feat: extract out ImageModel, AudioModel, SpeechModel (openai#3)

jacobzim-stl · Aug 7, 2024 · 4b90869 · 4b90869
1 parent 103d454
commit 4b90869
Show file tree

Hide file tree

Showing 18 changed files with 95 additions and 226 deletions.
diff --git a/api.md b/api.md
@@ -87,6 +87,10 @@ Methods:
 
 # Images
 
+Params Types:
+
+- <a href="https://pkg.go.dev/github.com/openai/openai-go">openai</a>.<a href="https://pkg.go.dev/github.com/openai/openai-go#ImageModel">ImageModel</a>
+
 Response Types:
 
 - <a href="https://pkg.go.dev/github.com/openai/openai-go">openai</a>.<a href="https://pkg.go.dev/github.com/openai/openai-go#Image">Image</a>
@@ -100,6 +104,10 @@ Methods:
 
 # Audio
 
+Params Types:
+
+- <a href="https://pkg.go.dev/github.com/openai/openai-go">openai</a>.<a href="https://pkg.go.dev/github.com/openai/openai-go#AudioModel">AudioModel</a>
+
 ## Transcriptions
 
 Response Types:
@@ -122,12 +130,20 @@ Methods:
 
 ## Speech
 
+Params Types:
+
+- <a href="https://pkg.go.dev/github.com/openai/openai-go">openai</a>.<a href="https://pkg.go.dev/github.com/openai/openai-go#SpeechModel">SpeechModel</a>
+
 Methods:
 
 - <code title="post /audio/speech">client.Audio.Speech.<a href="https://pkg.go.dev/github.com/openai/openai-go#AudioSpeechService.New">New</a>(ctx <a href="https://pkg.go.dev/context">context</a>.<a href="https://pkg.go.dev/context#Context">Context</a>, body <a href="https://pkg.go.dev/github.com/openai/openai-go">openai</a>.<a href="https://pkg.go.dev/github.com/openai/openai-go#AudioSpeechNewParams">AudioSpeechNewParams</a>) (http.Response, <a href="https://pkg.go.dev/builtin#error">error</a>)</code>
 
 # Moderations
 
+Params Types:
+
+- <a href="https://pkg.go.dev/github.com/openai/openai-go">openai</a>.<a href="https://pkg.go.dev/github.com/openai/openai-go#ModerationModel">ModerationModel</a>
+
 Response Types:
 
 - <a href="https://pkg.go.dev/github.com/openai/openai-go">openai</a>.<a href="https://pkg.go.dev/github.com/openai/openai-go#Moderation">Moderation</a>

diff --git a/audio.go b/audio.go
@@ -30,3 +30,17 @@ func NewAudioService(opts ...option.RequestOption) (r *AudioService) {
 	r.Speech = NewAudioSpeechService(opts...)
 	return
 }
+
+type AudioModel string
+
+const (
+	AudioModelWhisper1 AudioModel = "whisper-1"
+)
+
+func (r AudioModel) IsKnown() bool {
+	switch r {
+	case AudioModelWhisper1:
+		return true
+	}
+	return false
+}
diff --git a/audiospeech.go b/audiospeech.go
@@ -40,12 +40,27 @@ func (r *AudioSpeechService) New(ctx context.Context, body AudioSpeechNewParams,
 	return
 }
 
