加入imagetotext.py

text2image.py

@@ -0,0 +1,55 @@
+import os
+import logging
+from io import BytesIO
+from PIL import Image
+import gradio as gr
+from google import genai
+from google.genai import types
+
+# 設定 logging
+logging.basicConfig(
+    filename='app.log',
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s'
+)
+
+# 初始化 Gemini API
+GEMINI_API_KEY = os.environ.get("GEMINI_API_KEY")
+client = genai.Client(api_key=GEMINI_API_KEY)
+
+# 定義「圖解釋文」功能
+def explain_image(image: Image.Image):
+    # 將 PIL Image 轉成 Gemini 所需的格式
+    buffered = BytesIO()
+    image.save(buffered, format="PNG")
+    image_data = buffered.getvalue()
+
+    # 準備輸入給 Gemini 的內容
+    contents = [
+        types.ContentPart.from_data(data=image_data, mime_type="image/png"),
+        types.ContentPart.text("請用繁體中文說明這張圖片的內容。")
+    ]
+
+    # 呼叫 Gemini 模型
+    response = client.models.generate_content(
+        model="gemini-1.5-flash",
+        contents=contents,
+        config=types.GenerateContentConfig(response_modalities=["TEXT"])
+    )
+
+    # 回傳第一個回答
+    explanation = response.candidates[0].content.parts[0].text
+    logging.info("圖片說明成功取得。")
+    return explanation
+
+# Gradio 介面
+with gr.Blocks() as demo:
+    gr.Markdown("## 🧠 Gemini 圖片解釋器（圖 ➜ 文）")
+    image_input = gr.Image(type="pil", label="上傳圖片")
+    explain_button = gr.Button("解釋圖片")
+    output_text = gr.Textbox(label="圖片說明", lines=5)
+
+    explain_button.click(fn=explain_image, inputs=image_input, outputs=output_text)
+
+if __name__ == "__main__":
+    demo.launch()