Upload 2 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+workbook.db filter=lfs diff=lfs merge=lfs -text

workbook_server.py

@@ -55,23 +55,24 @@ class ChapterRequest(BaseModel):
 def get_questions_by_chapter(request: ChapterRequest):
     db = get_db()
     cursor = db.cursor()
-    cursor.execute("SELECT question, options, answer, explain FROM question WHERE chapter = ? AND kind = '正誤問題'", (request.chapter_number,))
+    cursor.execute("SELECT question, options, answer, explain, image FROM question WHERE chapter = ? AND kind = '正誤問題'", (request.chapter_number,))
     questions = cursor.fetchall()
     if not questions:
         raise HTTPException(status_code=404, detail="Questions not found for the given chapter number")
     question_list = []
     for row in questions:
-        '''
-        image_path = os.path.join('./image', row[4])
-        with open(image_path, "rb") as image_file:
-            encoded_string = base64.b64encode(image_file.read()).decode('utf-8')
-        '''
+        if row[4] is None:
+            encoded_string = ''
+        else:
+            image_path = os.path.join('./image', row[4])
+            with open(image_path, "rb") as image_file:
+                encoded_string = base64.b64encode(image_file.read()).decode('utf-8')
         question_list.append({
             "question_text": row[0],
             "options": row[1],
             "answer": row[2],
             "explanation": row[3],
-            # "image": encoded_string,
+            "image": encoded_string,
         })
     return JSONResponse(content=question_list)
 
@@ -83,6 +84,7 @@ class HintRequest(BaseModel):
 @app.post('/api/hint')
 def generate_hint(request: HintRequest):
     prompt = f"設問: {request.question_text}\n選択肢: {request.options}\n正解: {request.answer}\nこの設問に対するヒントを生成してください。なおレスポンスはヒント文章のみとせよ。冒頭に「ヒント：」などの見出しをつけるな。"
+    print(prompt)
     try:
         response = client.chat.completions.create(
             model="gpt-4o-mini",