChatCompletionNamedToolChoice,
     ChatCompletionRole,
     ChatCompletionStreamOptions,

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "openai"
-version = "1.51.2"
+version = "1.52.0"
 description = "The official Python library for the openai API"
 dynamic = ["readme"]
 license = "Apache-2.0"

src/openai/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "openai"
-__version__ = "1.51.2"  # x-release-please-version
+__version__ = "1.52.0"  # x-release-please-version

src/openai/resources/beta/chat/completions.py

@@ -28,7 +28,9 @@
 from ....types.chat.chat_completion import ChatCompletion
 from ....types.chat.chat_completion_chunk import ChatCompletionChunk
 from ....types.chat.parsed_chat_completion import ParsedChatCompletion
+from ....types.chat.chat_completion_modality import ChatCompletionModality
 from ....types.chat.chat_completion_tool_param import ChatCompletionToolParam
+from ....types.chat.chat_completion_audio_param import ChatCompletionAudioParam
 from ....types.chat.chat_completion_message_param import ChatCompletionMessageParam
 from ....types.chat.chat_completion_stream_options_param import ChatCompletionStreamOptionsParam
 from ....types.chat.chat_completion_tool_choice_option_param import ChatCompletionToolChoiceOptionParam
@@ -61,6 +63,7 @@ def parse(
         *,
         messages: Iterable[ChatCompletionMessageParam],
         model: Union[str, ChatModel],
+        audio: Optional[ChatCompletionAudioParam] | NotGiven = NOT_GIVEN,
         response_format: type[ResponseFormatT] | NotGiven = NOT_GIVEN,
         frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN,
@@ -70,6 +73,7 @@ def parse(
         max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
@@ -153,6 +157,7 @@ def parser(raw_completion: ChatCompletion) -> ParsedChatCompletion[ResponseForma
                 {
                     "messages": messages,
                     "model": model,
+                    "audio": audio,
                     "frequency_penalty": frequency_penalty,
                     "function_call": function_call,
                     "functions": functions,
@@ -161,6 +166,7 @@ def parser(raw_completion: ChatCompletion) -> ParsedChatCompletion[ResponseForma
                     "max_completion_tokens": max_completion_tokens,
                     "max_tokens": max_tokens,
                     "metadata": metadata,
+                    "modalities": modalities,
                     "n": n,
                     "parallel_tool_calls": parallel_tool_calls,
                     "presence_penalty": presence_penalty,
@@ -198,6 +204,7 @@ def stream(
         *,
         messages: Iterable[ChatCompletionMessageParam],
         model: Union[str, ChatModel],
+        audio: Optional[ChatCompletionAudioParam] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | type[ResponseFormatT] | NotGiven = NOT_GIVEN,
         frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN,
@@ -207,6 +214,7 @@ def stream(
         max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
@@ -259,6 +267,7 @@ def stream(
             self._client.chat.completions.create,
             messages=messages,
             model=model,
+            audio=audio,
             stream=True,
             response_format=_type_to_response_format(response_format),
             frequency_penalty=frequency_penalty,
@@ -269,6 +278,7 @@ def stream(
             max_completion_tokens=max_completion_tokens,
             max_tokens=max_tokens,
             metadata=metadata,
+            modalities=modalities,
             n=n,
             parallel_tool_calls=parallel_tool_calls,
             presence_penalty=presence_penalty,
@@ -320,6 +330,7 @@ async def parse(
         *,
         messages: Iterable[ChatCompletionMessageParam],
         model: Union[str, ChatModel],
+        audio: Optional[ChatCompletionAudioParam] | NotGiven = NOT_GIVEN,
         response_format: type[ResponseFormatT] | NotGiven = NOT_GIVEN,
         frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN,
@@ -329,6 +340,7 @@ async def parse(
         max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
@@ -412,6 +424,7 @@ def parser(raw_completion: ChatCompletion) -> ParsedChatCompletion[ResponseForma
                 {
                     "messages": messages,
                     "model": model,
+                    "audio": audio,
                     "frequency_penalty": frequency_penalty,
                     "function_call": function_call,
                     "functions": functions,
@@ -420,6 +433,7 @@ def parser(raw_completion: ChatCompletion) -> ParsedChatCompletion[ResponseForma
                     "max_completion_tokens": max_completion_tokens,
                     "max_tokens": max_tokens,
                     "metadata": metadata,
+                    "modalities": modalities,
                     "n": n,
                     "parallel_tool_calls": parallel_tool_calls,
                     "presence_penalty": presence_penalty,
@@ -457,6 +471,7 @@ def stream(
         *,
         messages: Iterable[ChatCompletionMessageParam],
         model: Union[str, ChatModel],
+        audio: Optional[ChatCompletionAudioParam] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | type[ResponseFormatT] | NotGiven = NOT_GIVEN,
         frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN,
@@ -466,6 +481,7 @@ def stream(
         max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
@@ -519,6 +535,7 @@ def stream(
         api_request = self._client.chat.completions.create(
             messages=messages,
             model=model,
+            audio=audio,
             stream=True,
             response_format=_type_to_response_format(response_format),
             frequency_penalty=frequency_penalty,
@@ -529,6 +546,7 @@ def stream(
             max_completion_tokens=max_completion_tokens,
             max_tokens=max_tokens,
             metadata=metadata,
+            modalities=modalities,
             n=n,
             parallel_tool_calls=parallel_tool_calls,
             presence_penalty=presence_penalty,