+type SpeechModel string
+
+const (
+	SpeechModelTTS1   SpeechModel = "tts-1"
+	SpeechModelTTS1HD SpeechModel = "tts-1-hd"
+)
+
+func (r SpeechModel) IsKnown() bool {
+	switch r {
+	case SpeechModelTTS1, SpeechModelTTS1HD:
+		return true
+	}
+	return false
+}
+
 type AudioSpeechNewParams struct {
 	// The text to generate audio for. The maximum length is 4096 characters.
 	Input param.Field[string] `json:"input,required"`
 	// One of the available [TTS models](https://platform.openai.com/docs/models/tts):
 	// `tts-1` or `tts-1-hd`
-	Model param.Field[AudioSpeechNewParamsModel] `json:"model,required"`
+	Model param.Field[SpeechModel] `json:"model,required"`
 	// The voice to use when generating the audio. Supported voices are `alloy`,
 	// `echo`, `fable`, `onyx`, `nova`, and `shimmer`. Previews of the voices are
 	// available in the
@@ -63,21 +78,6 @@ func (r AudioSpeechNewParams) MarshalJSON() (data []byte, err error) {
 	return apijson.MarshalRoot(r)
 }
 
-type AudioSpeechNewParamsModel string
-
-const (
-	AudioSpeechNewParamsModelTTS1   AudioSpeechNewParamsModel = "tts-1"
-	AudioSpeechNewParamsModelTTS1HD AudioSpeechNewParamsModel = "tts-1-hd"
-)
-
-func (r AudioSpeechNewParamsModel) IsKnown() bool {
-	switch r {
-	case AudioSpeechNewParamsModelTTS1, AudioSpeechNewParamsModelTTS1HD:
-		return true
-	}
-	return false
-}
-
 // The voice to use when generating the audio. Supported voices are `alloy`,
 // `echo`, `fable`, `onyx`, `nova`, and `shimmer`. Previews of the voices are
 // available in the

diff --git a/audiospeech_test.go b/audiospeech_test.go
@@ -28,7 +28,7 @@ func TestAudioSpeechNewWithOptionalParams(t *testing.T) {
 	)
 	resp, err := client.Audio.Speech.New(context.TODO(), openai.AudioSpeechNewParams{
 		Input:          openai.F("input"),
-		Model:          openai.F(openai.AudioSpeechNewParamsModelTTS1),
+		Model:          openai.F(openai.SpeechModelTTS1),
 		Voice:          openai.F(openai.AudioSpeechNewParamsVoiceAlloy),
 		ResponseFormat: openai.F(openai.AudioSpeechNewParamsResponseFormatMP3),
 		Speed:          openai.F(0.250000),

diff --git a/audiotranscription.go b/audiotranscription.go
@@ -72,7 +72,7 @@ type AudioTranscriptionNewParams struct {
 	File param.Field[io.Reader] `json:"file,required" format:"binary"`
 	// ID of the model to use. Only `whisper-1` (which is powered by our open source
 	// Whisper V2 model) is currently available.
-	Model param.Field[AudioTranscriptionNewParamsModel] `json:"model,required"`
+	Model param.Field[AudioModel] `json:"model,required"`
 	// The language of the input audio. Supplying the input language in
 	// [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format will
 	// improve accuracy and latency.
@@ -114,20 +114,6 @@ func (r AudioTranscriptionNewParams) MarshalMultipart() (data []byte, contentTyp
 	return buf.Bytes(), writer.FormDataContentType(), nil
 }
 
-type AudioTranscriptionNewParamsModel string
-
-const (
-	AudioTranscriptionNewParamsModelWhisper1 AudioTranscriptionNewParamsModel = "whisper-1"
-)
-
-func (r AudioTranscriptionNewParamsModel) IsKnown() bool {
-	switch r {
-	case AudioTranscriptionNewParamsModelWhisper1:
-		return true
-	}
-	return false
-}
-
 // The format of the transcript output, in one of these options: `json`, `text`,
 // `srt`, `verbose_json`, or `vtt`.
 type AudioTranscriptionNewParamsResponseFormat string

diff --git a/audiotranscription_test.go b/audiotranscription_test.go
@@ -29,7 +29,7 @@ func TestAudioTranscriptionNewWithOptionalParams(t *testing.T) {
 	)
 	_, err := client.Audio.Transcriptions.New(context.TODO(), openai.AudioTranscriptionNewParams{
 		File:                   openai.F(io.Reader(bytes.NewBuffer([]byte("some file contents")))),
-		Model:                  openai.F(openai.AudioTranscriptionNewParamsModelWhisper1),
+		Model:                  openai.F(openai.AudioModelWhisper1),
 		Language:               openai.F("language"),
 		Prompt:                 openai.F("prompt"),
 		ResponseFormat:         openai.F(openai.AudioTranscriptionNewParamsResponseFormatJSON),

