Use the streamed response API

main.go

@@ -107,13 +107,13 @@ var newCmd = &cobra.Command{
 			},
 		}
 
-		response, err := CreateChatCompletion("You are a helpful assistant.", messages)
+		err = CreateChatCompletionStream("You are a helpful assistant.", messages, os.Stdout)
 		if err != nil {
-			fmt.Fprintf(os.Stderr, "Error getting chat response: %v\n", err)
+			fmt.Fprintf(os.Stderr, "An error occured: %v\n", err)
 			os.Exit(1)
 		}
 
-		fmt.Println(response);
+		fmt.Println()
 	},
 }
 

openai.go

@@ -2,7 +2,9 @@ package main
 
 import (
 	"context"
+	"errors"
 	"fmt"
+	"io"
 	"os"
 	openai "github.com/sashabaranov/go-openai"
 )
@@ -34,3 +36,45 @@ func CreateChatCompletion(system string, messages []Message) (string, error) {
 
 	return resp.Choices[0].Message.Content, nil
 }
+
+func CreateChatCompletionStream(system string, messages []Message, output io.Writer) (error) {
+	client := openai.NewClient(os.Getenv("OPENAI_APIKEY"))
+	ctx := context.Background()
+
+
+	var chatCompletionMessages []openai.ChatCompletionMessage
+	for _, m := range(messages) {
+		chatCompletionMessages = append(chatCompletionMessages, openai.ChatCompletionMessage{
+			Role: m.Role,
+			Content: m.OriginalContent,
+		})
+	}
+
+	req := openai.ChatCompletionRequest{
+		Model:     openai.GPT3Dot5Turbo,
+		MaxTokens: 20,
+		Messages: chatCompletionMessages,
+		Stream: true,
+	}
+
+	stream, err := client.CreateChatCompletionStream(ctx, req)
+	if err != nil {
+		return err
+	}
+
+	defer stream.Close()
+
+	for {
+		response, err := stream.Recv()
+		if errors.Is(err, io.EOF) {
+			return nil
+		}
+
+		if err != nil {
+			//fmt.Printf("\nStream error: %v\n", err)
+			return err
+		}
+
+		fmt.Fprint(output, response.Choices[0].Delta.Content)
+	}
+}