Merge pull request #12 from nbox363/feat/image_to_text_model

Add model field to ImageToTextParams

examples/image_to_text/main.go

@@ -8,7 +8,8 @@ import (
 	_ "github.com/joho/godotenv/autoload"
 
 	"github.com/neurocult/agency"
-	"github.com/neurocult/agency/providers/openai"
+	openAIProvider "github.com/neurocult/agency/providers/openai"
+	"github.com/sashabaranov/go-openai"
 )
 
 func main() {
@@ -17,8 +18,8 @@ func main() {
 		panic(err)
 	}
 
-	result, err := openai.New(openai.Params{Key: os.Getenv("OPENAI_API_KEY")}).
-		ImageToText(openai.ImageToTextParams{MaxTokens: 300}).
+	result, err := openAIProvider.New(openAIProvider.Params{Key: os.Getenv("OPENAI_API_KEY")}).
+		ImageToText(openAIProvider.ImageToTextParams{Model: openai.GPT4o, MaxTokens: 300}).
 		SetPrompt("describe what you see").
 		Execute(
 			context.Background(),

go.mod

@@ -3,7 +3,7 @@ module github.com/neurocult/agency
 go 1.21.0
 
 require (
-	github.com/sashabaranov/go-openai v1.21.0
+	github.com/sashabaranov/go-openai v1.36.1
 	github.com/weaviate/weaviate v1.24.8
 	github.com/weaviate/weaviate-go-client/v4 v4.13.1
 )

go.sum

@@ -50,6 +50,8 @@ github.com/rogpeppe/go-internal v1.11.0 h1:cWPaGQEPrBb5/AsnsZesgZZ9yb1OQ+GOISoDN
 github.com/rogpeppe/go-internal v1.11.0/go.mod h1:ddIwULY96R17DhadqLgMfk9H9tvdUzkipdSkR5nkCZA=
 github.com/sashabaranov/go-openai v1.21.0 h1:isAf3zPSD3VLd0pC2/2Q6ZyRK7jzPAaz+X3rjsviaYQ=
 github.com/sashabaranov/go-openai v1.21.0/go.mod h1:lj5b/K+zjTSFxVLijLSTDZuP7adOgerWeFyZLUhAKRg=
+github.com/sashabaranov/go-openai v1.36.1 h1:EVfRXwIlW2rUzpx6vR+aeIKCK/xylSrVYAx1TMTSX3g=
+github.com/sashabaranov/go-openai v1.36.1/go.mod h1:lj5b/K+zjTSFxVLijLSTDZuP7adOgerWeFyZLUhAKRg=
 github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
 github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/weaviate/weaviate v1.24.8 h1:obeBOJuXScDvUlbTKuqPwJl/cUB5csRhCN6q4smcQiM=

providers/openai/image_to_text.go

@@ -11,6 +11,7 @@ import (
 )
 
 type ImageToTextParams struct {
+	Model            string
 	MaxTokens        int
 	Temperature      NullableFloat32
 	TopP             NullableFloat32
@@ -45,7 +46,7 @@ func (f *Provider) ImageToText(params ImageToTextParams) *agency.Operation {
 
 		resp, err := f.client.CreateChatCompletion(ctx, openai.ChatCompletionRequest{
 			MaxTokens:        params.MaxTokens,
-			Model:            openai.GPT4Turbo,
+			Model:            params.Model,
 			Messages:         []openai.ChatCompletionMessage{openaiMsg},
 			Temperature:      nullableToFloat32(params.Temperature),
 			TopP:             nullableToFloat32(params.TopP),