diff --git a/audiotranslation.go b/audiotranslation.go
@@ -69,7 +69,7 @@ type AudioTranslationNewParams struct {
 	File param.Field[io.Reader] `json:"file,required" format:"binary"`
 	// ID of the model to use. Only `whisper-1` (which is powered by our open source
 	// Whisper V2 model) is currently available.
-	Model param.Field[AudioTranslationNewParamsModel] `json:"model,required"`
+	Model param.Field[AudioModel] `json:"model,required"`
 	// An optional text to guide the model's style or continue a previous audio
 	// segment. The
 	// [prompt](https://platform.openai.com/docs/guides/speech-to-text/prompting)
@@ -100,17 +100,3 @@ func (r AudioTranslationNewParams) MarshalMultipart() (data []byte, contentType
 	}
 	return buf.Bytes(), writer.FormDataContentType(), nil
 }
-
-type AudioTranslationNewParamsModel string
-
-const (
-	AudioTranslationNewParamsModelWhisper1 AudioTranslationNewParamsModel = "whisper-1"
-)
-
-func (r AudioTranslationNewParamsModel) IsKnown() bool {
-	switch r {
-	case AudioTranslationNewParamsModelWhisper1:
-		return true
-	}
-	return false
-}
diff --git a/audiotranslation_test.go b/audiotranslation_test.go
@@ -29,7 +29,7 @@ func TestAudioTranslationNewWithOptionalParams(t *testing.T) {
 	)
 	_, err := client.Audio.Translations.New(context.TODO(), openai.AudioTranslationNewParams{
 		File:           openai.F(io.Reader(bytes.NewBuffer([]byte("some file contents")))),
-		Model:          openai.F(openai.AudioTranslationNewParamsModelWhisper1),
+		Model:          openai.F(openai.AudioModelWhisper1),
 		Prompt:         openai.F("prompt"),
 		ResponseFormat: openai.F("response_format"),
 		Temperature:    openai.F(0.000000),

diff --git a/betaassistant.go b/betaassistant.go
@@ -1988,7 +1988,7 @@ type BetaAssistantNewParams struct {
 	// see all of your available models, or see our
 	// [Model overview](https://platform.openai.com/docs/models/overview) for
 	// descriptions of them.
-	Model param.Field[BetaAssistantNewParamsModel] `json:"model,required"`
+	Model param.Field[ChatModel] `json:"model,required"`
 	// The description of the assistant. The maximum length is 512 characters.
 	Description param.Field[string] `json:"description"`
 	// The system instructions that the assistant uses. The maximum length is 256,000
@@ -2042,41 +2042,6 @@ func (r BetaAssistantNewParams) MarshalJSON() (data []byte, err error) {
 	return apijson.MarshalRoot(r)
 }
 
