feat: you can summary screen shot directly
This commit is contained in:
@@ -0,0 +1,72 @@
|
||||
package application
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"time"
|
||||
|
||||
"github.com/mmmy/snapgo/internal/domain"
|
||||
"github.com/mmmy/snapgo/internal/infrastructure/clipboard"
|
||||
)
|
||||
|
||||
// VisionSummarizer describes a multimodal model capable of reading a public
|
||||
// image URL and returning a textual summary.
|
||||
type VisionSummarizer interface {
|
||||
SummarizeImage(ctx context.Context, prompt string, imageURL string) (string, error)
|
||||
}
|
||||
|
||||
// CaptureSummaryService wires screenshot bytes -> S3 public URL -> LLM
|
||||
// summary -> clipboard. It intentionally does not notify UI state itself:
|
||||
// the caller emits fine-grained "uploading / recognizing / done" progress.
|
||||
type CaptureSummaryService struct {
|
||||
Provider domain.OSSProvider
|
||||
Summarizer VisionSummarizer
|
||||
Clipboard clipboard.Writer
|
||||
Prompt string
|
||||
PathPrefix string
|
||||
}
|
||||
|
||||
// UploadImage uploads the screenshot and returns the public URL visible to
|
||||
// the multimodal provider.
|
||||
func (s *CaptureSummaryService) UploadImage(ctx context.Context, pngBytes []byte) (*domain.UploadResult, error) {
|
||||
if s.Provider == nil {
|
||||
return nil, fmt.Errorf("s3 is not configured")
|
||||
}
|
||||
if len(pngBytes) == 0 {
|
||||
return nil, fmt.Errorf("empty screenshot")
|
||||
}
|
||||
key := buildObjectKey(s.PathPrefix)
|
||||
start := time.Now()
|
||||
url, err := s.Provider.Upload(ctx, key, pngBytes, "image/png")
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("s3 put object: %w", err)
|
||||
}
|
||||
return &domain.UploadResult{
|
||||
URL: url,
|
||||
Key: key,
|
||||
Provider: s.Provider.Name(),
|
||||
Elapsed: time.Since(start),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Summarize asks the configured model to summarize the uploaded image URL.
|
||||
func (s *CaptureSummaryService) Summarize(ctx context.Context, imageURL string) (string, error) {
|
||||
if s.Summarizer == nil {
|
||||
return "", fmt.Errorf("llm is not configured")
|
||||
}
|
||||
return s.Summarizer.SummarizeImage(ctx, s.Prompt, imageURL)
|
||||
}
|
||||
|
||||
// CopySummary writes the final summary text to the clipboard.
|
||||
func (s *CaptureSummaryService) CopySummary(_ context.Context, summary string) error {
|
||||
if summary == "" {
|
||||
return fmt.Errorf("empty summary")
|
||||
}
|
||||
if s.Clipboard == nil {
|
||||
return fmt.Errorf("clipboard is not configured")
|
||||
}
|
||||
if err := s.Clipboard.WriteText(summary); err != nil {
|
||||
return fmt.Errorf("clipboard write failed: %w", err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
Reference in New Issue
Block a user