-type BetaAssistantNewParamsModel string
-
-const (
-	BetaAssistantNewParamsModelGPT4o               BetaAssistantNewParamsModel = "gpt-4o"
-	BetaAssistantNewParamsModelGPT4o2024_05_13     BetaAssistantNewParamsModel = "gpt-4o-2024-05-13"
-	BetaAssistantNewParamsModelGPT4oMini           BetaAssistantNewParamsModel = "gpt-4o-mini"
-	BetaAssistantNewParamsModelGPT4oMini2024_07_18 BetaAssistantNewParamsModel = "gpt-4o-mini-2024-07-18"
-	BetaAssistantNewParamsModelGPT4Turbo           BetaAssistantNewParamsModel = "gpt-4-turbo"
-	BetaAssistantNewParamsModelGPT4Turbo2024_04_09 BetaAssistantNewParamsModel = "gpt-4-turbo-2024-04-09"
-	BetaAssistantNewParamsModelGPT4_0125Preview    BetaAssistantNewParamsModel = "gpt-4-0125-preview"
-	BetaAssistantNewParamsModelGPT4TurboPreview    BetaAssistantNewParamsModel = "gpt-4-turbo-preview"
-	BetaAssistantNewParamsModelGPT4_1106Preview    BetaAssistantNewParamsModel = "gpt-4-1106-preview"
-	BetaAssistantNewParamsModelGPT4VisionPreview   BetaAssistantNewParamsModel = "gpt-4-vision-preview"
-	BetaAssistantNewParamsModelGPT4                BetaAssistantNewParamsModel = "gpt-4"
-	BetaAssistantNewParamsModelGPT4_0314           BetaAssistantNewParamsModel = "gpt-4-0314"
-	BetaAssistantNewParamsModelGPT4_0613           BetaAssistantNewParamsModel = "gpt-4-0613"
-	BetaAssistantNewParamsModelGPT4_32k            BetaAssistantNewParamsModel = "gpt-4-32k"
-	BetaAssistantNewParamsModelGPT4_32k0314        BetaAssistantNewParamsModel = "gpt-4-32k-0314"
-	BetaAssistantNewParamsModelGPT4_32k0613        BetaAssistantNewParamsModel = "gpt-4-32k-0613"
-	BetaAssistantNewParamsModelGPT3_5Turbo         BetaAssistantNewParamsModel = "gpt-3.5-turbo"
-	BetaAssistantNewParamsModelGPT3_5Turbo16k      BetaAssistantNewParamsModel = "gpt-3.5-turbo-16k"
-	BetaAssistantNewParamsModelGPT3_5Turbo0613     BetaAssistantNewParamsModel = "gpt-3.5-turbo-0613"
-	BetaAssistantNewParamsModelGPT3_5Turbo1106     BetaAssistantNewParamsModel = "gpt-3.5-turbo-1106"
-	BetaAssistantNewParamsModelGPT3_5Turbo0125     BetaAssistantNewParamsModel = "gpt-3.5-turbo-0125"
-	BetaAssistantNewParamsModelGPT3_5Turbo16k0613  BetaAssistantNewParamsModel = "gpt-3.5-turbo-16k-0613"
-)
-
-func (r BetaAssistantNewParamsModel) IsKnown() bool {
-	switch r {
-	case BetaAssistantNewParamsModelGPT4o, BetaAssistantNewParamsModelGPT4o2024_05_13, BetaAssistantNewParamsModelGPT4oMini, BetaAssistantNewParamsModelGPT4oMini2024_07_18, BetaAssistantNewParamsModelGPT4Turbo, BetaAssistantNewParamsModelGPT4Turbo2024_04_09, BetaAssistantNewParamsModelGPT4_0125Preview, BetaAssistantNewParamsModelGPT4TurboPreview, BetaAssistantNewParamsModelGPT4_1106Preview, BetaAssistantNewParamsModelGPT4VisionPreview, BetaAssistantNewParamsModelGPT4, BetaAssistantNewParamsModelGPT4_0314, BetaAssistantNewParamsModelGPT4_0613, BetaAssistantNewParamsModelGPT4_32k, BetaAssistantNewParamsModelGPT4_32k0314, BetaAssistantNewParamsModelGPT4_32k0613, BetaAssistantNewParamsModelGPT3_5Turbo, BetaAssistantNewParamsModelGPT3_5Turbo16k, BetaAssistantNewParamsModelGPT3_5Turbo0613, BetaAssistantNewParamsModelGPT3_5Turbo1106, BetaAssistantNewParamsModelGPT3_5Turbo0125, BetaAssistantNewParamsModelGPT3_5Turbo16k0613:
-		return true
-	}
-	return false
-}
-
 // A set of resources that are used by the assistant's tools. The resources are
 // specific to the type of tool. For example, the `code_interpreter` tool requires
 // a list of file IDs, while the `file_search` tool requires a list of vector store

diff --git a/betaassistant_test.go b/betaassistant_test.go
@@ -26,7 +26,7 @@ func TestBetaAssistantNewWithOptionalParams(t *testing.T) {
 		option.WithAPIKey("My API Key"),
 	)
 	_, err := client.Beta.Assistants.New(context.TODO(), openai.BetaAssistantNewParams{
-		Model:          openai.F(openai.BetaAssistantNewParamsModelGPT4o),
+		Model:          openai.F(openai.ChatModelGPT4o),
 		Description:    openai.F("description"),
 		Instructions:   openai.F("instructions"),
 		Metadata:       openai.F[any](map[string]interface{}{}),

diff --git a/betathread.go b/betathread.go
@@ -972,7 +972,7 @@ type BetaThreadNewAndRunParams struct {
 	// be used to execute this run. If a value is provided here, it will override the
 	// model associated with the assistant. If not, the model associated with the
 	// assistant will be used.
-	Model param.Field[BetaThreadNewAndRunParamsModel] `json:"model"`
+	Model param.Field[ChatModel] `json:"model"`
 	// Whether to enable
 	// [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
 	// during tool use.
@@ -1030,41 +1030,6 @@ func (r BetaThreadNewAndRunParams) MarshalJSON() (data []byte, err error) {
 	return apijson.MarshalRoot(r)
 }
 
-type BetaThreadNewAndRunParamsModel string
-
-const (
-	BetaThreadNewAndRunParamsModelGPT4o               BetaThreadNewAndRunParamsModel = "gpt-4o"
-	BetaThreadNewAndRunParamsModelGPT4o2024_05_13     BetaThreadNewAndRunParamsModel = "gpt-4o-2024-05-13"
-	BetaThreadNewAndRunParamsModelGPT4oMini           BetaThreadNewAndRunParamsModel = "gpt-4o-mini"
-	BetaThreadNewAndRunParamsModelGPT4oMini2024_07_18 BetaThreadNewAndRunParamsModel = "gpt-4o-mini-2024-07-18"
-	BetaThreadNewAndRunParamsModelGPT4Turbo           BetaThreadNewAndRunParamsModel = "gpt-4-turbo"
-	BetaThreadNewAndRunParamsModelGPT4Turbo2024_04_09 BetaThreadNewAndRunParamsModel = "gpt-4-turbo-2024-04-09"
-	BetaThreadNewAndRunParamsModelGPT4_0125Preview    BetaThreadNewAndRunParamsModel = "gpt-4-0125-preview"
-	BetaThreadNewAndRunParamsModelGPT4TurboPreview    BetaThreadNewAndRunParamsModel = "gpt-4-turbo-preview"
-	BetaThreadNewAndRunParamsModelGPT4_1106Preview    BetaThreadNewAndRunParamsModel = "gpt-4-1106-preview"
-	BetaThreadNewAndRunParamsModelGPT4VisionPreview   BetaThreadNewAndRunParamsModel = "gpt-4-vision-preview"
-	BetaThreadNewAndRunParamsModelGPT4                BetaThreadNewAndRunParamsModel = "gpt-4"
-	BetaThreadNewAndRunParamsModelGPT4_0314           BetaThreadNewAndRunParamsModel = "gpt-4-0314"
-	BetaThreadNewAndRunParamsModelGPT4_0613           BetaThreadNewAndRunParamsModel = "gpt-4-0613"
-	BetaThreadNewAndRunParamsModelGPT4_32k            BetaThreadNewAndRunParamsModel = "gpt-4-32k"
-	BetaThreadNewAndRunParamsModelGPT4_32k0314        BetaThreadNewAndRunParamsModel = "gpt-4-32k-0314"
-	BetaThreadNewAndRunParamsModelGPT4_32k0613        BetaThreadNewAndRunParamsModel = "gpt-4-32k-0613"
-	BetaThreadNewAndRunParamsModelGPT3_5Turbo         BetaThreadNewAndRunParamsModel = "gpt-3.5-turbo"
-	BetaThreadNewAndRunParamsModelGPT3_5Turbo16k      BetaThreadNewAndRunParamsModel = "gpt-3.5-turbo-16k"
-	BetaThreadNewAndRunParamsModelGPT3_5Turbo0613     BetaThreadNewAndRunParamsModel = "gpt-3.5-turbo-0613"
-	BetaThreadNewAndRunParamsModelGPT3_5Turbo1106     BetaThreadNewAndRunParamsModel = "gpt-3.5-turbo-1106"
-	BetaThreadNewAndRunParamsModelGPT3_5Turbo0125     BetaThreadNewAndRunParamsModel = "gpt-3.5-turbo-0125"
-	BetaThreadNewAndRunParamsModelGPT3_5Turbo16k0613  BetaThreadNewAndRunParamsModel = "gpt-3.5-turbo-16k-0613"
-)
-
-func (r BetaThreadNewAndRunParamsModel) IsKnown() bool {
-	switch r {
-	case BetaThreadNewAndRunParamsModelGPT4o, BetaThreadNewAndRunParamsModelGPT4o2024_05_13, BetaThreadNewAndRunParamsModelGPT4oMini, BetaThreadNewAndRunParamsModelGPT4oMini2024_07_18, BetaThreadNewAndRunParamsModelGPT4Turbo, BetaThreadNewAndRunParamsModelGPT4Turbo2024_04_09, BetaThreadNewAndRunParamsModelGPT4_0125Preview, BetaThreadNewAndRunParamsModelGPT4TurboPreview, BetaThreadNewAndRunParamsModelGPT4_1106Preview, BetaThreadNewAndRunParamsModelGPT4VisionPreview, BetaThreadNewAndRunParamsModelGPT4, BetaThreadNewAndRunParamsModelGPT4_0314, BetaThreadNewAndRunParamsModelGPT4_0613, BetaThreadNewAndRunParamsModelGPT4_32k, BetaThreadNewAndRunParamsModelGPT4_32k0314, BetaThreadNewAndRunParamsModelGPT4_32k0613, BetaThreadNewAndRunParamsModelGPT3_5Turbo, BetaThreadNewAndRunParamsModelGPT3_5Turbo16k, BetaThreadNewAndRunParamsModelGPT3_5Turbo0613, BetaThreadNewAndRunParamsModelGPT3_5Turbo1106, BetaThreadNewAndRunParamsModelGPT3_5Turbo0125, BetaThreadNewAndRunParamsModelGPT3_5Turbo16k0613:
-		return true
-	}
-	return false
-}
-
 // If no thread is provided, an empty thread will be created.
 type BetaThreadNewAndRunParamsThread struct {
 	// A list of [messages](https://platform.openai.com/docs/api-reference/messages) to

diff --git a/betathread_test.go b/betathread_test.go
@@ -248,7 +248,7 @@ func TestBetaThreadNewAndRunWithOptionalParams(t *testing.T) {
 		MaxCompletionTokens: openai.F(int64(256)),
 		MaxPromptTokens:     openai.F(int64(256)),
 		Metadata:            openai.F[any](map[string]interface{}{}),
-		Model:               openai.F(openai.BetaThreadNewAndRunParamsModelGPT4o),
+		Model:               openai.F(openai.ChatModelGPT4o),
 		ParallelToolCalls:   openai.F(true),
 		ResponseFormat:      openai.F[openai.AssistantResponseFormatOptionUnionParam](openai.AssistantResponseFormatOptionString(openai.AssistantResponseFormatOptionStringNone)),
 		Temperature:         openai.F(1.000000),